CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-08-31 18:30:39 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(evals): every E2E key's dep list names its own declaring test file

Browse Source 
129-of-177 keys omitted their own test file, so editing only a test's
prompt or assertions selected NOTHING — the changed test never ran on
the change that changed it. 135 keys self-registered (110 E2E + 25
LLM-judge), resolved by strict declaration evidence (testName:/
testIfSelected/judge call sites), with skill-name false positives
excluded.

e2e-tier-alignment's warn-only branch for unregistered files is now a
hard failure with a 4-entry KNOWN_UNREGISTERED ratchet (template-
literal testNames, fail-open-safe) + a burn-down test so the set only
shrinks. Selection sanity: a one-file diff on skill-e2e-qa-workflow now
selects its 4 tests (was 0); skill-llm-eval 0 → 25.

Known follow-ups (filed): 15 E2E + 2 judge PHANTOM keys select tests
that exist nowhere; codex-e2e-plan-format's testIfSelected names have
no map keys (run-all only).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-29 05:06:57 +00:00
co-authored by Claude Fable 5
parent 95b779f7cd
commit 2ec4dcf105
2 changed files with 203 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/e2e-tier-alignment.test.ts
+68 -9
View File
@@ -11,9 +11,15 @@
* Mapping rule (test filenames do NOT map mechanically to tier keys): for each * Mapping rule (test filenames do NOT map mechanically to tier keys): for each
* `test/skill-e2e-*.test.ts` with an EVALS_TIER self-gate, search the * `test/skill-e2e-*.test.ts` with an EVALS_TIER self-gate, search the
* E2E_TOUCHFILES / LLM_JUDGE_TOUCHFILES dep lists for the exact file path. If * E2E_TOUCHFILES / LLM_JUDGE_TOUCHFILES dep lists for the exact file path. If
* found under key K, the file's self-gate tier must equal E2E_TIERS[K]. Files * found under key K, the file's self-gate tier must equal E2E_TIERS[K].
* not named in any dep list are REPORTED as unmapped (a nudge to add them to *
* their eval's dep list), never silently skipped. * Self-registration is a HARD invariant (the dep-list sweep): every
* skill-e2e file must be named in at least one touchfiles dep list, so that
* editing only the test's prompt/assertions diff-selects the test itself.
* Before the sweep, 129 of ~177 E2E keys did not list their own declaring
* file — a changed test never re-ran on its own change. Files that genuinely
* cannot be mapped (no E2E map key exists for them) sit in KNOWN_UNREGISTERED
* below; that set is a ratchet, it only shrinks.
*/ */
import { describe, test, expect } from 'bun:test'; import { describe, test, expect } from 'bun:test';
@@ -35,6 +41,26 @@ const SELF_GATE_RE = /EVALS_TIER\s*===\s*['"](gate|periodic)['"]/g;
// the declared tier exactly like the raw predicate's tier literal did. // the declared tier exactly like the raw predicate's tier literal did.
const HELPER_GATE_RE = /\b(?:describeE2ETier|e2eTierEnabled)\(\s*['"](gate|periodic)['"]/g; const HELPER_GATE_RE = /\b(?:describeE2ETier|e2eTierEnabled)\(\s*['"](gate|periodic)['"]/g;
/**
* Ratchet, not amnesty (same contract as KNOWN_MATRIX_GAPS in
* test/evals-workflow-matrix.test.ts): skill-e2e files that are named in NO
* touchfiles dep list because no E2E map key exists for them. Every entry
* carries a one-line reason. Do NOT add new files here — give the test an
* E2E map key (touchfiles + tier) and register the file in its dep list.
* A stale entry (file deleted, or file now registered) FAILS the suite —
* delete it. Target: empty set.
*/
const KNOWN_UNREGISTERED = new Set([
// Standalone periodic self-gated probe; template-literal testNames (auq-consistency-${i}), no E2E map key — fail-open-safe, runs on every periodic sweep.
'test/skill-e2e-auq-consistency.test.ts',
// Standalone periodic self-gated matrix; template-literal testNames (auq-matrix-${m.skill}), no E2E map key — fail-open-safe, runs on every periodic sweep.
'test/skill-e2e-auq-matrix.test.ts',
// Standalone periodic self-gated A/B probe; template-literal testNames (auq-ab-${label}), no E2E map key — fail-open-safe, runs on every periodic sweep.
'test/skill-e2e-auq-verbose-vs-carved-ab.test.ts',
// bin-script pipeline test (spawns bun scripts, no model spend) that lives under the skill-e2e-* glob; no E2E map key exists for it.
'test/skill-e2e-memory-pipeline.test.ts',
]);
describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () => { describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () => {
const testFiles = readdirSync(TEST_DIR) const testFiles = readdirSync(TEST_DIR)
.filter((f) => f.startsWith('skill-e2e-') && f.endsWith('.test.ts')) .filter((f) => f.startsWith('skill-e2e-') && f.endsWith('.test.ts'))
@@ -44,14 +70,28 @@ describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () =>
test('every self-gated test file named in a dep list matches its declared tier', () => { test('every self-gated test file named in a dep list matches its declared tier', () => {
const misaligned: string[] = []; const misaligned: string[] = [];
const unregistered: string[] = [];
const reported: string[] = []; const reported: string[] = [];
for (const file of testFiles) { for (const file of testFiles) {
const content = readFileSync(path.join(TEST_DIR, file), 'utf-8'); const content = readFileSync(path.join(TEST_DIR, file), 'utf-8');
const repoPath = `test/${file}`;
// HARD self-registration invariant, independent of self-gate shape:
// a skill-e2e file named in no dep list means editing the test itself
// selects nothing — the changed test never re-runs on its own change.
const owningKeys = Object.keys(allDeps).filter((k) => allDeps[k].includes(repoPath));
if (owningKeys.length === 0 && !KNOWN_UNREGISTERED.has(repoPath)) {
unregistered.push(
`${repoPath}: not named in any touchfiles dep list — editing this test file would `
+ 'never diff-select it. Add the file path to its E2E map key\'s dep list in '
+ 'test/helpers/touchfiles-data.ts (do NOT extend KNOWN_UNREGISTERED for new files).',
);
}
const tiers = new Set<string>(); const tiers = new Set<string>();
for (const m of content.matchAll(SELF_GATE_RE)) tiers.add(m[1]); for (const m of content.matchAll(SELF_GATE_RE)) tiers.add(m[1]);
for (const m of content.matchAll(HELPER_GATE_RE)) tiers.add(m[1]); for (const m of content.matchAll(HELPER_GATE_RE)) tiers.add(m[1]);
const repoPath = `test/${file}`;
if (tiers.size === 0) { if (tiers.size === 0) {
// Every skill-e2e file is expected to self-gate; zero matches means // Every skill-e2e file is expected to self-gate; zero matches means
// either a genuinely ungated file or a gate shape the regex can't // either a genuinely ungated file or a gate shape the regex can't
@@ -65,8 +105,9 @@ describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () =>
} }
const selfTier = [...tiers][0]; const selfTier = [...tiers][0];
const owningKeys = Object.keys(allDeps).filter((k) => allDeps[k].includes(repoPath));
if (owningKeys.length === 0) { if (owningKeys.length === 0) {
// Only KNOWN_UNREGISTERED files reach here (anything else already
// hard-failed above) — keep the visible nudge.
reported.push(`${repoPath} (self-gates '${selfTier}'): not named in any touchfiles dep list`); reported.push(`${repoPath} (self-gates '${selfTier}'): not named in any touchfiles dep list`);
continue; continue;
} }
@@ -86,18 +127,36 @@ describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () =>
} }
} }
// Reported, not asserted: coverage holes the invariant can see but not // Reported, not asserted: tier-observability holes the invariant can see
// arbitrate. Add the test file to its eval's dep list (or a tier entry // but not arbitrate (map-driven files legitimately have no whole-file
// for the key) to bring it under the invariant. // self-gate; ratcheted files stay visible). Registration itself is
// asserted below.
if (reported.length > 0) { if (reported.length > 0) {
console.warn( console.warn(
`[tier-alignment] ${reported.length} file(s) outside the invariant:\n ` + reported.join('\n '), `[tier-alignment] ${reported.length} file(s) outside the tier invariant:\n ` + reported.join('\n '),
); );
} }
expect(unregistered).toEqual([]);
expect(misaligned).toEqual([]); expect(misaligned).toEqual([]);
}); });
// Ratchet cleanup enforcement (same contract as evals-workflow-matrix's
// burn-down test): a KNOWN_UNREGISTERED entry whose file was deleted, or
// whose file is now named in a dep list, is stale — delete the entry so
// the set can only shrink.
test('KNOWN_UNREGISTERED holds only live, still-unregistered files', () => {
const stale = [...KNOWN_UNREGISTERED].filter((repoPath) => {
const file = repoPath.replace(/^test\//, '');
if (!testFiles.includes(file)) return true; // file gone
return Object.keys(allDeps).some((k) => allDeps[k].includes(repoPath)); // now registered
});
expect(
stale,
'Entry registered in a dep list or file removed — delete it from KNOWN_UNREGISTERED.',
).toEqual([]);
});
// HARD invariant (C6): the paid sharded runner skips a skill-e2e shard when // HARD invariant (C6): the paid sharded runner skips a skill-e2e shard when
// none of the file's MAPPED test names (E2E map keys quoted in its source, // none of the file's MAPPED test names (E2E map keys quoted in its source,
// union E2E map keys whose dep list registers the file) are diff-selected. // union E2E map keys whose dep list registers the file) are diff-selected.
test/helpers/touchfiles-data.ts
+135 -130
View File
@@ -22,8 +22,8 @@
*/ */
export const E2E_TOUCHFILES: Record<string, string[]> = { export const E2E_TOUCHFILES: Record<string, string[]> = {
// Browse core (+ test-server dependency) // Browse core (+ test-server dependency)
'browse-basic': ['browse/src/**', 'browse/test/test-server.ts'], 'browse-basic': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts'], 'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
// Hermetic isolation canaries (hermetic-env.ts is also a GLOBAL touchfile; // Hermetic isolation canaries (hermetic-env.ts is also a GLOBAL touchfile;
// these entries exist so the canaries themselves stay tier-classified) // these entries exist so the canaries themselves stay tier-classified)
@@ -37,21 +37,21 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'first-task-scaffold': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-first-task-detect', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'test/skill-e2e-first-task-scaffold.test.ts', 'test/helpers/session-runner.ts'], 'first-task-scaffold': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-first-task-detect', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'test/skill-e2e-first-task-scaffold.test.ts', 'test/helpers/session-runner.ts'],
// SKILL.md setup + preamble (depend on ROOT SKILL.md + gen-skill-docs) // SKILL.md setup + preamble (depend on ROOT SKILL.md + gen-skill-docs)
'skillmd-setup-discovery': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'skillmd-setup-discovery': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'skillmd-no-local-binary': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'skillmd-no-local-binary': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'skillmd-outside-git': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'skillmd-outside-git': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'session-awareness': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'session-awareness': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'operational-learning': ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log'], 'operational-learning': ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log', 'test/skill-e2e-bws.test.ts'],
// QA (+ test-server dependency) // QA (+ test-server dependency)
'qa-quick': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'], 'qa-quick': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
'qa-b6-static': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json'], 'qa-b6-static': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
'qa-b7-spa': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json'], 'qa-b7-spa': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json'], 'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
'qa-only-no-fix': ['qa-only/**', 'qa/templates/**'], 'qa-only-no-fix': ['qa-only/**', 'qa/templates/**', 'test/skill-e2e-qa-workflow.test.ts'],
'qa-fix-loop': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'], 'qa-fix-loop': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
'qa-bootstrap': ['qa/**', 'ship/**'], 'qa-bootstrap': ['qa/**', 'ship/**', 'test/skill-e2e-qa-workflow.test.ts'],
// Review // Review
'review-sql-injection': ['review/**', 'test/fixtures/review-eval-vuln.rb', 'test/skill-e2e-review.test.ts'], 'review-sql-injection': ['review/**', 'test/fixtures/review-eval-vuln.rb', 'test/skill-e2e-review.test.ts'],
@@ -60,27 +60,27 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'review-design-lite': ['review/**', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-review.test.ts'], 'review-design-lite': ['review/**', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-review.test.ts'],
// Review Army (specialist dispatch) // Review Army (specialist dispatch)
'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope'], 'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
'review-army-perf-n-plus-one': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope'], 'review-army-perf-n-plus-one': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
'review-army-delivery-audit': ['review/**', 'scripts/resolvers/review.ts', 'scripts/resolvers/review-army.ts'], 'review-army-delivery-audit': ['review/**', 'scripts/resolvers/review.ts', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-quality-score': ['review/**', 'scripts/resolvers/review-army.ts'], 'review-army-quality-score': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-json-findings': ['review/**', 'scripts/resolvers/review-army.ts'], 'review-army-json-findings': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-red-team': ['review/**', 'scripts/resolvers/review-army.ts'], 'review-army-red-team': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-consensus': ['review/**', 'scripts/resolvers/review-army.ts'], 'review-army-consensus': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
// Office Hours // Office Hours
'office-hours-spec-review': ['office-hours/**', 'scripts/gen-skill-docs.ts'], 'office-hours-spec-review': ['office-hours/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'office-hours-forcing-energy': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'], 'office-hours-forcing-energy': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours.test.ts'],
'office-hours-builder-wildness': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'], 'office-hours-builder-wildness': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours.test.ts'],
// Plan reviews // Plan reviews
'plan-ceo-review': ['plan-ceo-review/**'], 'plan-ceo-review': ['plan-ceo-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-ceo-review-selective': ['plan-ceo-review/**'], 'plan-ceo-review-selective': ['plan-ceo-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-ceo-review-benefits': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'], 'plan-ceo-review-benefits': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'plan-ceo-review-expansion-energy': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'], 'plan-ceo-review-expansion-energy': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan.test.ts'],
'plan-eng-review': ['plan-eng-review/**'], 'plan-eng-review': ['plan-eng-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-eng-review-artifact': ['plan-eng-review/**'], 'plan-eng-review-artifact': ['plan-eng-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-review-report': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'], 'plan-review-report': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
// Plan-mode smoke tests — gate-tier safety regression tests. Each test file // Plan-mode smoke tests — gate-tier safety regression tests. Each test file
// contains TWO test cases as of v1.21: the baseline plan-mode case and the // contains TWO test cases as of v1.21: the baseline plan-mode case and the
@@ -91,7 +91,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// regression test outcome between 'asked' and 'auto_decided'. // regression test outcome between 'asked' and 'auto_decided'.
'plan-ceo-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts'], 'plan-ceo-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts'],
'plan-eng-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts'], 'plan-eng-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts'],
'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts'], 'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts', 'test/skill-e2e-design.test.ts'],
'plan-devex-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts'], 'plan-devex-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts'],
// Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not // Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not
// fire outside plan mode) + the named-target exception case. 4 PTY runs; // fire outside plan mode) + the named-target exception case. 4 PTY runs;
@@ -117,7 +117,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// written a never-ask preference, AUQ should still auto-decide rather than // written a never-ask preference, AUQ should still auto-decide rather than
// surfacing the question. Touches the question-tuning + preference // surfacing the question. Touches the question-tuning + preference
// infrastructure plus the resolvers that own the AUTO_DECIDE preamble. // infrastructure plus the resolvers that own the AUTO_DECIDE preamble.
'auto-decide-preserved': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts'], 'auto-decide-preserved': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-auto-decide-preserved.test.ts'],
// Conductor → prose decision brief (Conductor signal makes prose the default; // Conductor → prose decision brief (Conductor signal makes prose the default;
// the PreToolUse hook denies the flaky tool). Touches the resolver that owns // the PreToolUse hook denies the flaky tool). Touches the resolver that owns
@@ -128,18 +128,18 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// Each one tests behavior the SDK harness can't observe (rendered TTY, // Each one tests behavior the SDK harness can't observe (rendered TTY,
// numbered-option lists, multi-phase ordering, idempotency state echo). // numbered-option lists, multi-phase ordering, idempotency state echo).
'preamble-script-ab': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'plan-ceo-review/**', 'test/helpers/auq-sdk-capture.ts', 'test/skill-e2e-preamble-script-ab.test.ts'], 'preamble-script-ab': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'plan-ceo-review/**', 'test/helpers/auq-sdk-capture.ts', 'test/skill-e2e-preamble-script-ab.test.ts'],
'auq-format-gate': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts'], 'auq-format-gate': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-ask-user-question-format-compliance.test.ts'],
'plan-ceo-mode-routing': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-mode-routing.test.ts'], 'plan-ceo-mode-routing': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-mode-routing.test.ts'],
'plan-design-with-ui-scope': ['plan-design-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-with-ui.test.ts'], 'plan-design-with-ui-scope': ['plan-design-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-with-ui.test.ts'],
'budget-regression-pty': ['test/helpers/eval-store.ts', 'test/skill-budget-regression.test.ts'], 'budget-regression-pty': ['test/helpers/eval-store.ts', 'test/skill-budget-regression.test.ts'],
'ship-idempotency-pty': ['ship/**', 'bin/gstack-next-version', 'bin/gstack-version-bump', 'scripts/resolvers/sections.ts', 'lib/worktree.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-ship-idempotency.test.ts'], 'ship-idempotency-pty': ['ship/**', 'bin/gstack-next-version', 'bin/gstack-version-bump', 'scripts/resolvers/sections.ts', 'lib/worktree.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-ship-idempotency.test.ts'],
'ship-section-loading': ['ship/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-ship-section-loading.test.ts'], 'ship-section-loading': ['ship/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-ship-section-loading.test.ts'],
'plan-ceo-section-loading': ['plan-ceo-review/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'], 'plan-ceo-section-loading': ['plan-ceo-review/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-plan-ceo-review-section-loading.test.ts'],
// Data-driven behavioral guard for the 'plan'/'prompt' carves (eng, design, // Data-driven behavioral guard for the 'plan'/'prompt' carves (eng, design,
// devex, office-hours + future PR2 carves). One file iterating CARVE_GUARDS; // devex, office-hours + future PR2 carves). One file iterating CARVE_GUARDS;
// the selector sets GSTACK_CARVE_SKILL=<name> to scope cost to the changed // the selector sets GSTACK_CARVE_SKILL=<name> to scope cost to the changed
// skill (D-CODEX A). Touching the registry/helper or sections.ts runs all. // skill (D-CODEX A). Touching the registry/helper or sections.ts runs all.
'carve-section-loading': ['design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'], 'carve-section-loading': ['design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/carve-section-loading.test.ts'],
'autoplan-chain-pty': ['autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-autoplan-chain.test.ts'], 'autoplan-chain-pty': ['autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-autoplan-chain.test.ts'],
'e2e-harness-audit': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/claude-pty-runner.ts'], 'e2e-harness-audit': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/claude-pty-runner.ts'],
@@ -185,18 +185,18 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// AskUserQuestion format regression (RECOMMENDATION + Completeness: N/10) // AskUserQuestion format regression (RECOMMENDATION + Completeness: N/10)
// Fires when either template OR the two preamble resolvers change. // Fires when either template OR the two preamble resolvers change.
'plan-ceo-review-format-mode': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'], 'plan-ceo-review-format-mode': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
'plan-ceo-review-format-approach': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'], 'plan-ceo-review-format-approach': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
'plan-eng-review-format-coverage': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'], 'plan-eng-review-format-coverage': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
'plan-eng-review-format-kind': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'], 'plan-eng-review-format-kind': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
// v1.7.0.0 Pros/Cons format cadence + format + negative-escape evals. // v1.7.0.0 Pros/Cons format cadence + format + negative-escape evals.
// Dependencies: same as format-mode + the 4 plan-review templates + overlay. // Dependencies: same as format-mode + the 4 plan-review templates + overlay.
// All periodic-tier (non-deterministic Opus 4.7 behavior). // All periodic-tier (non-deterministic Opus 4.7 behavior).
'plan-ceo-review-prosons-cadence': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'], 'plan-ceo-review-prosons-cadence': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
'plan-review-prosons-format': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'], 'plan-review-prosons-format': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
'plan-review-prosons-hardstop-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'], 'plan-review-prosons-hardstop-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
'plan-review-prosons-neutral-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'], 'plan-review-prosons-neutral-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
// Expanded coverage (CT3) — 6 non-plan-review skills inherit Pros/Cons via preamble // Expanded coverage (CT3) — 6 non-plan-review skills inherit Pros/Cons via preamble
'ship-prosons-format': ['ship/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'], 'ship-prosons-format': ['ship/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
@@ -208,24 +208,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'document-release-prosons-format': ['document-release/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'], 'document-release-prosons-format': ['document-release/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
// /plan-tune (v1 observational) // /plan-tune (v1 observational)
'plan-tune-inspect': ['plan-tune/**', 'scripts/question-registry.ts', 'scripts/psychographic-signals.ts', 'scripts/one-way-doors.ts', 'bin/gstack-question-log', 'bin/gstack-question-preference', 'bin/gstack-developer-profile'], 'plan-tune-inspect': ['plan-tune/**', 'scripts/question-registry.ts', 'scripts/psychographic-signals.ts', 'scripts/one-way-doors.ts', 'bin/gstack-question-log', 'bin/gstack-question-preference', 'bin/gstack-developer-profile', 'test/skill-e2e-plan-tune.test.ts'],
// /plan-tune cathedral (T16 — 5 E2E scenarios, all gate per D12) // /plan-tune cathedral (T16 — 5 E2E scenarios, all gate per D12)
'plan-tune-hook-capture': ['hosts/claude/hooks/**', 'bin/gstack-question-log', 'bin/gstack-developer-profile', 'plan-tune/**'], 'plan-tune-hook-capture': ['hosts/claude/hooks/**', 'bin/gstack-question-log', 'bin/gstack-developer-profile', 'plan-tune/**', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-enforcement': ['hosts/claude/hooks/**', 'bin/gstack-question-preference', 'scripts/question-registry.ts'], 'plan-tune-enforcement': ['hosts/claude/hooks/**', 'bin/gstack-question-preference', 'scripts/question-registry.ts', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-annotation': ['hosts/claude/hooks/**', 'scripts/declared-annotation.ts', 'scripts/psychographic-signals.ts', 'scripts/question-registry.ts'], 'plan-tune-annotation': ['hosts/claude/hooks/**', 'scripts/declared-annotation.ts', 'scripts/psychographic-signals.ts', 'scripts/question-registry.ts', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-codex-import': ['bin/gstack-codex-session-import', 'bin/gstack-question-log', 'docs/spikes/codex-session-format.md'], 'plan-tune-codex-import': ['bin/gstack-codex-session-import', 'bin/gstack-question-log', 'docs/spikes/codex-session-format.md', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-dream-cycle': ['bin/gstack-distill-free-text', 'bin/gstack-distill-apply', 'hosts/claude/hooks/**', 'plan-tune/**'], 'plan-tune-dream-cycle': ['bin/gstack-distill-free-text', 'bin/gstack-distill-apply', 'hosts/claude/hooks/**', 'plan-tune/**', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
// Codex offering verification // Codex offering verification
'codex-offered-office-hours': ['office-hours/**', 'scripts/gen-skill-docs.ts'], 'codex-offered-office-hours': ['office-hours/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'codex-offered-ceo-review': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'], 'codex-offered-ceo-review': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'codex-offered-design-review': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'], 'codex-offered-design-review': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'codex-offered-eng-review': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'], 'codex-offered-eng-review': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
// Ship // Ship
'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-review-attribution.test.ts'], 'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-review-attribution.test.ts'],
'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts'], 'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-workflow.test.ts'],
'review-dashboard-via': ['ship/**', 'scripts/resolvers/review.ts', 'codex/**', 'autoplan/**', 'land-and-deploy/**', 'test/skill-e2e-review-attribution.test.ts'], 'review-dashboard-via': ['ship/**', 'scripts/resolvers/review.ts', 'codex/**', 'autoplan/**', 'land-and-deploy/**', 'test/skill-e2e-review-attribution.test.ts'],
// Retro // Retro
@@ -236,51 +236,51 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'global-discover': ['bin/gstack-global-discover.ts', 'test/global-discover.test.ts'], 'global-discover': ['bin/gstack-global-discover.ts', 'test/global-discover.test.ts'],
// CSO // CSO
'cso-full-audit': ['cso/**'], 'cso-full-audit': ['cso/**', 'test/skill-e2e-cso.test.ts'],
'cso-diff-mode': ['cso/**'], 'cso-diff-mode': ['cso/**', 'test/skill-e2e-cso.test.ts'],
'cso-infra-scope': ['cso/**'], 'cso-infra-scope': ['cso/**', 'test/skill-e2e-cso.test.ts'],
// Learnings // Learnings
'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts'], 'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts', 'test/skill-e2e-learnings.test.ts'],
// Session Intelligence (timeline, context recovery, /context-save + /context-restore) // Session Intelligence (timeline, context recovery, /context-save + /context-restore)
'timeline-event-flow': ['bin/gstack-timeline-log', 'bin/gstack-timeline-read'], 'timeline-event-flow': ['bin/gstack-timeline-log', 'bin/gstack-timeline-read', 'test/skill-e2e-session-intelligence.test.ts'],
'context-recovery-artifacts': ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**'], 'context-recovery-artifacts': ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**', 'test/skill-e2e-session-intelligence.test.ts'],
'context-save-writes-file': ['context-save/**', 'bin/gstack-slug'], 'context-save-writes-file': ['context-save/**', 'bin/gstack-slug', 'test/skill-e2e-session-intelligence.test.ts'],
'context-restore-loads-latest': ['context-restore/**', 'bin/gstack-slug'], 'context-restore-loads-latest': ['context-restore/**', 'bin/gstack-slug', 'test/skill-e2e-session-intelligence.test.ts'],
// Context skills E2E (live-fire, Skill-tool routing path) — see // Context skills E2E (live-fire, Skill-tool routing path) — see
// test/skill-e2e-context-skills.test.ts. These are periodic-tier because // test/skill-e2e-context-skills.test.ts. These are periodic-tier because
// each one spawns claude -p and costs ~$0.20-$0.40. Collectively they // each one spawns claude -p and costs ~$0.20-$0.40. Collectively they
// verify the thing the /checkpoint → /context-save rename was for. // verify the thing the /checkpoint → /context-save rename was for.
'context-save-routing': ['context-save/**', 'scripts/resolvers/preamble.ts'], 'context-save-routing': ['context-save/**', 'scripts/resolvers/preamble.ts', 'test/skill-e2e-context-skills.test.ts'],
'context-save-then-restore-roundtrip': ['context-save/**', 'context-restore/**', 'bin/gstack-slug'], 'context-save-then-restore-roundtrip': ['context-save/**', 'context-restore/**', 'bin/gstack-slug', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-fragment-match': ['context-restore/**'], 'context-restore-fragment-match': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-empty-state': ['context-restore/**'], 'context-restore-empty-state': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-list-delegates': ['context-restore/**'], 'context-restore-list-delegates': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-legacy-compat': ['context-restore/**'], 'context-restore-legacy-compat': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-save-list-current-branch': ['context-save/**'], 'context-save-list-current-branch': ['context-save/**', 'test/skill-e2e-context-skills.test.ts'],
'context-save-list-all-branches': ['context-save/**'], 'context-save-list-all-branches': ['context-save/**', 'test/skill-e2e-context-skills.test.ts'],
// Document-release // Document-release
'document-release': ['document-release/**'], 'document-release': ['document-release/**', 'test/skill-e2e-workflow.test.ts'],
// Codex (Claude E2E — tests /codex skill via Claude) // Codex (Claude E2E — tests /codex skill via Claude)
'codex-review': ['codex/**'], 'codex-review': ['codex/**', 'test/skill-e2e-workflow.test.ts'],
// Codex E2E (tests skills via Codex CLI + worktree) // Codex E2E (tests skills via Codex CLI + worktree)
'codex-discover-skill': ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts'], 'codex-discover-skill': ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts'],
'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts'], 'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts'],
// GPT-5.6 Sol scope-termination E2E (Codex CLI, full generated investigate skill) // GPT-5.6 Sol scope-termination E2E (Codex CLI, full generated investigate skill)
'codex-sol-scope-termination': ['model-overlays/gpt-5.6-sol.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'scripts/resolvers/preamble/**', 'investigate/**', 'test/helpers/codex-session-runner.ts', 'test/codex-e2e-sol-scope.test.ts'], 'codex-sol-scope-termination': ['model-overlays/gpt-5.6-sol.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'scripts/resolvers/preamble/**', 'investigate/**', 'test/helpers/codex-session-runner.ts', 'test/codex-e2e-sol-scope.test.ts'],
// Gemini E2E — smoke test only (Gemini gets lost in worktrees on complex tasks) // Gemini E2E — smoke test only (Gemini gets lost in worktrees on complex tasks)
'gemini-smoke': ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts', 'lib/worktree.ts'], 'gemini-smoke': ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts', 'lib/worktree.ts', 'test/gemini-e2e.test.ts'],
// Coverage audit (shared fixture) + triage + gates // Coverage audit (shared fixture) + triage + gates
'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode'], 'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode', 'test/skill-e2e-workflow.test.ts'],
'review-coverage-audit': ['review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'], 'review-coverage-audit': ['review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'],
'plan-eng-coverage-audit': ['plan-eng-review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'], 'plan-eng-coverage-audit': ['plan-eng-review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'],
'ship-triage': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-triage.test.ts'], 'ship-triage': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-triage.test.ts'],
@@ -292,12 +292,12 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'review-plan-completion': ['review/**', 'scripts/gen-skill-docs.ts'], 'review-plan-completion': ['review/**', 'scripts/gen-skill-docs.ts'],
// Design // Design
'design-consultation-core': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts'], 'design-consultation-core': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-existing': ['design-consultation/**', 'scripts/gen-skill-docs.ts'], 'design-consultation-existing': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-research': ['design-consultation/**', 'scripts/gen-skill-docs.ts'], 'design-consultation-research': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-preview': ['design-consultation/**', 'scripts/gen-skill-docs.ts'], 'design-consultation-preview': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'], 'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-review-fix': ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts'], 'design-review-fix': ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
// Design Shotgun // Design Shotgun
'design-shotgun-path': ['design-shotgun/**', 'design/src/**', 'scripts/resolvers/design.ts'], 'design-shotgun-path': ['design-shotgun/**', 'design/src/**', 'scripts/resolvers/design.ts'],
@@ -306,24 +306,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// /diagram (diagram-render bundle consumers). Triplet = deterministic // /diagram (diagram-render bundle consumers). Triplet = deterministic
// functional (gate); authoring quality = LLM-judged benchmark (periodic). // functional (gate); authoring quality = LLM-judged benchmark (periodic).
'diagram-triplet': ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts'], 'diagram-triplet': ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts', 'test/skill-e2e-diagram.test.ts'],
'diagram-authoring-quality': ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts'], 'diagram-authoring-quality': ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-diagram.test.ts'],
// gstack-upgrade // gstack-upgrade
'gstack-upgrade-happy-path': ['gstack-upgrade/**'], 'gstack-upgrade-happy-path': ['gstack-upgrade/**', 'test/skill-e2e-workflow.test.ts'],
// Deploy skills // Deploy skills
'land-and-deploy-workflow': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts'], 'land-and-deploy-workflow': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
'land-and-deploy-first-run': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug'], 'land-and-deploy-first-run': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug', 'test/skill-e2e-deploy.test.ts'],
'land-and-deploy-review-gate': ['land-and-deploy/**', 'bin/gstack-review-read'], 'land-and-deploy-review-gate': ['land-and-deploy/**', 'bin/gstack-review-read', 'test/skill-e2e-deploy.test.ts'],
'canary-workflow': ['canary/**', 'browse/src/**'], 'canary-workflow': ['canary/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
'benchmark-workflow': ['benchmark/**', 'browse/src/**'], 'benchmark-workflow': ['benchmark/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
'setup-deploy-workflow': ['setup-deploy/**', 'scripts/gen-skill-docs.ts'], 'setup-deploy-workflow': ['setup-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
// Autoplan // Autoplan
'autoplan-core': ['autoplan/**', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**'], 'autoplan-core': ['autoplan/**', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**'],
'autoplan-dual-voice': ['autoplan/**', 'codex/**', 'bin/gstack-codex-probe', 'scripts/resolvers/review.ts', 'scripts/resolvers/design.ts'], 'autoplan-dual-voice': ['autoplan/**', 'codex/**', 'bin/gstack-codex-probe', 'scripts/resolvers/review.ts', 'scripts/resolvers/design.ts', 'test/skill-e2e-autoplan-dual-voice.test.ts'],
// Multi-provider benchmark adapters — live API smoke against real claude/codex/gemini CLIs // Multi-provider benchmark adapters — live API smoke against real claude/codex/gemini CLIs
'benchmark-providers-live': ['bin/gstack-model-benchmark', 'test/helpers/providers/**', 'test/helpers/benchmark-runner.ts', 'test/helpers/pricing.ts', 'test/skill-e2e-benchmark-providers.test.ts'], 'benchmark-providers-live': ['bin/gstack-model-benchmark', 'test/helpers/providers/**', 'test/helpers/benchmark-runner.ts', 'test/helpers/pricing.ts', 'test/skill-e2e-benchmark-providers.test.ts'],
@@ -336,41 +336,46 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'scrape-match-path': [ 'scrape-match-path': [
'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts', 'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
'browser-skills/hackernews-frontpage/**', 'browser-skills/hackernews-frontpage/**',
'test/skill-e2e-skillify.test.ts',
], ],
'scrape-prototype-path': [ 'scrape-prototype-path': [
'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts', 'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
'test/skill-e2e-skillify.test.ts',
], ],
'skillify-happy-path': [ 'skillify-happy-path': [
'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts', 'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts',
'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
'test/skill-e2e-skillify.test.ts',
], ],
'skillify-provenance-refusal': [ 'skillify-provenance-refusal': [
'skillify/**', 'browse/src/browser-skill-write.ts', 'skillify/**', 'browse/src/browser-skill-write.ts',
'test/skill-e2e-skillify.test.ts',
], ],
'skillify-approval-reject': [ 'skillify-approval-reject': [
'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts', 'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts',
'test/skill-e2e-skillify.test.ts',
], ],
// Skill routing — journey-stage tests (depend on ALL skill descriptions) // Skill routing — journey-stage tests (depend on ALL skill descriptions)
'journey-ideation': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-ideation': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-plan-eng': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-plan-eng': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-debug': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-debug': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-code-review': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-code-review': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-ship': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-ship': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-docs': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-docs': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-retro': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-retro': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-design-system': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-design-system': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-visual-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'journey-visual-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
// Opus 4.7 behavior evals — keys match testName: values in the test file. // Opus 4.7 behavior evals — keys match testName: values in the test file.
// Routing sub-tests use template literal `routing-${c.name}` testNames, // Routing sub-tests use template literal `routing-${c.name}` testNames,
// which the touchfile completeness scanner skips; they inherit selection // which the touchfile completeness scanner skips; they inherit selection
// from the file-level touchfile entry via GLOBAL_TOUCHFILES. // from the file-level touchfile entry via GLOBAL_TOUCHFILES.
'fanout-arm-overlay-on': 'fanout-arm-overlay-on':
['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts'], ['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-opus-47.test.ts'],
'fanout-arm-overlay-off': 'fanout-arm-overlay-off':
['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts'], ['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-opus-47.test.ts'],
// Overlay efficacy harness (SDK) — measures whether overlay nudges change // Overlay efficacy harness (SDK) — measures whether overlay nudges change
// behavior under @anthropic-ai/claude-agent-sdk (closer to real Claude Code // behavior under @anthropic-ai/claude-agent-sdk (closer to real Claude Code
@@ -754,49 +759,49 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
* LLM-judge test touchfiles — keyed by test description string. * LLM-judge test touchfiles — keyed by test description string.
*/ */
export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = { export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
'command reference table': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts'], 'command reference table': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/skill-llm-eval.test.ts'],
'snapshot flags reference': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts'], 'snapshot flags reference': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts', 'test/skill-llm-eval.test.ts'],
'browse/SKILL.md reference': ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**'], 'browse/SKILL.md reference': ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**', 'test/skill-llm-eval.test.ts'],
'setup block': ['SKILL.md', 'SKILL.md.tmpl'], 'setup block': ['SKILL.md', 'SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'regression vs baseline': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json'], 'regression vs baseline': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
'qa/SKILL.md workflow': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl'], 'qa/SKILL.md workflow': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'qa/SKILL.md health rubric': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl'], 'qa/SKILL.md health rubric': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'qa/SKILL.md anti-refusal': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'], 'qa/SKILL.md anti-refusal': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'], 'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'baseline score pinning': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json'], 'baseline score pinning': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
// Ship & Release // Ship & Release
'ship/SKILL.md workflow': ['ship/SKILL.md', 'ship/SKILL.md.tmpl'], 'ship/SKILL.md workflow': ['ship/SKILL.md', 'ship/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'document-release/SKILL.md workflow': ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl'], 'document-release/SKILL.md workflow': ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Plan Reviews // Plan Reviews
'plan-ceo-review/SKILL.md modes': ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl'], 'plan-ceo-review/SKILL.md modes': ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'plan-eng-review/SKILL.md sections': ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl'], 'plan-eng-review/SKILL.md sections': ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// /spec authored-spec quality (paid LLM-judge — periodic-tier). // /spec authored-spec quality (paid LLM-judge — periodic-tier).
'plan-design-review/SKILL.md passes': ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl'], 'plan-design-review/SKILL.md passes': ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Design skills // Design skills
'design-review/SKILL.md fix loop': ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl'], 'design-review/SKILL.md fix loop': ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl'], 'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Office Hours // Office Hours
'office-hours/SKILL.md spec review': ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'office-hours/SKILL.md spec review': ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'office-hours/SKILL.md design sketch': ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'office-hours/SKILL.md design sketch': ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
// Deploy skills // Deploy skills
'land-and-deploy/SKILL.md workflow': ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl', 'land-and-deploy/sections/**'], 'land-and-deploy/SKILL.md workflow': ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl', 'land-and-deploy/sections/**', 'test/skill-llm-eval.test.ts'],
'canary/SKILL.md monitoring loop': ['canary/SKILL.md', 'canary/SKILL.md.tmpl'], 'canary/SKILL.md monitoring loop': ['canary/SKILL.md', 'canary/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'benchmark/SKILL.md perf collection': ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl'], 'benchmark/SKILL.md perf collection': ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl'], 'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Other skills // Other skills
'retro/SKILL.md instructions': ['retro/sections/**', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'], 'retro/SKILL.md instructions': ['retro/sections/**', 'retro/SKILL.md', 'retro/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'qa-only/SKILL.md workflow': ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'], 'qa-only/SKILL.md workflow': ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl'], 'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Voice directive // Voice directive
'voice directive tone': ['scripts/resolvers/preamble.ts', 'review/SKILL.md', 'review/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'], 'voice directive tone': ['scripts/resolvers/preamble.ts', 'review/SKILL.md', 'review/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-llm-eval.test.ts'],
}; };
/** /**