菜单
Use when development work depends on current or external facts: latest docs/APIs, library or platform behavior, security guidance, unfamiliar errors, migrations, comparisons, best practices, prior art, or known fixes.
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
Use when a development task is unclear, multi-step, risky, or needs coordinated gates for shared understanding, research, parallel lanes, workflow artifacts, and verification. For a single concern, use the matching gate skill if available; for tiny mechanical changes, skip unless the user asks.
Use when development work has independent lanes for research, codebase exploration, inventory, validation, review, or non-overlapping implementation that can run in subagents, parallel tool calls, or separately owned workstreams.
Use when development work is large, risky, multi-session, multi-agent, interrupted, or needs durable plan/handoff memory for continuity across coding agents.
Use when a development request is vague, exploratory, conflicted, under-specified, or the user says they are unsure, wants to be grilled, wants assumptions challenged, or needs goal, scope, constraints, and success criteria clarified before planning or implementation.
Use before saying development work is done, or when choosing project-shaped tests/checks to prove code behavior, bug fixes, refactors, config, infrastructure, or UI changes.
Pi-only web research workflow for environments that have pi-9router-ext and a subagent extension such as @tintinweb/pi-subagents configured. Use this skill when the user explicitly asks to use 9router, pi-9router-ext, ninerouter tools, or a 9router route/combo for web research, or when project/user instructions state that 9router-web-researcher is the preferred research stack. Do NOT use for ordinary web research in standard shared-mcp-only or non-Pi clients; use web-researcher instead. This skill always delegates research lanes to subagents and then synthesizes compact cited findings.
| name | research-gate |
| description | Use when development work depends on current or external facts: latest docs/APIs, library or platform behavior, security guidance, unfamiliar errors, migrations, comparisons, best practices, prior art, or known fixes. |
Research is for reducing uncertainty, not for delaying local work.
Inspect local docs and code first when the answer may be repo-defined.
Use external research when:
Skip research when the answer is clearly local, mechanical, or already covered by authoritative repo docs/tests. If skipped, say why briefly.
Prefer sources in this order:
When research is used, cite source links in the answer. For medium/large work, also record important links and date-sensitive findings in the live workflow artifact.
End the gate only after local docs/code have been inspected or explicitly ruled out. If research is used, record each implementation-shaping finding, its authoritative source link, version/date constraints, conflicts or unavailable authoritative sources, and implementation impact. If research is skipped, state the repo-local evidence that makes it unnecessary.
