fix: shorten auto-trigger guard to stay under 1024-char description limit

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-05 05:05:08 +02:00 · 2026-03-22 22:54:36 -07:00
parent 53eefc9a20
commit c213be3943
29 changed files with 29 additions and 57 deletions
@@ -2,8 +2,7 @@
 name: gstack
 version: 1.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /gstack in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /gstack.
  Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with
  elements, verify state, diff before/after, take annotated screenshots, test responsive
  layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or
@@ -2,8 +2,7 @@
 name: autoplan
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /autoplan in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /autoplan.
  Auto-review pipeline — reads the full CEO, design, and eng review skills from disk
  and runs them sequentially with auto-decisions using 6 decision principles. Surfaces
  taste decisions (close approaches, borderline scope, codex disagreements) at a final
@@ -2,8 +2,7 @@
 name: benchmark
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /benchmark in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /benchmark.
  Performance regression detection using the browse daemon. Establishes
  baselines for page load times, Core Web Vitals, and resource sizes.
  Compares before/after on every PR. Tracks performance trends over time.
@@ -2,8 +2,7 @@
 name: browse
 version: 1.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /browse in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /browse.
  Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with
  elements, verify page state, diff before/after actions, take annotated screenshots, check
  responsive layouts, test forms and uploads, handle dialogs, and assert element states.
@@ -2,8 +2,7 @@
 name: canary
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /canary in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /canary.
  Post-deploy canary monitoring. Watches the live app for console errors,
  performance regressions, and page failures using the browse daemon. Takes
  periodic screenshots, compares against pre-deploy baselines, and alerts
@@ -2,8 +2,7 @@
 name: careful
 version: 0.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /careful in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /careful.
  Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE,
  force-push, git reset --hard, kubectl delete, and similar destructive operations.
  User can override each warning. Use when touching prod, debugging live systems,
@@ -2,8 +2,7 @@
 name: codex
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /codex in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /codex.
  OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via
  codex review with pass/fail gate. Challenge: adversarial mode that tries to break
  your code. Consult: ask codex anything with session continuity for follow-ups.
@@ -2,8 +2,7 @@
 name: cso
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /cso in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /cso.
  Chief Security Officer mode. Performs OWASP Top 10 audit, STRIDE threat modeling,
  attack surface analysis, auth flow verification, secret detection, dependency CVE
  scanning, supply chain risk assessment, and data classification review.
@@ -2,8 +2,7 @@
 name: design-consultation
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /design-consultation in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /design-consultation.
  Design consultation: understands your product, researches the landscape, proposes a
  complete design system (aesthetic, typography, color, layout, spacing, motion), and
  generates font+color preview pages. Creates DESIGN.md as your project's design source
@@ -2,8 +2,7 @@
 name: design-review
 version: 2.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /design-review in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /design-review.
  Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems,
  AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues
  in source code, committing each fix atomically and re-verifying with before/after
@@ -2,8 +2,7 @@
 name: document-release
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /document-release in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /document-release.
  Post-ship documentation update. Reads all project docs, cross-references the
  diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped,
  polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when
@@ -2,8 +2,7 @@
 name: freeze
 version: 0.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /freeze in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /freeze.
  Restrict file edits to a specific directory for the session. Blocks Edit and
  Write outside the allowed path. Use when debugging to prevent accidentally
  "fixing" unrelated code, or when you want to scope changes to one module.
@@ -2,8 +2,7 @@
 name: gstack-upgrade
 version: 1.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /gstack-upgrade in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /gstack-upgrade.
  Upgrade gstack to the latest version. Detects global vs vendored install,
  runs the upgrade, and shows what's new. Use when asked to "upgrade gstack",
  "update gstack", or "get latest version".
@@ -2,8 +2,7 @@
 name: guard
 version: 0.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /guard in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /guard.
  Full safety mode: destructive command warnings + directory-scoped edits.
  Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with
  /freeze (blocks edits outside a specified directory). Use for maximum safety
@@ -2,8 +2,7 @@
 name: investigate
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /investigate in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /investigate.
  Systematic debugging with root cause investigation. Four phases: investigate,
  analyze, hypothesize, implement. Iron Law: no fixes without root cause.
  Use when asked to "debug this", "fix this bug", "why is this broken",
@@ -2,8 +2,7 @@
 name: land-and-deploy
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /land-and-deploy in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /land-and-deploy.
  Land and deploy workflow. Merges the PR, waits for CI and deploy,
  verifies production health via canary checks. Takes over after /ship
  creates the PR. Use when: "merge", "land", "deploy", "merge and verify",
@@ -2,8 +2,7 @@
 name: office-hours
 version: 2.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /office-hours in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /office-hours.
  YC Office Hours — two modes. Startup mode: six forcing questions that expose
  demand reality, status quo, desperate specificity, narrowest wedge, observation,
  and future-fit. Builder mode: design thinking brainstorming for side projects,
@@ -2,8 +2,7 @@
 name: plan-ceo-review
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /plan-ceo-review in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /plan-ceo-review.
  CEO/founder-mode plan review. Rethink the problem, find the 10-star product,
  challenge premises, expand scope when it creates a better product. Four modes:
  SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick
@@ -2,8 +2,7 @@
 name: plan-design-review
 version: 2.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /plan-design-review in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /plan-design-review.
  Designer's eye plan review — interactive, like CEO and Eng review.
  Rates each design dimension 0-10, explains what would make it a 10,
  then fixes the plan to get there. Works in plan mode. For live site
@@ -2,8 +2,7 @@
 name: plan-eng-review
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /plan-eng-review in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /plan-eng-review.
  Eng manager-mode plan review. Lock in the execution plan — architecture,
  data flow, diagrams, edge cases, test coverage, performance. Walks through
  issues interactively with opinionated recommendations. Use when asked to
@@ -2,8 +2,7 @@
 name: qa-only
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /qa-only in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /qa-only.
  Report-only QA testing. Systematically tests a web application and produces a
  structured report with health score, screenshots, and repro steps — but never
  fixes anything. Use when asked to "just report bugs", "qa report only", or
@@ -2,8 +2,7 @@
 name: qa
 version: 2.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /qa in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /qa.
  Systematically QA test a web application and fix bugs found. Runs QA testing,
  then iteratively fixes bugs in source code, committing each fix atomically and
  re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs",
@@ -2,8 +2,7 @@
 name: retro
 version: 2.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /retro in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /retro.
  Weekly engineering retrospective. Analyzes commit history, work patterns,
  and code quality metrics with persistent history and trend tracking.
  Team-aware: breaks down per-person contributions with praise and growth areas.
@@ -2,8 +2,7 @@
 name: review
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /review in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /review.
  Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust
  boundary violations, conditional side effects, and other structural issues. Use when
  asked to "review this PR", "code review", "pre-landing review", or "check my diff".
@@ -2972,7 +2972,7 @@ function processTemplate(tmplPath: string, host: Host = 'claude'): { outputPath:
  // Adds explicit trigger criteria so Claude Code doesn't auto-fire skills
  // based on semantic similarity. Preserves existing "Use when" and
  // "Proactively suggest" text (both are tested in skill-validation.test.ts).
-  const triggerGuard = `  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /${skillName} in their message.\n  Do not auto-trigger this skill from semantic similarity alone.\n`;
+  const triggerGuard = `  MANUAL TRIGGER ONLY: invoke only when user types /${skillName}.\n`;
  const descMatch = content.match(/^(description:\s*\|?\s*\n)/m);
  if (descMatch && descMatch.index !== undefined) {
    const insertAt = descMatch.index + descMatch[0].length;
@@ -2,8 +2,7 @@
 name: setup-browser-cookies
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /setup-browser-cookies in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /setup-browser-cookies.
  Import cookies from your real Chromium browser into the headless browse session.
  Opens an interactive picker UI where you select which cookie domains to import.
  Use before QA testing authenticated pages. Use when asked to "import cookies",
@@ -2,8 +2,7 @@
 name: setup-deploy
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /setup-deploy in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /setup-deploy.
  Configure deployment settings for /land-and-deploy. Detects your deploy
  platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom),
  production URL, health check endpoints, and deploy status commands. Writes
@@ -2,8 +2,7 @@
 name: ship
 version: 1.0.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /ship in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /ship.
  Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push".
  Proactively suggest when the user says code is ready or asks about deploying.
 allowed-tools:
@@ -2,8 +2,7 @@
 name: unfreeze
 version: 0.1.0
 description: |
-  MANUAL TRIGGER ONLY: only run this skill when the user explicitly types /unfreeze in their message.
-  Do not auto-trigger this skill from semantic similarity alone.
+  MANUAL TRIGGER ONLY: invoke only when user types /unfreeze.
  Clear the freeze boundary set by /freeze, allowing edits to all directories
  again. Use when you want to widen edit scope without ending the session.
  Use when asked to "unfreeze", "unlock edits", "remove freeze", or