Commit Graph
3 Commits
Author SHA1 Message Date
d29cf651c7 fix(skills): declare activation triggers in descriptions and normalize version metadata (#2618)
* fix(skills): move version into metadata and normalize to semver

29 skills declared `version` at the top level of their frontmatter. The
schema reads it from `metadata`, so tooling that follows the schema either
misses it or has to special-case the top level.

Three motion skills also declared `version: 1.0`, which is not a valid
semantic version; normalized to `1.0.0`.

No behavioral change — frontmatter metadata only.

* fix(skills): state activation triggers in skill descriptions

148 skills described what they cover but never named the situation that
should trigger them. Since the description is what Claude matches against
to decide whether to load a skill, a description without a trigger makes
activation guesswork — the skill is either missed or loaded at the wrong
time.

Added a "Use when ..." clause to each, derived from the skill's own body
(most already stated the trigger under "## When to Use" or in the opening
line; that intent is now reflected in the frontmatter where it is actually
read from).

Descriptions were only appended to; no existing wording was removed.

* fix(skills): sync activation triggers into the Codex skill mirror

10 of the skills whose descriptions changed are also mirrored under
`.agents/skills/`, where the description was previously a verbatim copy.
Left alone, the two surfaces would disagree about when the skill applies.

Only the description line is synced; the Codex copies keep their reduced
frontmatter, since that validator accepts only name, description,
metadata, license, and allowed-tools.

* fix(skills): correct three activation clauses from review

- autonomous-loops: the clause pulled new loop work into a skill that its
  own body marks as a compatibility shim retained for one release. It now
  points at the canonical continuous-agent-loop instead.
- continuous-learning: the description carried the v1 routing directive
  twice; collapsed to one.
- homelab-pihole-dns: the clause fired on any broken home DNS. Narrowed to
  tasks that actually involve Pi-hole.

* chore: retain current main lockfile

---------

Co-authored-by: Çağrı Solakoğlu <cagri.solakoglu@vtcenerji.com>
Co-authored-by: haelyra <49814733+haelyra@users.noreply.github.com>
2026-08-11 23:58:14 -04:00
BERORINPO db7f2a6fd5 fix(skills): move top-level origin frontmatter key under metadata
The official Agent Skills spec (agentskills.io/specification) whitelists exactly
6 top-level frontmatter keys (name/description/license/compatibility/metadata/
allowed-tools). A top-level `origin` key fails the official validator
(anthropics/skills quick_validate.py ALLOWED_PROPERTIES; skills-ref validate).

This moves `origin: X` -> `metadata.origin: X` across the canonical skills/
tree, preserving each value verbatim. Frontmatter-only, minimal diff.

- 251 SKILL.md updated (242 new metadata block, 9 appended to existing metadata)
- origin values preserved verbatim (verified 251/251)
- YAML validated on all changed files
- scoped to canonical skills/ only (docs/<lang> translations + tool mirrors
  .cursor/.kiro/.agents left untouched; presumably regenerated from canonical)

Addresses #2233
2026-06-11 21:12:21 +09:00
477d23a34f feat(agents,skills): add opensource-pipeline — 3-agent workflow for safe public releases (#1036)
* feat(agents,skills): add opensource-pipeline — 3-agent open-source release workflow

Adds a complete pipeline for safely preparing private projects for public
release: secret stripping (20+ patterns), independent sanitization audit,
and professional doc generation (CLAUDE.md, setup.sh, README, LICENSE).

Agents added:
- agents/opensource-forker.md    — copies project, strips secrets, generates .env.example
- agents/opensource-sanitizer.md — independent PASS/FAIL audit, read-only, 20+ patterns
- agents/opensource-packager.md  — generates CLAUDE.md, setup.sh, README, LICENSE, CONTRIBUTING

Skill added:
- skills/opensource-pipeline/SKILL.md — orchestrator: routes /opensource commands, chains agents

Source: https://github.com/herakles-dev/opensource-pipeline (MIT)

* fix: address P1/P2 review findings from Cubic, CodeRabbit, and Greptile

- Collect GitHub org/username in Step 1, use quoted vars in publish command
- Add 3-attempt retry cap on sanitizer FAIL loop
- Use dynamic sanitization verdict in final review output
- Broaden rsync exclusions: .env*, .claude/, .secrets/, secrets/
- Fix JWT regex to match full 3-segment tokens (header.payload.signature)
- Broaden GitHub token regex to cover gho_, ghu_ prefixes
- Fix AWS regex to be case-insensitive, match env var formats
- Tighten generic env regex: increase min length to 16, add non-secret lookaheads
- Separate heuristic WARNING patterns from CRITICAL patterns in sanitizer
- Broaden internal path detection: macOS /Users/, Windows C:\Users\
- Clarify sanitizer is source-read-only (report writing is allowed)

* fix: flag *.map files as dangerous instead of skipping them

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

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-31 14:06:23 -07:00