skills-management
Skills Management
Unified entry point for the entire skill lifecycle: finding existing skills, writing new ones, enforcing conventions, reviewing quality, and managing installations.
Reference Files
Load the reference appropriate to your current task:
| Reference | When to load |
|---|---|
| references/finding-skills.md | Discovering and vetting skills from marketplaces and repos |
| references/writing-skills.md | TDD methodology for authoring new skills |
| references/conventions.md | Directory layout, naming rules, frontmatter requirements |
| references/skill-manager-usage.md | CLI reference for the skill-manager script |
| references/dispatch-prompt-template.md | 6-section template for agent dispatch prompts |
| references/agent-skills-spec.md | Agent Skills open standard reference |
| references/reviewing-skills.md | Auditing skills for quality and portability |
Writing-Skills Sub-References
The writing-skills reference has its own deep-dive files:
| Reference | Content |
|---|---|
| references/skill-structure.md | SKILL.md structure, directory layout, file organization |
| references/claude-search-optimization.md | CSO techniques, keyword coverage, token efficiency |
| references/testing-methodology.md | Testing all skill types, rationalizations, bulletproofing |
| references/skill-creation-checklist.md | Complete TDD-adapted checklist |
| references/anti-patterns.md | Anti-patterns with examples |
| references/context-optimization-patterns.md | Extracting oversized skills, plugin-to-skill conversion |
Quick Decision
- Need a capability? Start with finding-skills to search before building
- Building from scratch? Use writing-skills (TDD methodology)
- Unsure about structure? Check conventions and agent-skills-spec
- Auditing existing skills? Use reviewing-skills
- Managing installs? Use skill-manager-usage
More from hjewkes/agent-skills
self-improve
Use when a session produced reusable insights, when the user says "learn from this", "remember this", or "improve yourself", or after completing a complex task where patterns were discovered
63md-render
Use when asked to render, preview, or view a markdown file in the browser. Triggers on "render markdown", "preview this", "show me this document", "open in browser".
21code-review
Unified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.
17github-pr
GitHub PR workflow — creating PRs, posting automated review comments, managing PR feedback cycles. Use when code is reviewed and ready for GitHub.
14buildkite
Buildkite CI/CD integration. Use when the user needs to check build status, trigger builds, read build logs, debug failures, manage pipelines, or any Buildkite workflow. Triggers include "buildkite", "build", "pipeline", "CI", "deploy", "build log", "build failed".
14agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
13