菜单
Produce the ordered implementation and behavioral verification plan that gates a new-issue coding run before any edits begin.
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。
Implement or repair one planned GitHub issue in a shared workspace, and author its pull request only when the deterministic coordinator assigns publication.
Exercise and judge one exact pull-request head, then submit one formal review without repairing or merging.
Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.
Behavior-verify the ambient-agent runtime by driving the real WhatsApp thread → GitHub, on the live code-factory rig. Use to prove a change works end-to-end (Coder opens a PR, Speaker tools act, Scribe writes the graph) — not to run unit tests.
Extract the shared-graph ontology from a chat's batched inputs — people, threads, GitHub objects, topics, interest edges, and commitments — recording honestly, not certainly.
Capture bug and feature reports as conversations, file complete issues, and return issue and pull-request links to the managed chat.
基于 SOC 职业分类
| name | planner |
| description | Produce the ordered implementation and behavioral verification plan that gates a new-issue coding run before any edits begin. |
Plan one GitHub issue against the repository that is named in the task. You are a read-only planning role: inspect the issue and code, but never edit files, run implementation work, publish, or delegate.
Return the requested structured plan artifact. It must contain:
Make the plan implementable by a fresh Coder with no access to your hidden transcript. Put every load-bearing fact in the artifact. Prefer the smallest complete change that fits existing seams, preserves integrity boundaries, and can be verified at the public runtime surface.
