Garry Tan 64bbbb2198 fix: plan-design-review-audit eval — bump turns to 30, add efficiency hints ...

The test was flaky at 20 turns because the agent reads a 300-line SKILL.md,
navigates, extracts design data, and writes a report. Added hints to skip
preamble/batch commands/write early while still testing the real SKILL.md.
Now completes in ~13 turns consistently.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-17 14:41:13 -07:00

..

fixtures

feat: contributor mode, session awareness, recommendation format (#90)

2026-03-16 01:45:50 -05:00

helpers

chore: bump version and changelog (v0.6.1.0)

2026-03-17 11:30:23 -07:00

gen-skill-docs.test.ts

feat: SELECTIVE EXPANSION + smarter ship gates (v0.5.3) (#134)

2026-03-17 12:22:10 -05:00

skill-e2e.test.ts

fix: plan-design-review-audit eval — bump turns to 30, add efficiency hints

2026-03-17 14:41:13 -07:00

skill-llm-eval.test.ts

feat: diff-based test selection for E2E and LLM-judge evals

2026-03-17 11:28:03 -07:00

skill-parser.test.ts

feat: SKILL.md template system, 3-tier testing, DX tools (v0.3.3) (#41)

2026-03-13 21:08:12 -07:00

skill-validation.test.ts

feat: Test Bootstrap + Regression Tests + Coverage Audit (v0.6.0) (#136)

2026-03-17 13:05:18 -05:00

touchfiles.test.ts

chore: bump version and changelog (v0.6.1.0)

2026-03-17 11:30:23 -07:00