Agent skill
peer-review-spec
Run spec review using the codex CLI as an independent reviewer. Returns structured findings without applying fixes. Use when the user asks to "peer review my spec", "get a second opinion on my spec", "codex review my spec", or "run codex on my spec".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/peer-review-spec
SKILL.md
Peer Review Spec
AI-powered spec review via codex. Delegates to /codex-exec for an independent review of the specification document.
Step 1: Identify the Spec
Determine the spec to review:
- If spec text was provided by the caller, use it
- If a spec file path was provided, read the file
- If neither was provided, check for a spec at
.turbo/spec.md, or look in the current conversation context
Step 2: Run /codex-exec Skill
Run the /codex-exec skill in read-only mode with the full spec text and these review instructions:
Review the following specification document for issues that would cause problems during implementation planning. For each issue found, state: (1) what the problem is, (2) where in the spec it occurs, (3) what impact it has on planning or implementation, (4) a suggested fix, and (5) priority: P0 (fundamentally flawed), P1 (significant gap), P2 (moderate issue), or P3 (minor improvement). Ignore stylistic preferences and minor wording. If no issues are found, state that the spec looks sound.
Step 3: Return Findings
Return the codex review output. The caller determines what to do with the findings.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?