agentleFS
karthikkumar27karthikkumar27/grepable/skills/code-review/SKILL.md

code-review

Skill0 starsChanged 50 days agoMITView on GitHub

Review code changes only against the original requirement document. Finds code that contradicts the spec, behaviour the spec never asked for, in-scope rules that are missing or untested, and code built on open decisions, each cited as spec ID and source line. Use when asked to review code or a PR against the spec, PRD, FSD or requirements, check requirement coverage, or verify that a change implements a requirement ID.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • PydanticSkill

    add-new-model

    Add support for a newly-released language or image generation model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5, openai:gpt-image-2). Use when a provider ships a new model id and you need to wire literals, profile flags, adapters, and tests to recognize it. Handles SDK-lag, gateway list conventions, capability probing, and direct image-model geometry.

    Also in 9 projects that use this

  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 5 projects that use this

  • Microsoft AzureSkill

    azsdk-common-apiview-feedback-resolution

    Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_customized_code_update, azure-sdk-mcp:azsdk_typespec_delegate_apiview_feedback, azure-sdk-mcp:azsdk_run_typespec_validation, azure-sdk-mcp:azsdk_package_generate_code.

    Also in 6 projects that use this

  • Microsoft AzureSkill

    azsdk-common-generate-sdk-locally

    Generate and finalize Azure SDKs locally from TypeSpec, including build, checks, tests, changelog, metadata, and version updates by default. WHEN: "generate SDK locally", "build SDK", "run SDK tests", "run CI checks", "validate package", "run checks", "update changelog", "fix SDK build errors", "resolve SDK generation errors", "customize TypeSpec", "rename SDK client", "rename SDK model", "hide operation from SDK", "fix analyzer errors", "resolve customization drift", "create subclient", "update metadata", "update version". INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.

    Also in 6 projects that use this

  • +4 more from dzhng
  • +2 more from Azure

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If none exists, stop and ask for the path.

    line 17
  2. Very specific:

    If the user points at a shard, INDEX.md or the shards folder, the source is the path in the shard's line-1 marker (<!-- source: …

    line 19
  3. Very specific:

    Reading the spec: If shards exist and are fresh, use INDEX.md and ID-MAP.md to find the section, then read that shard (its content is a …

    line 22
  4. Very specific:

    What to review: Use the target the user gives (PR, branch, commit, files).

    line 34
  5. Distinctive:

    Only report what you can show: quote the spec text verbatim and point at the code line.

    line 53
  6. Distinctive:

    Don't report style, naming, performance or security issues here unless the spec states the rule.

    line 67
  7. Distinctive:

    Don't treat existing code as the spec.

    line 68
  8. Distinctive:

    Don't fix the code unless the user asks.

    line 69
  9. Distinctive:

    Don't edit the requirement document or the shards.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 184 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

grepable:code-review

A review with one question: does this code do what the original requirement document says, and nothing else? Style, performance and general best practice are out of scope. Leave them to other reviewers.

Spec location (shared by all grepable skills)

Find the requirement document in this order and use the first that exists:

  1. A path the user gives in the request.
  2. A Spec source: <path> line in the repo's CLAUDE.md or AGENTS.md.
  3. docs/original-requirement.md (the default).

If none exists, stop and ask for the path. Never pick a "similar-looking" document yourself. Shards live in the Spec shards: <dir> line if present, otherwise docs/fsd/. If the user points at a shard, INDEX.md or the shards folder, the source is the path in the shard's line-1 marker (<!-- source: <path>:L<start>-L<end> -->).

Reading the spec. If shards exist and are fresh, use INDEX.md and ID-MAP.md to find the section, then read that shard (its content is a byte-exact copy of the source). Shards are stale when the source changed after INDEX.md was generated (compare git log -1 or file times); then re-run grepable:shard or read the source directly. With no shards, grep the source for the ID or term and read the whole section around it.

Citations always point at the source document, never at a shard.

  • With IDs: LN-03.R2 (docs/original-requirement.md:L103). ID-MAP.md gives the source line.
  • Without IDs: docs/original-requirement.md:L103. From a shard, source line = marker start + shard line − 2. If the spec has no IDs at all, say so once and suggest adding them; then proceed with lines.

Steps

  1. What to review. Use the target the user gives (PR, branch, commit, files). Otherwise review the uncommitted changes plus the current branch against its base (git diff <base>...HEAD and git diff). Read changed files in full where needed to understand behaviour.
  2. Map code to spec. For each observable behaviour in the change (inputs accepted or refused, values, limits, messages, codes, state changes, permissions), find the spec ID that governs it. Also list the spec IDs in scope for this change (from the PR description, commit messages, test names, or the section the code clearly implements), so missing work is visible.
  3. Classify findings.

    TypeMeaning
    MISMATCHCode contradicts the spec (a different limit, code, message, rule or permission).
    UNSPECIFIEDObservable behaviour with no spec citation: an invented default, limit, fallback, message or rule.
    MISSINGAn in-scope rule or acceptance criterion that the change does not implement.
    UNTESTEDImplemented, but no test exercises that rule or criterion.
    OPEN ITEMCode built on a spec item marked Decision pending, TBD or NOT IN SPEC.

    Only report what you can show: quote the spec text verbatim and point at the code line. If the spec is ambiguous, report it as a question, not as a defect in the code.

  4. Report.

    #TypeCode (file:line)Spec ID (source line)Spec says (verbatim)Code does

    Then:

    • Coverage: each in-scope spec ID with ✅ implemented and tested / ⚠ untested / ❌ missing.
    • Questions for the spec owner: ambiguities and gaps found while reviewing.
    • Verdict: Matches spec, Matches spec with gaps or Does not match spec.

Don't

  • Don't report style, naming, performance or security issues here unless the spec states the rule.
  • Don't treat existing code as the spec. If old code and the spec disagree, it is a MISMATCH.
  • Don't fix the code unless the user asks. This skill reviews.
  • Don't edit the requirement document or the shards.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.