Stats
Actions
Tags
From spec-pipeline
Multi-model cross-review for spec documents. Uses fresh Claude context + Gemini to independently review requirements.md, design.md, and tasks.md, then merges findings into a unified report with consensus markers.
How this skill is triggered — by the user, by Claude, or both
Slash command
/spec-pipeline:review-specThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review a spec directory (requirements.md + design.md + tasks.md) using multiple AI models to catch issues that a single model would miss.
Review a spec directory (requirements.md + design.md + tasks.md) using multiple AI models to catch issues that a single model would miss.
The same model that wrote the spec will tend to confirm its own work. Different models have different blind spots — cross-review catches structural issues, logical contradictions, and missing edge cases that single-model review misses.
If $ARGUMENTS is provided, use it as the spec directory path.
Otherwise, search for spec directories:
find . -path "*specs*" -name "requirements.md" -o -path "*specs*" -name "design.md" | head -20
Ask the user to confirm which spec to review.
Read the following files from the spec directory:
requirements.md (if exists)design.md (if exists)tasks.md (if exists)If any file is missing, note it as a finding.
Before calling external models, do a quick consistency check:
[HUMAN] tags used appropriately?List any contradictions found.
Execute the review script:
bash ${CLAUDE_SKILL_DIR}/../scripts/review-spec.sh "<spec-directory>"
This script:
Read the generated reviews/review-final.md and present to the user:
Ask the user:
[HUMAN] tags are justified (not marking AI-doable tasks as HUMAN)npx claudepluginhub yinshucheng/claude-skills --plugin spec-pipelineReviews design artifacts (proposals, specs, designs, tasks) for internal consistency, gaps, and cross-artifact alignment before implementation.
Reviews spec.md files for completeness, clarity, implementability, testability, and structure. Identifies ambiguities, gaps, and missing sections before implementation.
Dispatches a read-only subagent to verify SPEC.md completeness before exploration. Enforces the rule that no exploration begins without a reviewed spec.