From searchpo
Use when Searchpo agents need to inspect available .env keys, provider/API capabilities, DeepWiki MCP availability, credential routing, side-effect boundaries, or decide which agent should use which external service without exposing secrets.
How this skill is triggered — by the user, by Claude, or both
Slash command
/searchpo:searchpo-agent-capabilitiesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill to let Searchpo agents organize available credentials and MCP services without leaking secrets.
Use this skill to let Searchpo agents organize available credentials and MCP services without leaking secrets.
config/agent_capabilities.jsonscripts/agent_capabilities.py.mcp.json.env only; never print, copy, or persist values.python3 scripts/agent_capabilities.py --profile all --format text
Use narrower profiles when possible: research, repo, paper, implementation, provider, render, lambda, publish, or live.
Route work by owner:
searchpo-research-agent: DeepWiki MCP, GitHub/GitLab/source APIs, AnySearch and supplemental research, social/web source context.searchpo-impl-agent: DeepSeek, Gemini, Remotion, Lambda, Douyin adapter/upload execution.searchpo-main-agent: command profile selection, side-effect boundary, notification, final release decision.Treat status=available as permission to use a capability only inside the existing Searchpo gate model. Live publishing still requires an explicit current-run user request.
If a required capability is unavailable, fail at the relevant gate and report the missing key names only.
.env.example only as a variable-name reference; it must not contain real values.npx claudepluginhub sunflowerslwtech/sunkit --plugin searchpoResolves and loads capabilities across multiple agent ecosystems (Claude, Codex, Gemini, OpenCode, OpenClaw, .agents). Use to find which agent has a skill for a given task before authoring a new one.
Connects agents to external APIs, MCP servers, Lambda functions, and OpenAPI tools via Gateway. Handles outbound auth, credentials, and Cedar policy authoring.
Sub-agent skill that evaluates tools during setup by checking MCP availability and API capabilities, returning a unified capability matrix.