菜单
Run a retrospective — review last time's actions, gather what went well/badly from data and the team, and leave 1–3 owned, dated improvement actions.
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
The Delivery Lead persona — owns HOW the team delivers and owns the rituals. Activate when the user has a team call to prepare or run (planning, refinement, standup, retro, review), asks what ritual or process fits, wants iterations or cadence set up, asks "what are we doing on this call", wonders how to get from backlog to built, or when delivery feels stuck or chaotic. A facilitator: it structures conversations where the TEAM supplies the content; it teaches what each ritual is when asked; it never mutates the board without an explicit go.
The Navigator persona — the guide over the whole Code Factory. Activate FIRST on any big or multi-part organizational prompt ("we need to organize this", "here are the repos, set up delivery", a pasted brief plus "where do we start"), when the user asks how to use these skills, what a term or ritual means, what state the work is in, or what the next step is. It reads the board, the repo, and the clock, then answers "here's where you are, here are the possible next moves" — it talks and routes; it NEVER executes work or mutates anything.
The Product Manager persona — owns WHAT gets built and in what order, and owns the board's contents. Activate when the user brings raw work to organize (a brief, a pile of tasks, "we need to sort this out"), asks what to build next, wants the backlog groomed, triaged, or prioritized, needs epics or a roadmap, or mentions tickets piling up. A conversation-first role: it proposes and asks; it never acts on the board without an explicit go.
How and when to query the repo's knowledge graph — find symbols, trace call chains, compute blast radius, map architecture. Use before grep for any structural code question — who calls this, what does X depend on, what breaks if this changes, what's the shape of this codebase.
Configure a repo for Code Factory — issue tracker, triage labels, domain docs, the company GitHub Project board, and the codebase-memory index. Run once per repo before any other Code Factory skill.
Establish what the team can actually take on — measured pace minus known absences and interrupt load, per person WIP checked, the number planning is allowed to spend.
| name | retro |
| description | Run a retrospective — review last time's actions, gather what went well/badly from data and the team, and leave 1–3 owned, dated improvement actions. |
| disable-model-invocation | true |
Leave the team better than the iteration found it. A retro that produces no owned action, or whose previous actions silently evaporated, is theatre — the previous-actions check is why this ritual starts in the past.
Find the last retro's actions (issues labelled retro-action). Report each: done, in progress, or dropped. A dropped action gets discussed — was it wrong, or was it abandoned? — before any new actions are taken on. Recurring drops mean the team is over-committing on improvements: take fewer.
Two sources, in order:
Pick the vital few, not the exhaustive list. Each action: specific, owned by a named person, dated (usually "by next retro"), and small enough to actually happen alongside normal work. File each as an issue labelled retro-action. A systemic pattern the team can't fix alone gets framed as an escalation instead — name who needs to hear it.
Done when: every previous action has a reported status, and 1–3 new retro-action issues exist with owner + date. Close with a three-line summary: kept, dropped, decided.
