| name | skill-create |
| version | 2.4.0 |
| description | Analyze the repository's technology stack and generate appropriate skills, rules, and hook configurations. |
| trigger | manual |
| depends-on | [] |
| references | [] |
| disable-model-invocation | true |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep, Bash, Edit, Write |
skill-create
Analyzing repository and generating technology skills.
1. Scan Repository
Identify technologies, frameworks, and tools in use:
1a. Parse dependency files
Scan for all dependency/config files in the project:
package.json, pyproject.toml, Cargo.toml, Package.swift
go.mod, pom.xml, build.gradle, Gemfile, composer.json
.pre-commit-config.yaml, CI configuration files
1b. Scan imports and usage
Identify major technology areas by scanning source code imports and configuration files.
1c. Check existing skills
Read .claude/skills/SKILLS_INVENTORY.md to avoid creating duplicates.
2. Classify Technologies
Categorize each technology by impact and relevance:
| Category | Examples | Skill Priority |
|---|
| Core Framework (>20% of codebase) | React, Django, Rails, SwiftUI | High — create skill + reference doc |
| Major Library (significant usage) | SQLite, Redis, Prisma | Medium — create skill |
| Build/Dev Tool (development workflow) | webpack, jest, ruff | Low — create skill if complex |
| Minor Dependency (small usage) | lodash, httpx, pydantic | Skip — standard usage, no skill needed |
Decision Criteria for Reference Documents
Create reference docs co-located with the skill (.claude/skills/<tech-name>/references/) when:
- Technology is core (>20% of codebase interaction)
- API is complex with project-specific patterns
- Version-specific gotchas exist that an LLM would miss
- Official documentation is large and we use a specific subset
Co-locating references with skills keeps everything self-contained and allows relative path references from SKILL.md.
Skip reference doc when:
- Usage is standard/well-known (e.g., JSON, basic HTTP)
- Official docs are concise and sufficient