code-review

Files (2)

• SKILL.md
• smells.md · references/

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 / 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. If `docs/agents/issue-tracker.md` is missing, tell the user to run `/setup-agy-skills`.

## 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 (`git rev-parse <fixed-point>`) and the diff is non-empty. A bad ref or empty diff should fail here, not inside two parallel sub-agents.

### 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.), fetched via the workflow in `docs/agents/issue-tracker.md`.
2. A path the user passed as an argument.
3. A 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, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`.

On top of whatever the repo documents, the Standards axis always carries the Fowler code smells baseline defined in [references/smells.md](./references/smells.md).

Two rules bind it:
- **The repo overrides**: A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
- **Always a judgement call**: Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation. Skip anything tooling already enforces.

### 4. Spawn both subagents in parallel

Spawn two subagents concurrently using the `invoke_subagent` tool (`TypeName: "research"`, `Model: "inherit"`, `Workspace: "share"`). Because Antigravity is reactive, do not poll in a loop; wait for the subagents to report back.

Subagents return their findings using the **Structured Envelope** over `send_message` or in their final completion payload:

```json
{
  "type": "review_finding",
  "taskId": "code-review-<axis>",
  "status": "completed",
  "payload": {
    "axis": "standards" | "spec",
    "findings": [
      {
        "file": "path/to/file",
        "lineRange": "L10-L20",
        "severity": "violation" | "smell" | "deviation",
        "description": "Description of finding",
        "quote": "Code or spec snippet"
      }
    ]
  },
  "nextAction": "Aggregate findings into review artifact."
}
```

**Standards subagent prompt** should include:

- The full diff command and commit list.
- The list of standards-source files found in step 3, plus instructions to consult [references/smells.md](./references/smells.md).
- 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 baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls: documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."

**Spec subagent prompt** should 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 subagent and note this in the final report.

### 5. Aggregate and format as an Artifact

Present the two reports under `## Standards` and `## Spec` headings, verbatim or lightly cleaned, rendered as a structured Antigravity Artifact (or formatted markdown output). Do not merge or rerank findings, because the two axes are deliberately separate (see _Why two axes_).

Leverage `generative_ui` patterns when presenting findings in the artifact:
- Use markdown carousels (` ````carousel `) to display before-and-after diff snippets sequentially across multiple findings.
- Render visual status cards (e.g. `Pass`, `Smell / Judgement Call`, `Spec Deviation`) and structured scorecards.

End with a one-line summary: total findings per axis, and the worst issue within each axis (if any). Do not pick a single winner across axes: that is the reranking the separation exists to prevent.

## 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.

From fderuiter/agy-skills, MIT.

More from fderuiter/agy-skills