aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Build a project skill library under .claude/skills/ as a resumable mission: discover, author in parallel, review adversarially.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/skill-libraryContext preview
What this command does when you run it.
Build a project skill library under .claude/skills/ as a resumable mission: discover, author in parallel, review adversarially.
name: skill-library description: "Build a project skill library under .claude/skills/ as a resumable mission: discover, author in parallel, review adversarially."
Build (or rebuild) a project skill library under `.claude/skills/` so junior engineers and Sonnet-class models can carry the project forward: debug it, extend it, validate it, and advance it at the departing expert's standard.
Use this command when you need to:
or session holding it moves on
Avoid this command if:
`/abstract:create-skill`)
`Skill(plugin-dev:skill-development)`)
`/abstract:skills-eval`)
# Full mission: discover, author, review, report /attune:skill-library # Resume an interrupted mission from .attune/mission-state.json /attune:skill-library --resume # Constrain the library size (default: adapt within 10-16) /attune:skill-library --max-skills 12
1. Invokes `Skill(attune:skill-library-mission)` and creates a custom mission in `.attune/mission-state.json` with phases `discover, author, review, report` 2. **Discover**: investigates the repo like an incoming principal engineer, then asks the user at most five questions the repo cannot answer 3. **Author**: dispatches one authoring agent per skill from the adapted taxonomy, each carrying the non-negotiable authoring rules and a write fence limited to `.claude/skills/` 4. **Review**: runs factual, doctrine, and usability reviewers in parallel, then one fixer applying blocking and important findings 5. **Report**: delivers the skill inventory, spot-check evidence, and remaining uncertainties
| Argument | Description | |----------|-------------| | `--resume` | Continue from saved mission state | | `--max-skills <n>` | Cap the adapted taxonomy at `n` skills | | `--skip-questions` | Proceed with repo evidence only; record assumptions in mission state |
state and resume machinery
this command dispatches
phase routing
enforce
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.