菜单
Review one assigned PlanWeave review gate and produce a pass or needs_changes result. Use when a coordinator assigns a specific review ref, implementation evidence, and review-result expectation.
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
Review an already-authored PlanWeave plan for goal coverage, data-flow coverage, lifecycle gaps, contract drift, execution graph errors, weak prompts, and unverifiable completion criteria. Use when auditing, reviewing, checking, or challenging a PlanWeave plan before execution.
Coordinate end-to-end PlanWeave execution as the main agent by inspecting status, assigning work to subagents, routing review and recovery, and keeping the plan loop moving. Use when orchestrating a full PlanWeave plan, managing multiple agents, continuing execution, or deciding what should run next.
Import existing project documentation into a block-level PlanWeave Plan Package and validate it through the PlanWeave CLI. Use when importing PRDs, roadmaps, issue sets, architecture notes, or another strong source plan.
Create a PlanWeave package-shaped plan draft from a fuzzy goal, sparse requirements, codebase context, or a user idea before a formal Plan Package exists. Use when the user asks to make, draft, design, break down, or plan PlanWeave work without an existing PRD, roadmap, issue set, or strong source plan. Materialize a Plan Package only when the user explicitly asks.
Diagnose and recover PlanWeave execution anomalies such as stale current refs, state/results drift, orphan artifacts, blocked or diverged blocks, submit retries, and review-feedback loop inconsistencies. Use when PlanWeave execution state looks wrong, doctor reports issues, submit partially succeeded, or coordinator cannot safely continue.
Execute one assigned PlanWeave implementation block with scoped code changes, validation, and a completion report. Use when a coordinator assigns a specific implementation ref, prompt, scope, and reporting expectation.
| name | plan-reviewer |
| description | Review one assigned PlanWeave review gate and produce a pass or needs_changes result. Use when a coordinator assigns a specific review ref, implementation evidence, and review-result expectation. |
Use this skill after the coordinator assigns one review gate. Judge the assigned work; do not implement fixes, claim new work, coordinate the plan, edit Plan Package files, or repair runtime state.
The handoff should include:
review-result.json path or instruction to return the JSON.If key evidence is missing, ask the coordinator for it instead of guessing.
claim-next; claim only the exact review ref if the coordinator explicitly says claim required.passed or needs_changes; submit only if the coordinator explicitly asked you to submit.passed only when acceptance is met and validation evidence is adequate.needs_changes for incomplete, unsafe, unverifiable, out-of-scope, or contract-breaking work.NEEDS_COORDINATOR for blocked work, divergence, missing evidence, tool failure, stale prompts, invalid acceptance, bad dependencies, or review-gate design defects.project-graph.json, canvas manifest.json, source prompt Markdown, state.json, or results/.NEEDS_COORDINATOR to the coordinator.{
"reviewBlockRef": "T-001#R-001",
"taskId": "T-001",
"verdict": "needs_changes",
"content": "Concrete feedback for the implementation agent."
}
For passed, cite evidence. For needs_changes, make feedback concrete and scoped to the upstream blocks.
Write content as concise Markdown. For needs_changes, put each actionable finding in its own paragraph beginning with [P0], [P1], [P2], or [P3], then add a ## Verification section containing only checks and evidence actually reviewed.