Round 3 repair from GEVA-2's climb-2 dev table: Capy exposure fell from 40 to 15 of 40 after factory.md point 10 changed from 'Reports and replies' to 'Replies', so that wording returns; skill-layer recall stayed level with no gstack while broken tests (0.43) and failed checks (0.50) trailed the lens arm, so Failed or skipped: now names anything that failed even if fixed later, in the closer and in /investigate's report. Rendered closer is 660 B against 664 B at 641d622; factory.md is 3,600 B.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Round 2 repair from GEVA-2's climb-1 dev table: the closer reached only 14 of 40 ship reports, Capy reports under the 200-word cap lost recall (0.487 vs 0.552 current), and config or CI changes were the largest missed category (0.32 of 88 facts). The closer now covers any status report, after work or when asked; the cap is 250 words; a third line, Also changed:, names config, CI and out-of-scope files. The same line joins /investigate's debug report, factory.md point 10, the lane report Outcome and READY's lane lines. Rendered closer is 662 B against 664 B at 641d622; factory.md is 3,595 B.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The shared closer now asks for a report under 200 words that opens with two lines, Failed or skipped: and Unverified:, each naming every item or saying none, then what changed and what ran. Rendered closer shrinks 664 -> 654 B; ship's size ledger records -10 B.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(skill-evals): /learn before/after tasks, written before any cut (GSTA-133)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(learnings): --help, unknown-flag errors and --stats on the learnings bins; cross-project search no longer drops every project when the state root path contains the slug
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* refactor(learn): diet /learn onto the levels: tool flags replace the inline stats program, one mode table, prune rules kept
Skill-Diet: learn
Skill-Size: 5797→2586 bytes (SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(write-skill): /write-skill skill, gstack-skill-bill, static skill-to-bin drift ratchet, shared skill eval contract
Skill-Size: 0→3245 bytes (write-skill/SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(learn): guard the state-root lookup in Prune; re-measure the learn ceiling
Skill-Size: 2586→2707 bytes (learn/SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (drift scanner, learnings flags, skill-bill baselines, eval fixtures)
- skill-bin-drift: a redirect no longer ends a command, so `bin/x 2>/dev/null --bogus` is checked
- gstack-learnings-search: a missing value or a non-positive --limit exits 2 like an unknown flag
- gstack-skill-bill: the gstack root skill is a checkout skill; Skill-Diet trailers match the exact name; the baseline counts the committed bytes untrimmed
- skill-evals task files get a free contract test and are registered in FREE_FIXTURES, with the drift allowlist
- learn eval: the no-code-change safety task no longer asks the model to fix code (its check penalised obeying the user)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(learn,write-skill): full bin paths in the mode table; prune asks per entry unless the request names the action
Skill-Diet: learn
Skill-Size: 2707→2955 bytes (learn/SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(changelog): /write-skill, gstack-skill-bill, drift ratchet, eval contract, /learn diet
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: drift ratchet in CONTRIBUTING's static tests; /learn prune example asks per entry
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(skill-bill): report a checkout skill's eval task file and check it against the contract
The skill-evals task-file test now exercises lib/skill-bill.ts's checkEvalTasks, with a negative control, instead of a test-only validator (test-of-test ratchet).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(skill-bill): EVAL TASKS path uses forward slashes on every platform; a non-object task entry is a problem, not a crash
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(learn): BASH_COMPAT guard on in-window heredocs; count skill-e2e-write-skill in the paid census
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>