feat(skills): declare which surfaces each skill ships to
CI / Check / Test (push) Failing after 1s
CI / Tag release (push) Skipped

The repo distributes three ways — the Claude Code plugin, the symlinked
library for Crush/Pi/OpenCode, and claude.ai, which has no fetch path at all —
and treated every skill as belonging to all of them. claude.ai is not a fourth
host to mirror: gitea-ci, playwright and web-shot have no shell and no cluster
there, so a flat mirror installs skills that can never fire and degrades
selection for the ones that can.

Every SKILL.md now carries `surfaces:`, defaulting to [claude-code, library];
dream, own-the-task and grill-me add `chat`, matching what is actually
installed on claude.ai today. Claude Code accepts the extra key —
`claude plugin validate` passes and the skills still load.

bin/check-surfaces validates values, not just presence, because the failure
mode here is silent: a wrong surface removes a skill from a harness rather than
erroring. install.sh links only skills whose surfaces include `library`, and a
source that declares nothing at all is treated as foreign and linked as-is —
Anthropic's official set has no reason to know this convention. doctor's
missing-link check skips non-library skills for the same reason.

Refs #29
Bump-Type: minor
This commit is contained in:
2026-08-29 10:09:52 +02:00
parent 15737321ac
commit 90a58f0b9e
49 changed files with 214 additions and 1 deletions
+1
View File
@@ -1,5 +1,6 @@
---
name: trainer
surfaces: [claude-code, library]
description: Two-phase brain curation — scan session logs to score candidate learnings (READ), then write the ones that pass the quality gate as generalized knowledge entries (WRITE). Use periodically to keep the brain useful, not noisy.
---