@majiayu000/shared-setup-patterns
BShared configuration patterns for project setup commands. Provides security hooks, Claude framework structure templates, and framework detection patterns used across multiple setup commands.
Install
agr install @majiayu000/shared-setup-patterns --target claudeWrites 2 files into .claude/skills/, pinned to git-37f510f4.
- .claude/skills/shared-setup-patterns/SKILL.md
- .claude/skills/shared-setup-patterns/metadata.json
Document
name: shared-setup-patterns description: Shared configuration patterns for project setup commands. Provides security hooks, Claude framework structure templates, and framework detection patterns used across multiple setup commands.
Shared Setup Patterns
Purpose: Common configuration patterns and templates shared across all project setup commands.
Used by: /setup:python, /setup:javascript, /setup:existing, /setup:explore, /setup:user
Token Impact: Provides ~1,700 tokens of shared templates loaded once, avoiding duplication across 5+ commands (saves ~3,200 tokens through reuse).
Contents
This skill contains ONLY patterns shared by multiple setup commands:
- Security Hooks - PreToolUse and PostToolUse hooks for all project types
- Claude Framework Structure - .claude/ directory templates and memory files
- Framework Detection - Patterns for auto-detecting project languages and frameworks
Language-specific templates (Python, JavaScript, etc.) are kept inline in their respective commands.
1. Security Hooks
Located: templates/security_hooks.json
Comprehensive security and quality hooks configuration:
- PreToolUse: Blocks dangerous commands (rm -rf, sudo, chmod 777)
- PostToolUse: Auto-formats code (ruff, prettier, eslint), validates JSON/markdown
Used by: ALL setup commands that create projects
2. Claude Framework Structure
Located: templates/claude_framework/
Templates for .claude/ directory structure:
structure.md- Directory layout and purposememory_templates/- project_state.md, dependencies.md, conventions.md, decisions.mdwork_structure.md- Work directory organization
Used by: ALL setup commands
3. Framework Detection Patterns
Located: templates/framework_detection.md
Patterns for auto-detecting:
- Languages: Python, JavaScript/TypeScript, Go, Rust
- Frameworks: FastAPI, Django, Flask, Next.js, React, Express
- Tools: pytest, Jest, Mocha, go test, cargo test
Used by: /setup:existing, /setup (if dispatcher exists)
Usage Pattern
Commands reference this skill in frontmatter:
skills: [shared-setup-patterns]
Then access specific templates:
- Security hooks: Load from
templates/security_hooks.json - Framework structure: Generate from
templates/claude_framework/templates - Detection: Use patterns from
templates/framework_detection.md
Design Principle
Only truly shared content lives here. Language-specific templates (Python pyproject.toml, JavaScript package.json) stay inline in their respective commands to avoid skill overhead for single-use templates.
This keeps each command self-contained while sharing common infrastructure patterns.
Repository README
Describes majiayu000/claude-skill-registry-data as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.
Claude Skill Registry (Data)
This repo contains the archived skill contents (the heavy, browsable skill files).
Canonical layout
- Category folders at repo root (e.g.
development/,documents/,data/, ...) - Each skill lives under a category:
<category>/<skill>/SKILL.md+<category>/<skill>/metadata.json - Case conflicts are resolved with
{name}-{owner}-{repo}suffixes (fallback:-{short-hash}).
Archive status
- Live badges above are sourced from
claude-skill-registry-corestats.json. - Counts in this README are intentionally dynamic, not hardcoded.
- If the badges look stale, refresh the
corebuild/index pipeline rather than editing numbers here.
Where the index + site live
- Core repo: https://github.com/majiayu000/claude-skill-registry-core
- Main repo (merged publish artifact): https://github.com/majiayu000/claude-skill-registry
Trustgrade B
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- warnLicenseno SPDX license detected
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-37f510f42d082026-07-31