agentleFS
caoergoucaoergou/erics-skills/skills/code-review/SKILL.md

code-review

Skill0 starsChanged 7 months agoMITView on GitHub

Comprehensive code review combining Clean Code principles and senior engineer expertise. Reviews git changes for SOLID violations, security risks, clean code smells, and proposes actionable improvements.

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 10 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

  • ww-w-aiSkill

    bkend-auth

    bkend.ai authentication guide. Signup, login, JWT tokens, sessions, role-based access control, and password management with bkend.ai BaaS. Triggers: bkend auth, bkend login, bkend signup, JWT, session, RBAC, password, bkend 인증, 로그인, 회원가입, bkend認証, ログイン, 新規登録, bkend认证, 登录, 注册, autenticacion bkend, authentification bkend, bkend-Auth Do NOT use for: data operations (use $bkend-data), file storage (use $bkend-storage).

    Also in 4 projects that use this

  • +3 more from dzhng
  • +3 more from Azure

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. 0 are common, 12 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Writing new code: Ensure high quality from the start.

    line 13
  2. Distinctive:

    Use git status -sb, git diff --stat, and git diff to scope changes.

    line 30
  3. Very specific:

    If needed, use rg or grep to find related modules, usages, and contracts.

    line 31
  4. Distinctive:

    No changes: If git diff is empty, inform user and ask if they want to review staged changes or a specific commit range.

    line 35
  5. Very specific:

    Run linters on changed files only: Use git diff --name-only --diff-filter=ACMR HEAD to get changed files, then run the detected linter(s) …

    line 43
  6. Very specific:

    If auto-fix is available (e.g., eslint --fix, ruff check --fix), mention the command in the suggested fix.

    line 49
  7. Distinctive:

    If no linter is detected, skip this step and note it in the review output.

    line 50
  8. Very specific:

    Avoid Disinformation: Don't use accountList if it's actually a Map.

    line 58
  9. Very specific:

    Meaningful Distinctions: Avoid ProductData vs ProductInfo.

    line 59
  10. Very specific:

    Pronounceable/Searchable Names: Avoid genymdhms.

    line 60
  11. Distinctive:

    One Level of Abstraction: Don't mix high-level business logic with low-level details.

    line 67
  12. Very specific:

    Law of Demeter: Avoid a.getB().getC().doSomething().

    line 84
  13. Distinctive:

    When you propose a refactor, explain *why* it improves cohesion/coupling and outline a minimal, safe split.

    line 97
  14. Distinctive:

    If refactor is non-trivial, propose an incremental plan instead of a large rewrite.

    line 98
  15. Distinctive:

    Call out both exploitability and impact.

    line 117
  16. Distinctive:

    Inline comments: Use this format for file-specific findings:

    line 174
  17. Distinctive:

    Clean review: If no issues found, explicitly state:

    line 181
  18. Distinctive:

    After presenting findings, ask user how to proceed:

    line 188
  19. Distinctive:

    Important: Do NOT implement any changes until user explicitly confirms.

    line 207

“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

Code Review

Comprehensive code review skill that combines Clean Code principles (Robert C. Martin) with senior engineer expertise for SOLID, architecture, security, performance, and code quality.

When to Use

  • Reviewing Pull Requests: Provide constructive, principle-based feedback.
  • Writing new code: Ensure high quality from the start.
  • Refactoring legacy code: Identify and remove code smells.
  • Improving team standards: Align on industry-standard best practices.

Severity Levels

LevelNameDescriptionAction
P0CriticalSecurity vulnerability, data loss risk, correctness bugMust block merge
P1HighLogic error, significant SOLID violation, performance regressionShould fix before merge
P2MediumCode smell, maintainability concern, minor SOLID violationFix in this PR or create follow-up
P3LowStyle, naming, minor suggestionOptional improvement

Workflow

1) Preflight Context

  • Use git status -sb, git diff --stat, and git diff to scope changes.
  • If needed, use rg or grep to find related modules, usages, and contracts.
  • Identify entry points, ownership boundaries, and critical paths (auth, payments, data writes, network).

Edge cases:

  • No changes: If git diff is empty, inform user and ask if they want to review staged changes or a specific commit range.
  • Large diff (>500 lines): Summarize by file first, then review in batches by module/feature area.
  • Mixed concerns: Group findings by logical feature, not just file order.

2) Linter Zero-New-Violations Check

  • Load references/linter-checklist.md for detection and baseline strategy.
  • Detect project linters: Scan for config files (.eslintrc*, pyproject.toml, .golangci.yml, Cargo.toml, etc.) to identify which linters are configured.
  • Run linters on changed files only: Use git diff --name-only --diff-filter=ACMR HEAD to get changed files, then run the detected linter(s) targeting those files.
  • Baseline comparison: Cross-reference linter output with diff hunks — only report violations on changed/added lines. Pre-existing violations in unchanged code are out of scope.
  • Classification:
    • New error in changed line → P1 (must fix before merge)
    • New warning in changed line → P2 (should fix in this PR)
    • Formatter-only issues → P3 (suggest auto-fix command)
  • If auto-fix is available (e.g., eslint --fix, ruff check --fix), mention the command in the suggested fix.
  • If no linter is detected, skip this step and note it in the review output.

3) Clean Code Principles

Apply the following Clean Code principles during review:

Meaningful Names

  • Intention-Revealing Names: elapsedTimeInDays instead of d.
  • Avoid Disinformation: Don't use accountList if it's actually a Map.
  • Meaningful Distinctions: Avoid ProductData vs ProductInfo.
  • Pronounceable/Searchable Names: Avoid genymdhms.
  • Class Names: Nouns (Customer, WikiPage). Avoid Manager, Data.
  • Method Names: Verbs (postPayment, deletePage).

Functions

  • Small: Functions should be shorter than you think (~20 lines max).
  • Do One Thing: A function should do only one thing, and do it well.
  • One Level of Abstraction: Don't mix high-level business logic with low-level details.
  • Descriptive Names: isPasswordValid is better than check.
  • Arguments: 0 is ideal, 1-2 is okay, 3+ requires strong justification.
  • No Side Effects: Functions shouldn't secretly change global state.

Comments

  • Don't Comment Bad Code — Rewrite It: Most comments are a sign of failure to express ourselves in code.
  • Good Comments: Legal, Informative (regex intent), Clarification (external libraries), TODOs.
  • Bad Comments: Mumbling, Redundant, Misleading, Mandated, Noise, Position Markers.

Formatting

  • The Newspaper Metaphor: High-level concepts at the top, details at the bottom.
  • Vertical Density: Related lines should be close to each other.
  • Distance: Variables declared near their usage.

Objects, Data Structures & Error Handling

  • Data Abstraction: Hide implementation behind interfaces.
  • Law of Demeter: Avoid a.getB().getC().doSomething().
  • Use Exceptions instead of Return Codes.
  • Don't Return/Pass Null.

4) SOLID + Architecture Smells

  • Load references/solid-checklist.md for specific prompts.
  • Look for:
    • SRP: Overloaded modules with unrelated responsibilities.
    • OCP: Frequent edits to add behavior instead of extension points.
    • LSP: Subclasses that break expectations or require type checks.
    • ISP: Wide interfaces with unused methods.
    • DIP: High-level logic tied to low-level implementations.
  • When you propose a refactor, explain why it improves cohesion/coupling and outline a minimal, safe split.
  • If refactor is non-trivial, propose an incremental plan instead of a large rewrite.

5) Removal Candidates + Iteration Plan

  • Load references/removal-plan.md for template.
  • Identify code that is unused, redundant, or feature-flagged off.
  • Distinguish safe delete now vs defer with plan.
  • Provide a follow-up plan with concrete steps and checkpoints (tests/metrics).

6) Security and Reliability Scan

  • Load references/security-checklist.md for coverage.
  • Check for:
    • XSS, injection (SQL/NoSQL/command), SSRF, path traversal
    • AuthZ/AuthN gaps, missing tenancy checks
    • Secret leakage or API keys in logs/env/files
    • Rate limits, unbounded loops, CPU/memory hotspots
    • Unsafe deserialization, weak crypto, insecure defaults
    • Race conditions: concurrent access, check-then-act, TOCTOU, missing locks
  • Call out both exploitability and impact.

7) Code Quality Scan

  • Load references/code-quality-checklist.md for coverage.
  • Check for:
    • Error handling: swallowed exceptions, overly broad catch, missing error handling, async errors
    • Performance: N+1 queries, CPU-intensive ops in hot paths, missing cache, unbounded memory
    • Boundary conditions: null/undefined handling, empty collections, numeric boundaries, off-by-one
  • Flag issues that may cause silent failures or production incidents.

8) Output Format

Structure your review as follows:

## Code Review Summary

**Files reviewed**: X files, Y lines changed
**Overall assessment**: [APPROVE / REQUEST_CHANGES / COMMENT]

---

## Findings

### P0 - Critical
(none or list)

### P1 - High
1. **[file:line]** Brief title
  - Description of issue
  - Suggested fix

### P2 - Medium
2. (continue numbering across sections)
  - ...

### P3 - Low
...

---

## Linter Results
**Linters detected**: [list or "none"]
**New violations in changed lines**: X errors, Y warnings
(list each violation with file:line, rule, and auto-fix command if available)

## Clean Code Issues
(naming, function size, comment quality, formatting — grouped by principle)

## Removal/Iteration Plan
(if applicable)

## Additional Suggestions
(optional improvements, not blocking)

Inline comments: Use this format for file-specific findings:

::code-comment{file="path/to/file.ts" line="42" severity="P1"}
Description of the issue and suggested fix.
::

Clean review: If no issues found, explicitly state:

  • What was checked
  • Any areas not covered (e.g., "Did not verify database migrations")
  • Residual risks or recommended follow-up tests

9) Next Steps Confirmation

After presenting findings, ask user how to proceed:

---

## Next Steps

I found X issues (P0: _, P1: _, P2: _, P3: _).

**How would you like to proceed?**

1. **Fix all** - I'll implement all suggested fixes
2. **Fix P0/P1 only** - Address critical and high priority issues
3. **Fix specific items** - Tell me which issues to fix
4. **No changes** - Review complete, no implementation needed

Please choose an option or provide specific instructions.

Important: Do NOT implement any changes until user explicitly confirms. This is a review-first workflow.

Clean Code Checklist

  • Is this function smaller than 20 lines?
  • Does this function do exactly one thing?
  • Are all names searchable and intention-revealing?
  • Have I avoided comments by making the code clearer?
  • Am I passing too many arguments?
  • Is there a failing test for this change?
  • Does the code follow the Law of Demeter?
  • Are exceptions used instead of return codes?

Resources

references/

FilePurpose
linter-checklist.mdLinter detection, baseline comparison, and auto-fix commands
solid-checklist.mdSOLID smell prompts, common code smells, and refactor heuristics
security-checklist.mdWeb/app security and runtime risk checklist
code-quality-checklist.mdError handling, performance, boundary conditions
removal-plan.mdTemplate for deletion candidates and follow-up plan

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.