agent coding skill risk: low
Two-Axis Git Diff Code Reviewer
The prompt instructs an agent to review code changes from a user-specified fixed point to HEAD by first identifying standards documents and spec sources, then spawning parallel sub…
- External action: low
SKILL 1 file
SKILL.md
--- name: review description: "Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them s" --- # Review Two-axis review of the diff between `HEAD` and a fixed point the user supplies: - **Standards** — does the code conform to this repo's documented coding standards? - **Spec** — does the code faithfully implement the originating issue / PRD / spec? Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings. The issue tracker should have been provided to you — run `/setup-matt-pocock-skills` if `docs/agents/issue-tracker.md` is missing. ## Process ### 1. Pin the fixed point Whatever the user said is the fixed point — a commit SHA, branch name, tag, `main`, `HEAD~5`, etc. Don't be opinionated; pass it through. If they didn't specify one, ask: "Review against what — a branch, a commit, or `main`?" Don't proceed until you have it. Capture the diff command once: `git diff <fixed-point>...HEAD` (three-dot, so the comparison is against the merge-base). Also note the list of commits via `git log <fixed-point>..HEAD --oneline`. ### 2. Identify the spec source Look for the originating spec, in this order: 1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.) — fetch via the workflow in `docs/agents/issue-tracker.md`. 2. A path the user passed as an argument. 3. A PRD/spec file under `docs/`, `specs/`, or `.scratch/` matching the branch name or feature. 4. If nothing is found, ask the user where the spec is. If they say there isn't one, the **Spec** sub-agent will skip and report "no spec available". ### 3. Identify the standards sources Anything in the repo that documents how code should be written. Common locations: - `CLAUDE.md`, `AGENTS.md` - `CONTRIBUTING.md` - `CONTEXT.md`, `CONTEXT-MAP.md`, per-context `CONTEXT.md` files - `docs/adr/` (architectural decisions are standards) - `.editorconfig`, `eslint.config.*`, `biome.json`, `prettier.config.*`, `tsconfig.json` (machine-enforced standards — note them but don't re-check what tooling already checks) - Any `STYLE.md`, `STANDARDS.md`, `STYLEGUIDE.md`, or similar at the repo root or under `docs/` Collect the list of files. The **Standards** sub-agent will read them. ### 4. Spawn both sub-agents in parallel Send a single message with two `Agent` tool calls. Use the `general-purpose` subagent for both. **Standards sub-agent prompt** — include: - The full diff command and commit list. - The list of standards-source files you found in step 3. - The brief: "Read the standards docs. Then read the diff. Report — per file/hunk where relevant — every place the diff violates a documented standard. Cite the standard (file + the rule). Distinguish hard violations from judgement calls. Skip anything tooling enforces. Under 400 words." **Spec sub-agent prompt** — include: - The diff command and commit list. - The path or fetched contents of the spec. - The brief: "Read the spec. Then read the diff. Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words." If the spec is missing, skip the Spec sub-agent and note this in the final report. ### 5. Aggregate Present the two reports under `## Standards` and `## Spec` headings, verbatim or lightly cleaned. Do **not** merge or rerank findings — the two axes are deliberately separate so the user can see them independently. End with a one-line summary: total findings per axis, and the worst single issue (if any) flagged. ## Why two axes A change can pass one axis and fail the other: - Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.** - Code that does exactly what the issue asked but breaks the project's conventions → **Spec pass, Standards fail.** Reporting them separately stops one axis from masking the other.
REQUIRED CONTEXT
- fixed point (commit/branch/tag)
- git diff and log output
- standards source files
- spec/issue contents
TOOLS REQUIRED
- agent
ROLES & RULES
- Don't be opinionated; pass it through.
- Don't proceed until you have it.
- Capture the diff command once.
- Look for the originating spec, in this order.
- Collect the list of files.
- Send a single message with two Agent tool calls.
- Use the general-purpose subagent for both.
- If the spec is missing, skip the Spec sub-agent.
- Present the two reports under ## Standards and ## Spec headings, verbatim or lightly cleaned.
- Do not merge or rerank findings.
- End with a one-line summary.
EXPECTED OUTPUT
- Format
- markdown
- Schema
- markdown_sections · Standards, Spec, one-line summary
- Constraints
- use ## Standards and ## Spec headings
- report sub-agent findings verbatim or lightly cleaned
- end with one-line summary of total findings and worst issue
SUCCESS CRITERIA
- Report per file/hunk every place the diff violates a documented standard.
- Cite the standard (file + the rule).
- Distinguish hard violations from judgement calls.
- Skip anything tooling enforces.
- Under 400 words.
- Report missing/partial requirements, scope creep, and wrong implementations.
- Quote the spec line for each finding.
FAILURE MODES
- May fail to keep the two axes completely separate.
- May proceed without a fixed point or spec source.
CAVEATS
- Dependencies
- docs/agents/issue-tracker.md
- git repository with commits
- Missing context
- Exact mechanism or syntax for spawning the parallel Agent tool calls
- How to handle repos without an issue tracker or docs/agents/issue-tracker.md
- Preferred final report format or length
- Ambiguities
- Description field is truncated: "reports them s"
- References "general-purpose" subagent without defining how it is invoked or configured
- Does not specify desired output length beyond the sub-agent 400-word limits
QUALITY
- OVERALL
- 0.78
- CLARITY
- 0.75
- SPECIFICITY
- 0.90
- REUSABILITY
- 0.80
- COMPLETENESS
- 0.70
IMPROVEMENT SUGGESTIONS
- Complete the truncated sentence in the description field.
- Add an explicit placeholder or variable for the fixed-point argument so the prompt can be used as a template without editing.
- Define or link to the expected Agent tool format for spawning sub-agents.
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Rapid App MVP Prototyperagentcoding
- AI-First Design Handoff Specs Generatoragentcoding
- Test-Driven Development Workflow Rulesagentcoding
- Structured Autonomy Implementation Agentagentcoding
- PROGRESS.md Manager for Agentic Codingagentcoding
- Hard Bug Diagnosis Disciplineagentcoding
- Git Development Branch Finisheragentcoding
- Code Review Feedback Reception Protocolagentcoding
- Systematic Debugging Process Guideagentcoding
- Matplotlib Python Plotting Guideagentcoding
- LaTeX Paper PDF Compileragentcoding
- Full Output Enforcement for Code Generationagentcoding
- PyTorch Geometric GNN Implementation Guideagentcoding
- Premium React UI Design Architectagentcoding
- Astropy Python Astronomy Library Guideagentcoding
- Book SFT Style Transfer Pipelineagentcoding
- Event Sourcing and CQRS Architectagentcoding
- FluidSim Python CFD Simulation Guideagentcoding
- NetworkX Python Graph Analysis Toolkitagentcoding
- Phase-Gated Debugging Protocol Enforceragentcoding
- SimPy Discrete-Event Simulation Guideagentcoding
- Phase-Gated Code Debugging Protocolagentcoding
- Biopython Molecular Biology Toolkit Guideagentcoding
- Haskell Advanced Type Systems Expertagentcoding
- Anime.js Complex Animation Workflowagentcoding