菜单
Spec review via the consolidated belt:spec-reviewer agent. Reviews any spec-family document (requirements.md, goal-sheet.md, design.md, plan.md). Findings are triaged in one batched selection. --codex adds an adversarial pass via /codex:rescue in the same parallel batch.
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。
Experimental (mattpocock/skills wayfinder port, MIT). Charts a foggy effort as a shared Linear decision map, resolves its decision tickets across bounded sessions, and hands one graduated effort to /belt:requirements. Upstream of /belt:feature-dev; one run graduates exactly one effort.
Runs the shared build stage: TDD implementation from the plan document's task list and two-agent code review with autonomous triage. Use standalone with an existing plan.md/fix-plan.md, or composed as the build stage of /belt:feature-dev and /belt:bug-fix. QA runs as its own stage (/belt:qa) after build; integration happens at the orchestrator's integrate phase.
Runs the feature design stage: goal-sheet intake (/belt:goal) followed by a design document (architecture + key decisions) reviewed by belt:spec-reviewer. Use standalone for design-only work, or composed as the first stage of /belt:feature-dev. Task breakdown lives in the plan stage (/belt:plan), not here. --codex enables adversarial spec review.
Runs the bug diagnosis stage: root-cause analysis with a failing reproduction test and reproduction scenarios, fix planning, and adversarial plan review. Use standalone for diagnosis-only work, or composed as the upstream stage of /belt:bug-fix. --codex enables adversarial plan review.
Quality-gated feature pipeline from ticket to integration: goal-sheet intake, design document with spec review, implementation plan with QA scenarios, context-reset checkpoint, TDD implementation, autonomous code review, mandatory QA with human-readable evidence (screenshots / transcripts), and integration with evidence publishing. Accepts a Linear id, URL, free text, or a requirements.md path. --codex enables adversarial review.
Runs the implementation planning stage: writes plan.md (test strategy + task list) and scenarios.yml (QA replay scenarios) from an approved design.md, then reviews the plan via belt:spec-reviewer. Use standalone when a design already exists, or composed between the design and build stages of /belt:feature-dev. --codex enables adversarial plan review.
| name | spec-review |
| description | Spec review via the consolidated belt:spec-reviewer agent. Reviews any spec-family document (requirements.md, goal-sheet.md, design.md, plan.md). Findings are triaged in one batched selection. --codex adds an adversarial pass via /codex:rescue in the same parallel batch. |
| argument-hint | [<target-path>] [--codex] |
Runs in the main context because triage and fix apply need user dialogue and Edit access.
The spec document: use the caller-supplied path if given, otherwise the
most recently modified design.md, plan.md, *-design.md,
goal-sheet.md, or requirements.md under docs/.
findings-plan) →
run belt-agent status and read that artifact's resolved_path.findings-spec
artifact's resolved_path.<target document's directory>/review/.
The findings file is findings-spec.json in that directory.--codex: in a belt run, read the findings-codex artifact's
resolved_path the same way; otherwise use findings-codex.json in
the same output directory.. With --codex, invoke /codex:rescue` in the same
message with the spec path, the findings JSON schema from the
spec-reviewer agent, and its own output_path.Read the findings JSON file(s). Present ALL findings as one numbered list, sorted by severity (critical > high > medium > low). For each: one line of description + the suggested fix. Ask the user once, via AskUserQuestion or a single message, which numbers to apply. Do not ask per-finding questions across multiple turns.
Apply accepted suggestions to the spec with Edit. Then:
git diff — confirm only the target spec changed.