code-review

Files (2)

• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

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.

## Process

### 1. Pin the fixed point

Whatever the user said is the fixed point — a commit SHA, branch name, tag, `main`, `HEAD~5`, etc. If they didn't specify one, ask for 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`.

Before going further, confirm the fixed point resolves and the diff is non-empty. If the caller supplied pinned OIDs, use them as the fixed point and `HEAD`. Otherwise `git show --no-patch --format=fuller <fixed-point>` confirms the ref. A bad ref or empty diff should fail here — not inside two parallel sub-agents.

Issue each shell command on its own, not chained with `&&`, `;`, or `|`. Every review profile allows `git diff`, `git log`, `git show`, and `git status`; some also allow a few other read-only git subcommands, but chained commands can be denied.

### 2. Identify the spec source

Look for the originating spec, in this order:

1. Issue references in the commit messages (`#123`, `Closes #45`, etc.) — fetch per the work-record contract in [`../wayfinder/WORK-RECORDS.md`](../wayfinder/WORK-RECORDS.md).
2. A path the user passed as an argument.

### 3. Identify the standards sources

Anything in the repo that documents how code should be written, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`.

On top of whatever the repo documents, the Standards axis always carries the **unified code standard** in [`../codebase-design/STANDARD.md`](../codebase-design/STANDARD.md). 

### 4. Spawn both sub-agents in parallel

Send a single message with two subagents.

**Standards sub-agent prompt** — include:

- The full diff command and commit list.
- The list of standards-source files you found in step 3, **plus the full contents of `../codebase-design/STANDARD.md`** pasted into the prompt. 
- The brief: "Report — per file/hunk where relevant — (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any violation of the pasted unified standard: name the rule or smell and quote the hunk. Apply the standard's binding rules. Under 400 words."

**Spec sub-agent prompt** — include:

- The diff command and commit list.
- The path or fetched contents of the spec.
- The brief: "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, keeping each finding on its own axis — never merged, reranked, or resolved to a single winner across axes (see _Why two axes_).

End with a one-line summary: total findings per axis, and the worst issue _within each axis_ (if any).

From ejarmand/skills, MIT.

More from ejarmand/skills