710 free skills
Code Review skills
Skills for reviewing code well — structured checklists, spotting anti-patterns, and giving actionable feedback on pull requests.
Sourced from real, public repositories — synced daily, never invented.
710 free skills
Skills for reviewing code well — structured checklists, spotting anti-patterns, and giving actionable feedback on pull requests.
Sourced from real, public repositories — synced daily, never invented.
15 tools across six categories
13 of them never send your data anywhere
Free · No signup · No trial clock
SEE THE DIRECTORY
performance-review
kavionai/kavion
Use this skill for performance checks involving slow pages, APIs, database queries, memory, bundle size, caching, concurrency, scalability, and cost.
performance-reviewer
gvkhosla/compound-engineering-pi
Conditional code-review persona, selected when the diff touches database queries, loop-heavy data transforms, caching layers, or I/O-intensive paths. Reviews code for runtime performance and scalability issues. Spawned by the ce:review-beta skill as part of a reviewer ensemble.
create-pr
microsoft/vscode
Create a pull request for the current session. Use when the user wants to open a PR with the session's changes.
update-pr
microsoft/vscode
Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.
create-draft-pr
microsoft/vscode
Create a draft pull request for the current session. Use when the user wants to open a draft PR with the session's changes.
drive-pr-local-review
prisma/prisma-next
Generate local PR/branch review artifacts for the current branch vs its base — an in-repo canonical spec (if present) or an inferred review `spec.md`, plus `system-design-review.md`, `code-review.md`, and `walkthrough.md`. Multi-persona — adopts `tech-lead` as orchestrator, transitions to `architect` for the system-design pass, to `principal-engineer` for the code-review pass, then reloads `tech-lead` for the walkthrough and synthesis. Writes artifacts to disk (next to the in-repo spec when present, otherwise under `wip/`). Use when the user asks for a local PR/branch review, a code review, a system-design review, to "review this branch", or to produce written review docs. Do not modify implementation code.
contrib-pr
prisma/prisma-next
Open a high-quality external contributor PR against prisma-next. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
drive-pr-description
prisma/prisma-next
Generates PR descriptions by analyzing git diffs between the current branch and the default branch. Use when the user requests a PR description, pull request summary, or commit message for a squash merge.
cpp-review
clickhouse/pg_stat_ch
Review C++ code against Google C++ Style Guide. Use when reviewing C++ code, pull requests, or when asked to check code style compliance.
investigate-ci-failure
openshift/lightspeed-service
Investigate CI/Prow job failures on a GitHub pull request. Use when the user pastes a PR URL and asks about CI failures, red checks, test failures, or wants to understand why a job failed.
review-pr
openshift/lightspeed-service
Review PR with structured approach covering architecture, naming, patterns, and critical questions
raise-pr
openshift/lightspeed-service
Step-by-step workflow for committing staged changes and opening a pull request in the lightspeed-service repo.
review-fetch-phase
prisma/prisma-next
Fetches canonical PR review state and renders derived state artifacts. Use when the user wants the state acquisition phase only (fetch, render, summarize) for a review-framework PR.
drive-pr-walkthrough
prisma/prisma-next
Write an intent-first walkthrough (semantic narrative) of a PR/branch or commit range - the overall purpose, the sequence of conceptual steps, the concrete behavior changes, and links to both implementation touchpoints and tests as evidence. Use during branch/PR review when the user asks for a walkthrough, narrative of changes, semantic diff, intent of commits, or “what changed and why” (not a file-by-file diff recap).
github-review-iteration
prisma/prisma-next
Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.
create-pr
prisma/prisma-next
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
drive-code-review
prisma/prisma-next
Generate local PR/branch review artifacts for the current branch vs its base — an in-repo canonical spec (if present) or an inferred review `spec.md`, plus `system-design-review.md`, `code-review.md`, and `walkthrough.md`. Multi-persona — adopts `tech-lead` as orchestrator, transitions to `architect` for the system-design pass, to `principal-engineer` for the code-review pass, then reloads `tech-lead` for the walkthrough and synthesis. Writes artifacts to disk (next to the in-repo spec when present, otherwise under `wip/`). Use when the user asks for a local PR/branch review, a code review, a system-design review, to "review this branch", or to produce written review docs. Do not modify implementation code.
resolve-pr-parallel
iliaal/compound-engineering-plugin
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
bitbucket-automation
rohitg00/buildwithclaude
Automate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP (Composio). Always search tools first for current schemas.
github-automation
rohitg00/buildwithclaude
Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code, and handle deployments programmatically.
pr-review
community-access/accessibility-agents
Your code review command center -- pull PR diffs, before/after snapshots, developer comments, reactions, release context, and generate full review documents (markdown + HTML) in your workspace.
cy-review-round
pedronauck/kodebase-go
Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with cy-fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.
kb
pedronauck/kodebase-go
Comprehensive skill for the `kb` CLI and the Karpathy Knowledge Base pattern. Covers the full KB lifecycle — topic scaffolding, multi-source ingestion (URLs, files, YouTube, bookmarks, codebases), wiki article compilation, cross-article querying with file-back, lint-and-heal passes, QMD indexing, and hybrid search. Also covers codebase-specific analysis via inspect commands for complexity, coupling, blast radius, dead code, circular dependencies, symbol/file lookups, backlinks, and code smells. Use when working with kb CLI commands, knowledge base workflows, code vault generation, code graph analysis, code metrics inspection, wiki compilation, or the ingest-compile-query-lint cycle. Do not use for general code review, linting, formatting, building Go projects, or writing application code.
cy-fix-reviews
pedronauck/kodebase-go
Executes provider-agnostic PR review remediation using existing review round files under .compozy/tasks/<name>/reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for PRD task execution, review export/fetch, or generic coding tasks without review issue files.
cy-workflow-memory
pedronauck/kodebase-go
Maintains workflow-scoped task memory for Compozy runs using .compozy/tasks/<name>/memory/ files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.
cy-execute-task
pedronauck/kodebase-go
Executes one PRD task end-to-end using a provided task file, PRD directory, tracking file paths, and auto-commit mode. Use when a prompt includes a task specification that must be implemented, validated, and reflected in task tracking files. Do not use for PR review batches, generic coding tasks without a PRD task file, or standalone verification-only work.
kodebase
pedronauck/kodebase-go
Generates Obsidian knowledge vaults from source code repositories, inspects code metrics such as complexity, coupling, blast radius, dead code, and circular dependencies, indexes vault content for hybrid retrieval, and searches indexed vaults with lexical or vector queries. Use when analyzing a codebase for code quality, architecture health, symbol relationships, or code smells. Use when the task mentions kodebase, code vault, code knowledge base, code graph analysis, or code metrics inspection. Do not use for general code review, linting, formatting, building Go projects, or writing application code.
review-pr
hmcts/agentic-plugins-marketplace
Review a pull request for a CPP or HMCTS Crime Common Platform repository against CPP coding standards. Use when asked to review a PR or code changes specifically in a CP or HMCTS context service.
review-comet-pr
myx778/datafusion-comet
Review a DataFusion Comet pull request for Spark compatibility and implementation correctness. Provides guidance to a reviewer rather than posting comments directly.
gdpr-compliant
aibot88/sec_skill_store
Apply GDPR-compliant engineering practices across your codebase. Use this skill whenever you are designing APIs, writing data models, building authentication flows, implementing logging, handling user data, writing retention/deletion jobs, designing cloud infrastructure, or reviewing pull requests for privacy compliance. Trigger this skill for any task involving personal data, user accounts, cookies, analytics, emails, audit logs, encryption, pseudonymization, anonymization, data exports, breach response, CI/CD pipelines that process real data, or any question framed as "is this GDPR-compliant?". Inspired by CNIL developer guidance and GDPR Articles 5, 25, 32, 33, 35.
check-qa
covoiturage-gouv-fr/mono
Quality code review enforcing Deno standards and project conventions
gdpr-compliant
cogni-ai-ou/cogni-ai-agent-skills
Apply GDPR-compliant engineering practices across your codebase. You MUST load this skill whenever you are designing APIs, writing data models, handling user data, implementing logging, or reviewing pull requests for privacy compliance.
land
stvangaal/arboretum
Drive an open pull request to merge-ready through the configured repo backend. GitHub gets the full CI/reviewer loop; Azure DevOps gets explicit PR state/policy checks and merge handoff guidance. Chained from /finish; also runnable standalone on any open PR.
gdpr-compliant
trumedia-creative/tmc
Apply GDPR-compliant engineering practices across your codebase. Use this skill whenever you are designing APIs, writing data models, building authentication flows, implementing logging, handling user data, writing retention/deletion jobs, designing cloud infrastructure, or reviewing pull requests for privacy compliance. Trigger this skill for any task involving personal data, user accounts, cookies, analytics, emails, audit logs, encryption, pseudonymization, anonymization, data exports, breach response, CI/CD pipelines that process real data, or any question framed as "is this GDPR-compliant?". Inspired by CNIL developer guidance and GDPR Articles 5, 25, 32, 33, 35.
rails-review
rockwellll/skills
Use when the user asks for review, code review, PR review, risk assessment, Bugbot-style feedback, or help finding bugs in Rails changes. This skill is for reviewing code and surfacing real risks, not for writing new code.
pr-review-canvas
kdoroszewicz/cursor-plugins-claude
Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR".
pr-review-canvas
kentnielsen-droid/cursor-skills
Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR".
gemini
shalomeir/gemini-plugin-codex
Use Gemini CLI from Codex for large-context codebase analysis, code review, multimodal file inspection, second-opinion investigations, and Gemini job management. Use when the user explicitly mentions Gemini, wants Gemini to review local changes, asks for a Gemini-powered architecture analysis, wants Gemini to inspect screenshots, images, audio, video, or PDF files, or needs setup, status, result, or cancel help for Gemini background jobs.
gemini
juanjosegongi/skills
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
gemini
metamask/skills
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
gemini
codesharpdev/agent-toolkit
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
donate-trace
simonaszilinskas/donate-trace
Donate a single coding-agent session to Trace Commons, an open public dataset of agent traces. Use this skill whenever the user wants to donate, contribute, share, or publish an agent session, trace, or conversation history to Trace Commons or an open dataset, or says things like "/donate-trace", "donate this session", "contribute my trace", "share this to the commons", or "publish my agent history". The skill locates the current session from the agent's own logs, strips paths, identity, secrets and PII locally, shows the user exactly what was removed, confirms the project is open-source, and opens a pull request to the dataset. Only ever donates from public, open-source repositories — never private or proprietary code.
css-reviewer
sensiblemnd/css-reasoning-engine
Deterministic audit workflow for reviewing existing CSS. Use whenever reviewing, auditing, or critiquing stylesheets or CSS in a pull request, checking CSS quality, or when asked to find problems in CSS code. Produces structured findings (Issue / Severity / Location / Problem / Why / Fix / Example) covering architecture, modern-CSS usage, accessibility, and performance against a configurable browser profile. For writing new CSS use css-engineer; for applying modernization use css-refactor.
reviewer
sanderginn/clubhouse
Thoroughly review a Clubhouse pull request and post findings or signal approval. Use when asked to review a PR, e.g. "$reviewer 123" or "review PR #123". Expects a PR number from the user's message.
kotlin-reviewer
pepsi1978/proggs
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
kotlin-review
pepsi1978/proggs
Comprehensive Kotlin code review for idiomatic patterns, null safety, coroutine safety, and security. Invokes the kotlin-reviewer agent.
pr-review-canvas
aliceisjustplaying/cursor-plugins
Generate an interactive PR review walkthrough as an HTML page. Fetches PR data via gh API, categorizes files into core vs mechanical changes, adds reviewer annotations, and renders diffs with moved-code detection. Use when the user pastes a GitHub PR URL and asks for a review, walkthrough, or summary, or says "review this PR".
dx-step-verify
easingthemes/dx-aem-flow
6-phase verification with auto-fix — compile, lint, test, secret scan, architecture, then code review with fix loop (max 3 cycles). Only passes when all phases are clean. Use after /dx-step-build passes and before creating a PR.
forgejo-fj
stevejuma/jujutsu-skills
Use Forgejo through the forgejo-contrib `fj` CLI for repositories, issues, pull requests, releases, and Actions. Prefer Jujutsu (`jj`) for local version-control work when the current repository is a jj repository, fall back to Git otherwise, feature-detect job and log support built into `fj`, and use `fj-ex` only for Actions capabilities the installed `fj` lacks.
kennedy-pr
harmsworth/agent-skills
Invoke with /kennedy-pr. Service Diffguard: read-only PR review lenses for correctness, error visibility, comment truthfulness, test coverage, type/contract boundaries, and simplification across every language in this repo (Go, Vue/JS/SCSS, Rego, protobuf, SQL, Helm/YAML, shell). Use for PR review, pre-commit review, unstaged-diff review, or a targeted review of one of those aspects.