菜单
Research the web for solutions, competitors, alternatives, or prior art for a decision facing this project — then store the findings in project memory so they survive the session. Use when choosing a library or approach, comparing tools, checking what others do, or evaluating whether to build vs adopt.
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
Rebuild a flow-first project wiki using the mimirs wiki MCP tool. Use when the user asks to generate, rebuild, refresh, or write the wiki for a codebase.
Build an accurate mental model of an unfamiliar codebase, feature, or area before changing it — where it lives, how it connects, what it does, and why. Use when asked how something works, where something is, when onboarding to a repo, or before editing code you don't know. For a cross-cutting question that needs answering from many sources, use research instead.
Wrap up a work session so the next session (or another agent) can pick up cleanly — what was done, what's in flight, what to watch out for. Use when ending a session, switching tasks, or asked to hand off, wrap up, or save state for later.
Design an implementation plan before writing code — where the change lands, what it will touch, what could break, and the steps in order. Use when asked to plan a feature, scope a change, or figure out how to approach an edit before making it. To assess a change that already exists (a diff, refactor, or rename), use review instead.
Answer "why" and "when" questions about a project's decisions — the intent behind a past choice, when it was made, what was tried before and rejected. Use when asked why something was decided, what the rationale was, or before reversing or redoing earlier work. For why the code mechanically behaves a certain way use research; for why it breaks use debug.
Answer a hard, open-ended question about how the project works or is built by synthesizing every source — code, structure, git history, prior decisions, discussion, caveats — and verifying each claim against the source. Use for deep cross-cutting questions that span more than one area. Narrower siblings — a single area's structure is explore, the rationale behind one past decision is recall, a failure's root cause is debug.
| name | scout |
| description | Research the web for solutions, competitors, alternatives, or prior art for a decision facing this project — then store the findings in project memory so they survive the session. Use when choosing a library or approach, comparing tools, checking what others do, or evaluating whether to build vs adopt. |
Goal: a sourced recommendation for a project decision — and it persists. Web research evaporates; the point of this skill is that the comparison and the why land in mimirs memory, so a later session recalls "we evaluated X vs Y and picked Y" instead of re-researching. Where research answers a question from the codebase and deep-research writes a generic report, scout weighs external options against this project and records the verdict.
search/read_relevant for what we already use (stack, existing deps, conventions) so the recommendation actually fits. A fast option that doesn't match the stack is not a real option.WebSearch for solutions, competitors, alternatives, and prior art. Cast wide first, then narrow to the serious contenders.WebFetch the primary sources (docs, repos, release notes) for the specifics that decide it: features, tradeoffs, maturity, license, last release / activity, and known issues. Prefer source over summaries.read_relevant the code it would touch.create_checkpoint (type decision) with the comparison, the choice, and why — this is the durable record; stamp the date and the versions you checked, since web facts go stale. annotate a file only when a finding pins to specific code (a CVE on the import site, a deprecated API on the call site) — not for general option notes, which have no file to anchor to.Finish: the recommendation with its tradeoffs and source links, and confirm it's saved as a checkpoint (with date + versions) so a future session can recall the decision. Flag findings likely to age out.