Agent skill
janitor-search
Search GitHub for new skills to install. Also use with --compare to analyze a local skill against GitHub alternatives and marketplace competition.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/janitor-search
Metadata
Additional technical details for this skill
- version
- 1.1.0
SKILL.md
Skill Discovery & Comparison
Search GitHub for Claude Code skills by keyword, or compare a local skill against alternatives.
How to Run
# Search for skills
bash ~/.claude/skills/skills-janitor/scripts/search.sh <keyword> [--limit N] [--json]
# Compare your skill against GitHub alternatives
bash ~/.claude/skills/skills-janitor/scripts/search.sh --compare <skill-name> [--json]
Search Mode
<keyword>- required search term (e.g., "marketing", "deployment", "testing")--limit N- max results (default: 10)--json- raw JSON output
How It Works
- Searches GitHub repos matching
{keyword} claude skillin name/description/README - Also searches by topic tag
claude-code - Cross-references results against your installed skills and plugins
- Marks each result as
INSTALLEDorAVAILABLE
Compare Mode (--compare)
Analyzes a local skill against alternatives found on GitHub:
- Composite scoring: 40% keyword overlap, 30% popularity, 15% recency, 15% activity
- Shows marketplace install counts when available
- Reports market position (unique niche vs. crowded space)
search.sh --compare my-marketing-skill
Rate Limits
- Unauthenticated: 60 requests/hour
- Set
GITHUB_TOKENenv var for 5,000 requests/hour - Results cached for 24 hours
Related Skills
- For checking which skills you actually use:
/janitor-usage - For token cost analysis:
/janitor-tokens - For pre-install overlap check:
/janitor-precheck
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?