Commit Graph

6 Commits

Author SHA1 Message Date
Bastien Chanot
61a98573d7 chore(skills): remove disable-model-invocation repo-wide
Strip the disable-model-invocation frontmatter key from all 19 editable skills. Absent = default = model invocation enabled. 8 were 'true' and blocked the model AND orchestrators from self-routing (status, plugin-check, analyze, onboard, refactor, init-project, pdf-translate, ship-feature) — contradicting the CLAUDE.md skill-routing rules. The other 11 were 'false', a no-op noise line.

The setting is binary (no per-caller granularity), so enabling orchestrator chaining also enables model auto-fire — accepted. Genuinely destructive operations remain guarded by the careful/guard hooks, independent of this flag.

Capitalized: BDR-019 (decision), LRN-026 (learning), journal 2026-06-09.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-09 16:18:10 +02:00
bastien
727e9fc73a optimize plugin-check: round 1 — D3 fallback + D1 triggers + advisory clarification
D3: fallback when plugin-advisor.md unreachable.
D1: triggers added.
D4: explicit 'never writes' clarification (skill is advisory-only).
Size: 425B → 628B (+48%, under 150% cap).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 17:57:48 +02:00
bastien
735ece3a0b test(darwin-skill): add baseline test-prompts.json for 18 personal skills 2026-05-06 17:53:51 +02:00
bchanot
f55a2b3fdf final version seems 2026-04-08 13:46:45 +02:00
bastien
f8811fab37 opus version correction 2026-04-03 18:08:21 +02:00
bastien
5b4112fbff added plugin management and install + usage of them in readme, corrected init and scaffold for a proper int creation. Added docker tool if it make sens 2026-04-03 03:04:31 +02:00