$npx -y skills add stevesolun/ctx --skill reviewReview 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-agent
| 1 | # Review |
| 2 | |
| 3 | Two-axis review of the diff between `HEAD` and a fixed point the user supplies: |
| 4 | |
| 5 | - **Standards** — does the code conform to this repo's documented coding standards? |
| 6 | - **Spec** — does the code faithfully implement the originating issue / PRD / spec? |
| 7 | |
| 8 | Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings. |
| 9 | |
| 10 | The issue tracker should have been provided to you — run `/setup-matt-pocock-skills` if `docs/agents/issue-tracker.md` is missing. |
| 11 | |
| 12 | ## Process |
| 13 | |
| 14 | ### 1. Pin the fixed point |
| 15 | |
| 16 | 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. |
| 17 | |
| 18 | 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`. |
| 19 | |
| 20 | ### 2. Identify the spec source |
| 21 | |
| 22 | Look for the originating spec, in this order: |
| 23 | |
| 24 | 1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.) — fetch via the workflow in `docs/agents/issue-tracker.md`. |
| 25 | 2. A path the user passed as an argument. |
| 26 | 3. A PRD/spec file under `docs/`, `specs/`, or `.scratch/` matching the branch name or feature. |
| 27 | 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". |
| 28 | |
| 29 | ### 3. Identify the standards sources |
| 30 | |
| 31 | Anything in the repo that documents how code should be written. Common locations: |
| 32 | |
| 33 | - `CLAUDE.md`, `AGENTS.md` |
| 34 | - `CONTRIBUTING.md` |
| 35 | - `CONTEXT.md`, `CONTEXT-MAP.md`, per-context `CONTEXT.md` files |
| 36 | - `docs/adr/` (architectural decisions are standards) |
| 37 | - `.editorconfig`, `eslint.config.*`, `biome.json`, `prettier.config.*`, `tsconfig.json` (machine-enforced standards — note them but don't re-check what tooling already checks) |
| 38 | - Any `STYLE.md`, `STANDARDS.md`, `STYLEGUIDE.md`, or similar at the repo root or under `docs/` |
| 39 | |
| 40 | Collect the list of files. The **Standards** sub-agent will read them. |
| 41 | |
| 42 | ### 4. Spawn both sub-agents in parallel |
| 43 | |
| 44 | Send a single message with two `Agent` tool calls. Use the `general-purpose` subagent for both. |
| 45 | |
| 46 | **Standards sub-agent prompt** — include: |
| 47 | |
| 48 | - The full diff command and commit list. |
| 49 | - The list of standards-source files you found in step 3. |
| 50 | - 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." |
| 51 | |
| 52 | **Spec sub-agent prompt** — include: |
| 53 | |
| 54 | - The diff command and commit list. |
| 55 | - The path or fetched contents of the spec. |
| 56 | - 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." |
| 57 | |
| 58 | If the spec is missing, skip the Spec sub-agent and note this in the final report. |
| 59 | |
| 60 | ### 5. Aggregate |
| 61 | |
| 62 | 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. |
| 63 | |
| 64 | End with a one-line summary: total findings per axis, and the worst single issue (if any) flagged. |
| 65 | |
| 66 | ## Why two axes |
| 67 | |
| 68 | A change can pass one axis and fail the other: |
| 69 | |
| 70 | - Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.** |
| 71 | - Code that does exactly what the issue asked but breaks the project's conventions → **Spec pass, Standards fail.** |
| 72 | |
| 73 | Reporting them separately stops one axis from masking the other. |