How do I install the Review Spec skill?

Run npx skillmds add majiayu000/review-spec-4 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Spec safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Spec?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Spec free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Review Spec?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Spec by majiayu000 — Agent Skill

Name: Review Spec
Rating: 4.5 (4 reviews)
Author: majiayu000

File contents

Follow feature-dev-aidd:aidd-core.

Steps

Set active stage review-plan, then review-prd; keep active feature in sync via canonical active-state runtime commands only.
Run python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-core/runtime/prd_review.py --ticket <ticket> to refresh structured PRD report payload.
Gate PRD readiness with python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/prd_check.py; block on failure.
Use the existing rolling context pack as review input; do not invoke standalone context-pack builder scripts from this stage.
Run subagent feature-dev-aidd:plan-reviewer, then run subagent feature-dev-aidd:prd-reviewer.
Persist PRD review report with python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-core/runtime/prd_review.py --ticket <ticket> --report aidd/reports/prd/<ticket>.json --require-ready for READY-path validation.
Review-stage RLM policy: if RLM links are empty, the runtime performs bounded auto-heal (rlm_links_build, then finalize probe) and returns WARN attribution with evidence instead of terminal block when review can continue.
Report payload (aidd/reports/prd/<ticket>.json|.pack.json) is the source of truth for final verdict: READY is allowed only when recommended_status=ready; otherwise return WARN/BLOCKED with canonical next action (/feature-dev-aidd:spec-interview <ticket>).

Command contracts

`python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-core/runtime/prd_review.py`

When to run: as canonical review-spec stage entrypoint before PRD approval decisions.
Inputs: --ticket <ticket> plus active PRD/plan artifacts.
Outputs: normalized PRD review report payload; verdict decisions use report payload (recommended_status) as source of truth.
Failure mode: non-zero exit when review inputs are incomplete or report validation fails; RLM links-empty path is handled as bounded auto-heal then WARN attribution.
Next action: fix missing artifacts/review findings or unresolved RLM prerequisites and rerun the CLI.

Notes

Planning stage: AIDD:ACTIONS_LOG: n/a.

Additional resources

PRD review runtime: ../aidd-core/runtime/prd_review.py (when: review-spec gate behavior is unclear; why: confirm report contract and status mapping).

---name: review-spec-4description: Reviews plan and PRD, then gates readiness for implementation. Use when plan and PRD artifacts are ready for spec approval.--- Follow `feature-dev-aidd:aidd-core`. ## Steps 1. Set active stage `review-plan`, then `review-prd`; keep active feature in sync via canonical active-state runtime commands only. 2. Run `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-core/runtime/prd_review.py --ticket <ticket>` to refresh structured PRD report payload. 3. Gate PRD readiness with `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/prd_check.py`; block on failure. 4. Use the existing rolling context pack as review input; do not invoke standalone context-pack builder scripts from this stage. 5. Run subagent `feature-dev-aidd:plan-reviewer`, then run subagent `feature-dev-aidd:prd-reviewer`. 6. Persist PRD review report with `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-core/runtime/prd_review.py --ticket <ticket> --report aidd/reports/prd/<ticket>.json --require-ready` for READY-path validation. 7. Review-stage RLM policy: if RLM links are empty, the runtime performs bounded auto-heal (`rlm_links_build`, then finalize probe) and returns WARN attribution with evidence instead of terminal block when review can continue. 8. Report payload (`aidd/reports/prd/<ticket>.json|.pack.json`) is the source of truth for final verdict: READY is allowed only when `recommended_status=ready`; otherwise return WARN/BLOCKED with canonical next action (`/feature-dev-aidd:spec-interview <ticket>`). ## Command contracts ### `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-core/runtime/prd_review.py` - When to run: as canonical review-spec stage entrypoint before PRD approval decisions. - Inputs: `--ticket <ticket>` plus active PRD/plan artifacts. - Outputs: normalized PRD review report payload; verdict decisions use report payload (`recommended_status`) as source of truth. - Failure mode: non-zero exit when review inputs are incomplete or report validation fails; RLM links-empty path is handled as bounded auto-heal then WARN attribution. - Next action: fix missing artifacts/review findings or unresolved RLM prerequisites and rerun the CLI. ## Notes - Planning stage: `AIDD:ACTIONS_LOG: n/a`. ## Additional resources - PRD review runtime: [../aidd-core/runtime/prd_review.py](../aidd-core/runtime/prd_review.py) (when: review-spec gate behavior is unclear; why: confirm report contract and status mapping).

Frequently asked questions