菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | searchpo-agent-capabilities |
| description | 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. |
| version | 1.0.0 |
| triggers | [".env","API keys","agent capabilities","credential routing","provider keys","DeepWiki MCP availability","能力清单","密钥路由"] |
| tools | ["shell","filesystem"] |
| mutating | false |
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.Convert prompts, vague tasks, product requirements, coding requests, research plans, monitors, reminders, and agent workflows into repeatable, verifiable loops. Use when the user asks to "loopify" a requirement, turn a prompt into an agent loop, design unattended or recurring work, define /loop or routine instructions, create guardrails for autonomous agents, convert one-shot tasks into monitored workflows, or make future prompts more reliable through goal/scope/verification/escalation/stop conditions.
Frontend design cognitive system grounded in Michael Polanyi's tacit knowledge theory. Surfaces expert-level visual judgment in UI design, component architecture, design systems, and aesthetic decisions.
Domain knowledge for designing a search harness for coding agents — search API landscape, ground-API pipeline/strategy, CLI + skills architecture, and roadmap. Use when discussing search agent infrastructure, choosing search APIs for agents, designing search pipelines, or reviewing the search-harness project direction.
Remotion video composition best practices for searchpo. Use when editing src/ components, configuring rendering, optimizing video output, or adding animations/effects to the Remotion pipeline.
Use when a Searchpo task involves GitHub repository understanding, DeepWiki MCP, repo architecture questions, dependency exploration, or source-code context as supporting context after AnySearch-first evidence planning has started.
Run the full Searchpo provider/live flow from input selection through evidence, FactBank, DeepSeek/Gemini, Remotion render, audit, delivery package, and Douyin gate verification. Use when the user asks to run the complete flow, full flow, /searchpo-full-flow, end-to-end publishable render, or live publish.