skill-agent-gateway — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-agent-gateway (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP-based gateway providing intelligent discovery, search, and lazy-loading for the Claude Code skill and agent ecosystem.
All tools are provided via the user-dcl-wrapper or skill-agent-gateway MCP server.
gateway_discoverBrowse by category. Call with no args for overview.
gateway_discover() # All categories
gateway_discover(category="lark") # Items in Lark category
gateway_discover(resource_type="agent") # Agents onlygateway_searchKeyword search — supports Chinese and English.
gateway_search(query="tdd")
gateway_search(query="飞书日历")
gateway_search(query="frontend", resource_type="skill")gateway_loadLoad details for a specific skill or agent.
gateway_load(name="web-access", resource_type="skill")
gateway_load(name="code-reviewer", resource_type="agent", detail_level="full")gateway_recommendTask-based skill + agent recommendations.
gateway_recommend(task_description="重构后端 API")
gateway_recommend(task_description="write a technical blog post")gateway_statsEcosystem statistics and health check.
gateway_rebuild_indexRe-scan directories and rebuild the index.
gateway_discover → pick category → gateway_search → gateway_load → Read SKILL.md~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.