agentleFS
IgorBabikovIgorBabikov/Flowcairn/skills/code-review/SKILL.md

code-review

Skill4 starsChanged 54 days agoMITView on GitHub

Independently assess actual changes and current evidence for each requirement in ai-review.

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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the full supplied bundle, including deletions, relevant callers, implementation receipts and prior repairs.

    line 8

“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

Review the result against the contract

  • Read the full supplied bundle, including deletions, relevant callers, implementation receipts and prior repairs. Judge artifacts and original criteria, not the implementer's narrative. Incomplete evidence prevents pass for the affected criterion; reviewEvidenceHash binds input but does not prove review quality.
  • Trace each changed boundary: input, state transition, consumer, error path and recovery. Check compatibility, access/privacy and regressions according to risk. Verify tests exercise the claimed behavior and meaningful failures. Broad rewrites, style preferences and unrelated dependencies are not completion criteria.
  • Return requirementAssessments for mandatory requirements: exact requirementId, criterion, verdict, checkIds, citations and reason. Global pass cannot replace separate assessments; failed requirements need concrete blocking findings.
  • Compare successful facts in priorEvidence.verificationChecks to the actual scenario/criterion. Source-review covers directly observable properties only; human acceptance remains the user's decision. Successful check/source-review assessments require nonempty citations with path, startLine and exact quote from a current file within verification.paths and readPaths. Runtime checks bytes; invented quotes or unrelated checks are not evidence.
  • Findings identify trigger, actual/expected behavior, location, user impact and suitable reverification. Calibrate severity to impact. Separate reproduced defects, plausible unverified risks, missing evidence and optional improvements. State out-of-contract risks explicitly without inventing requirement IDs or expanding the contract.

TypeScript boundaries, only when touched

Follow project compiler settings and public types. Inspect unsafe casts, any and non-null assertions at changed external-data/state boundaries. Types do not validate JSON/persisted data: inspect actual guards/schema checks, including malformed input. For discriminated state unions, verify reachable transitions and exhaustive handling; never checks are compile-time support, not runtime validation. Prefer simple existing types to unrelated advanced-type refactors.

Review is read-only: no edits, extra reviewer dispatch, commit or merge. Do not declare PROVEN; Executor owns final completion and evidence freshness. Repairs require fresh assessment of affected criteria.

Adapted from obra/superpowers requesting-code-review/code-reviewer and narrow wshobson/agents typescript-advanced-types guidance. Copyright (c) 2025 Jesse Vincent; Copyright (c) 2024 Seth Hobson. Obra MIT, wshobson MIT; official TypeScript docs and modifications: PROVENANCE.

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.