Distills tool patterns from external repositories into teachable skills and plugins. Use when build plugin for, create skills for CLI, package as plugin, repo to plugin, or turn into plugin are mentioned.
Transforms external repositories into Claude Code plugins by analyzing codebases and extracting automation patterns.
npx claudepluginhub outfitter-dev/outfitterThis skill is limited to using the following tools:
references/overview.mdreferences/repo-types.mdreferences/stage-1-discovery.mdreferences/stage-2-recon.mdreferences/stage-3-patterns.mdreferences/stage-4-mapping.mdreferences/stage-5-authoring.mdreferences/stage-6-packaging.mdreferences/stage-7-audit.mdTransform external repositories into Claude Code plugins.
External Repo → Research → Recon → Patterns → Codify → Author → Package → Audit → Plugin
research skill for external discovery (docs, APIs, community patterns)codebase-analysis skill for internal analysis of target repofind-patterns skill to extract repeatable patterns worth automatingcodify skill to map patterns to component typesskillcraft or claude-craftclaude-plugins skill to package into distributable pluginclaude-plugins audit checklists<when_to_use>
NOT for: plugins from scratch (use claude-plugins), single-skill creation (use skillcraft), auditing existing plugins (use claude-plugins)
</when_to_use>
Track progress with artifacts in artifacts/skill-distillery/:
artifacts/skill-distillery/
├── discovery.md # Research output (docs, APIs, community patterns)
├── recon.md # Codebase analysis (structure, conventions, key files)
├── patterns.md # Extracted patterns with automation value
├── mapping.md # Pattern → component mapping decisions
├── components/ # Authored skills, agents, hooks, commands
│ ├── skill-1/
│ ├── skill-2/
│ └── ...
└── audit.md # Plugin validation results
For simple repos (single-purpose CLI, small API wrapper):
Trigger: User says "quick", repo has < 5 main commands, or clear single purpose.
Load the maintain-tasks skill for stage tracking. Stages advance only.
| Stage | Skill | activeForm |
|---|---|---|
| 1. Discovery | research | "Researching external docs" |
| 2. Recon | codebase-analysis | "Analyzing target repo" |
| 3. Patterns | find-patterns | "Extracting patterns" |
| 4. Mapping | codify | "Mapping to components" |
| 5. Authoring | skillcraft | "Creating components" |
| 6. Packaging | claude-plugins | "Packaging plugin" |
| 7. Audit | claude-plugins | "Validating plugin" |
Load research skill. Gather external docs, community patterns, pain points.
See stage-1-discovery.md for details.
Load codebase-analysis skill. Analyze structure, API surface, conventions.
See stage-2-recon.md for details.
Load find-patterns skill. Extract workflows, command sequences, decision points.
See stage-3-patterns.md for details.
Load codify skill. Map patterns to component types (skill, command, hook, agent).
See stage-4-mapping.md for details.
Load appropriate skill per component type. Create in artifacts/skill-distillery/components/.
See stage-5-authoring.md for details.
Load claude-plugins skill. Create plugin structure with manifest and README.
Ask: "Do you have an existing marketplace to add this plugin to?" If yes, prepare the marketplace entry.
See stage-6-packaging.md for details.
Validate using the claude-plugins audit checklists. See its references/audit.md.
See stage-7-audit.md for details.
</workflow><decision_points>
Key decisions during engineering process:
Which patterns to automate?
Skills vs Commands?
Include agents?
Quick mode vs full pipeline?
</decision_points>
<rules>ALWAYS:
NEVER:
Stage guides:
Skills loaded:
research — external discovery methodologycodebase-analysis — repo analysis approachfind-patterns — pattern extractioncodify — pattern-to-component mappingclaude-plugins — plugin packagingActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.