agentsclimarketplace

Review & quality

19,040 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Copilot

    RokyYTR2/BetterThink/copilot Skill

    1★ repo

    Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's instructions file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user wants more disciplined thinking, fewer assumptions, and higher-confidence execution.

  • Cursor

    RokyYTR2/BetterThink/cursor Skill

    1★ repo

    Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's rules file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user wants more disciplined thinking, fewer assumptions, and higher-confidence execution.

  • Gemini

    RokyYTR2/BetterThink/gemini Skill

    1★ repo

    Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's memory file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user wants more disciplined thinking, fewer assumptions, and higher-confidence execution.

  • Pr comment triage

    Fyzel/claude-skills/skills/pr-comment-triage Skill

    1★ repo

    Triage and resolve pull-request review comments end to end — fetch reviewer comments (especially GitHub Copilot automated review), fix each one in code, run the project's tests, then post a threaded reply under each original comment by its comment ID. Use this skill whenever the user says "check the Copilot comment(s) on PR N", "address the review comments", "reply to the review comments", "resolve PR feedback", "handle the PR comments", or asks to go through a reviewer's findings on a pull request. Works for any reviewer (Copilot, humans, bots) and any language or repo. Requires the `gh` CLI to be authenticated.

  • Skill validator

    Fyzel/claude-skills/skills/skill-validator Skill

    1★ repo

    Validate Claude Code skill files (SKILL.md) against Anthropic's structural requirements. Use this skill whenever the user asks to validate, lint, check, or verify a skill file or skill structure. Triggers on "validate skill", "lint skill", "check skill", "verify SKILL.md", "does my skill meet requirements", or any request to confirm a skill is correctly structured before publishing or importing.

  • Git guardrails claude code

    steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/git-guardrails-claude-code Skill

    no license1★ repo

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

    The same file is in 18 other repositories

  • Grill me

    steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/grill-me Skill

    no license1★ repo

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

    The same file is in 23 other repositories

  • Setup pre commit

    steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/setup-pre-commit Skill

    no license1★ repo

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    The same file is in 19 other repositories

  • Finishing a development branch

    steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/finishing-a-development-branch Skill

    no license1★ repo

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

    The same file is in 10 other repositories

  • Receiving code review

    steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/receiving-code-review Skill

    no license1★ repo

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

    The same file is in 28 other repositories

  • Requesting code review

    steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/requesting-code-review Skill

    no license1★ repo

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    The same file is in 11 other repositories

  • Using git worktrees

    steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/using-git-worktrees Skill

    no license1★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

    The same file is in 13 other repositories

  • Verification before completion

    steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/verification-before-completion Skill

    no license1★ repo

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    The same file is in 40 other repositories

  • Multi reviewer patterns

    steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/agent-teams/skills/multi-reviewer-patterns Skill

    no license1★ repo

    Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.

    The same file is in 4 other repositories

  • Block no verify hook

    steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/block-no-verify/skills/block-no-verify-hook Skill

    no license1★ repo

    Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.

    The same file is in 3 other repositories

  • Code review excellence

    steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/developer-essentials/skills/code-review-excellence Skill

    no license1★ repo

    Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

    The same file is in 5 other repositories

  • Git advanced workflows

    steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/developer-essentials/skills/git-advanced-workflows Skill

    no license1★ repo

    Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

    The same file is in 1 other repository

  • Review agent setup

    steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/review-agent-governance/skills/review-agent-setup Skill

    no license1★ repo

    Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.

  • Superpowers requesting code review

    steph-frtech/cdesign-expo/.claude/skills/superpowers__requesting-code-review Skill

    no license1★ repo

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    The same file is in 11 other repositories

  • Superpowers using git worktrees

    steph-frtech/cdesign-expo/.claude/skills/superpowers__using-git-worktrees Skill

    no license1★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

    The same file is in 13 other repositories

  • Generate commit msg

    itsjavi/skills/skills/generate-commit-msg Skill

    1★ repo

    Generate a Conventional Commit message for the repository's current staged changes. Use when the user asks for a commit message, commit title, git commit message, or conventional commit summary based on staged changes. The output must be only the message as plaintext code, with no explanation or follow-up text.

  • Prd review

    janellecipriano/pm-skills/skills/prd-review Skill

    1★ repo

    Review a product requirements document (PRD) or spec against a quality checklist and surface gaps, ambiguities, and risks before engineering starts. Use when the user says "review this PRD", "is this spec ready", "critique my requirements", "PRD checklist", or shares a doc and wants it pressure-tested before build.

  • Review plan

    metallurgical/ogre-runner/skills/review-plan Skill

    no license1★ repo

    Review an Ogre execution plan against the repository for hallucinations, risky assumptions, missing validation, and over-scoped steps.

  • Review

    metallurgical/ogre-runner/skills/review Skill

    no license1★ repo

    Alias of the `review-plan` skill - review an Ogre execution plan against the repository for hallucinations, risky assumptions, missing validation, and over-scoped steps. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre review ...", "use ogre review for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.

  • Market sizer

    MariusGithub13/open-deal-kit/agents/market-sizer Skill

    1★ repo

    Pressure-test the market story a seller tells, separate the CIM's quoted claims from a grounded estimate, flag what's vague, and surface the competitive reality being downplayed. Use when a CIM makes market-size or growth claims, or when asked to 'sanity-check the market', 'is this TAM real', or 'pressure-test the growth story'.

  • Multiple sanity checker

    MariusGithub13/open-deal-kit/agents/multiple-sanity-checker Skill

    1★ repo

    Give a plain reality check on price before you anchor, the implied multiple shown, whether it's rich/cheap/fair for the profile, what you'd be betting on, and the case for offering less. Use before anchoring on a price or making an offer, or when asked to 'am I overpaying', 'sanity-check this multiple', or 'is this price reasonable'.

  • Ami data validator

    AnaCataVC/amiga-ia/skills/ami-data-validator Skill

    1★ repo

    Skills and agents for Claude and Gemini

  • Ami pr peer reviewer

    AnaCataVC/amiga-ia/skills/ami-pr-peer-reviewer Skill

    1★ repo

    Assists in reviewing Pull Requests from other people. Understands the PR goal, reads available documentation, asks the user clarifying questions, focuses solely on modified code, and outputs quality observations with criticality levels.

  • Ami pr self reviewer

    AnaCataVC/amiga-ia/skills/ami-pr-self-reviewer Skill

    1★ repo

    Acts as a critical self-reviewer for your own Pull Requests (draft or published). Instead of just leaving comments, it analyzes the diff and proactively suggests and applies concrete code fixes.

  • Review to faq builder

    SkillMedev/ecommerce-dtc-ops/skills/review-to-faq-builder Skill

    1★ repo

    Mines customer reviews and Q&A exports into a pre-purchase PDP FAQ and objection-handling block that answers shopper hesitation before it forms, ordered by conversion impact. Use when someone asks "turn these reviews into an FAQ", "shoppers keep asking the same questions before buying", "how do I address the negative reviews on the product page", or has a review or Q&A export and wants to write or rebuild a product page FAQ or cut returns from preventable surprises. Do NOT use to analyze support tickets or CSAT/NPS verbatims for quality root causes - use csat-root-cause instead; do NOT use to write the main product description - use product-description-writer instead.

    The same file is in 1 other repository

  • Web quality gate

    SrCodexStudio/Claude-Forge/skills/web-quality-gate Skill

    no license1★ repo

    Comprehensive web quality audit covering accessibility (WCAG 2.2), best practices (CSP, headers), Core Web Vitals (LCP, INP, CLS), performance (loading, bundling), and SEO (meta tags, structured data). Gate that must pass before declaring any web task complete.

  • Vault sync

    hootbu/llm-wiki-mind/skills/vault-sync Skill

    1★ repo

    Projede yapılan değişikliği llm-wiki-mind vault'una sindir. Git log, commit mesajları ve diff'leri okur; etkilenen wiki sayfalarını (entities, concepts, decisions) günceller; raw/pr-discussions/ altına commit özet dosyası düşer. Proje-vault bağlantısı projenin CLAUDE.md'sinden okunur. Her commit, PR veya haftalık toplu senkron için kullanılır.

  • Pre deploy check

    Dom1ng0s/Claude-Skills/pre-deploy-check Skill

    1★ repo

    Análise read-only pré-produção agnóstica de linguagem, gerando um relatório com checklist e ações recomendadas.

  • Git flow

    kennguyen887/agent-foundation/skills/git-flow Skill

    1★ repo

    Use when branching, opening an MR, cutting a release, or shipping a hotfix — the develop→staging→master branching & release flow, tagging, semantic versioning, hotfix path. Tool-agnostic (plain git).

  • Integrate external services

    kennguyen887/agent-foundation/skills/integrate-external-services Skill

    1★ repo

    Use when integrating a third-party/external system — calling a vendor API (anti-corruption adapter behind your own interface, resilient HTTP with circuit breaker + retry/backoff, outbound HMAC request signing, idempotency keys), receiving inbound webhooks (raw-body capture, signature verification, idempotent fast-ack-then-enqueue, vendor→internal event mapping), or exposing a partner/public API edge (client-credentials + token introspection + scopes, API-key role guard, client→tenant mapping). NestJS/TS reference, framework-flexible. For service-to-service calls inside your own platform, see integrate-internal-services.

  • Operate ecs services safely

    kennguyen887/agent-foundation/skills/operate-ecs-services-safely Skill

    1★ repo

    Use before ANY change to a deployed container service behind a load balancer (AWS ECS/Fargate, or equivalent) — changing an env var / task-def, scaling, deploying, terminating an instance — AND when such a service is down (502/503, deploy stuck below desired, tasks failing the LB health check) or a scheduled/cron worker isn't running. A verify-before-mutate discipline + an observe→diagnose→recover playbook. Principle-first; AWS ECS commands shown, but the failure modes apply to any orchestrated container service.

  • Write cross cutting code

    kennguyen887/agent-foundation/skills/write-cross-cutting-code Skill

    1★ repo

    Use when writing a reusable request-pipeline primitive rather than feature logic — a custom decorator (param/metadata/method-wrapper + applyDecorators bundles), a guard (metadata-driven role/scope, or an OR-composition "any of these guards" guard), a pipe (polymorphic/variant DTO validation, or wrapping a built-in pipe to throw your typed error), an interceptor (metadata-driven audit/logging that fires after the response), middleware (correlation id), or a custom validation constraint (sync or async-with-DI via class-validator). NestJS reference, framework-flexible.

  • Worktree setup

    punkaze/skills/plugin/skills/worktree-setup Skill

    1★ repo

    Use when starting an isolated task that needs a git worktree on a NEW branch — any project. Triggers — "set up a worktree for X", "start a worktree for this task", "isolate this work in a worktree", or before a subagent-driven / executing-plans run on a repo not already in a linked worktree. Reads a per-project config (in-repo .worktree.json or a registry under $CLAUDE_PLUGIN_DATA/projects) to decide single vs dual/multi-repo scope (identical branch names on coupled repos), cut from the right base branch, copy env files, and run the right install command. No-op when no config matches and you are not asked to init one.

  • Portfolio review

    yeshelloAB/investment-analysis-skills/skills/portfolio-review Skill

    1★ repo

    Runs a systematic health check across all current portfolio positions: checking each holding against its thesis, flagging breaches, assessing overall portfolio balance, and producing a prioritised action list. Use whenever the user wants to review their portfolio, check the health of their holdings, do a position review, run a monthly or weekly portfolio check-in, assess which positions need attention, or get a portfolio-level view of where things stand. Triggers on: "portfolio review", "check my portfolio", "how are my positions?", "weekly review", "monthly review", "which stocks need attention?", "what's the state of the portfolio?", "portfolio health check", "run the portfolio", "go through my holdings", "thesis check on all positions", or any request to review multiple holdings at once rather than a single stock. This skill is also the natural choice when the user has just reviewed a stock tracker or spreadsheet and wants to know what to do next. Use it: do not wait for the user to ask explicitly.

  • Design review

    bromso/metapowers/plugins/design/skills/design-review Skill

    1★ repo

    Generate a Figma Slides presentation summarizing a component's design journey through all 5 phases

  • Review

    bromso/metapowers/plugins/development/skills/review Skill

    1★ repo

    Review code pre-merge for bugs, security, quality, and test coverage

  • Review

    bromso/metapowers/plugins/finance/skills/review Skill

    1★ repo

    Monitor performance against budget, analyze variances, and reforecast

  • Compliance review

    bromso/metapowers/plugins/legal/skills/compliance-review Skill

    1★ repo

    Review document for regulatory compliance (GDPR, CCPA, SOC2, etc.)

  • Contract review

    bromso/metapowers/plugins/legal/skills/contract-review Skill

    1★ repo

    Review a contract for risks, missing clauses, and unfavorable terms

  • Ip review

    bromso/metapowers/plugins/legal/skills/ip-review Skill

    1★ repo

    Review intellectual property assignments, licenses, and ownership

  • Definition of done

    bromso/metapowers/plugins/project-management/skills/definition-of-done Skill

    1★ repo

    Establish shared DoD criteria for stories, sprints, and releases

  • Sprint review

    bromso/metapowers/plugins/project-management/skills/sprint-review Skill

    1★ repo

    Prepare sprint review — what was done, what wasn't, stakeholder demo plan

  • Wip review

    bromso/metapowers/plugins/project-management/skills/wip-review Skill

    1★ repo

    Review work-in-progress against sprint goal and capacity

  • Backup validation

    bromso/metapowers/plugins/security/skills/backup-validation Skill

    1★ repo

    Plan backup strategy, testing, and restoration verification

  • Opus review

    tchr-dev/autonovel/.claude/skills/revision/opus-review Skill

    1★ repo

    Send the full manuscript to two parallel personas — literary critic + professor of fiction — for deep prose-level review. Parses the result with scripts/parse_review.py to extract numbered actionable items with severity and qualification status. Decides whether to keep revising or stop based on stopping conditions. Use after automated revision cycles plateau.

  • Grizzly review

    HarishDvs/Grizzly/skills/grizzly-review Skill

    1★ repo

    Comprehensive quality review of one or more chapters. Use when the user asks for a full review, quality check, violation scan, or pre-publication pass. Runs five passes with severity-tiered findings. For "why is this boring" use grizzly-audit instead.

  • Fast review

    tibichi/fast-preset/skills/fast-review Skill

    1★ repo

    Polish pass for an Astro/Tailwind/DaisyUI prototype before sharing - visual quality, responsive behavior, interaction states, DaisyUI consistency, and unresolved assumptions still showing in the UI. Use after a build session, before showing the prototype to stakeholders, or when something feels off.

  • Pre push

    POSTTTT/SKILLs/.claude/skills/pre-push Skill

    1★ repo

    Pre-flight safety gate that checks whether the project is actually safe to commit/push to GitHub (or any remote) RIGHT NOW. Use when the user asks "is this ready to push?", "can I commit this?", "check before I push", "did I leave any secrets in", "ready for GitHub?". Inspects the real git state — staged diff, tracked files, source, and history — for secrets/API keys, .env/.venv being tracked, PII, leftover debug/conflict markers, and .gitignore gaps. Read-only; reports a clear ready/blockers verdict and defers to the gitignore and security-audit skills for fixes.

  • Security audit

    POSTTTT/SKILLs/.claude/skills/security-audit Skill

    1★ repo

    Audit a codebase for security weaknesses against the OWASP Top 10 (2025) and seven hardening areas — secrets management, data encryption, input validation/injection, auth, dependency/supply-chain, error handling/logging, and configuration/transport hardening. Use when the user asks to "check security", "do a security review/audit", "find vulnerabilities", "is this app secure", "OWASP review", "check for hardcoded secrets / SQL injection / XSS", or similar. On invocation, ask which area(s) to investigate (or all), then report findings with severity, file:line, and remediation — without changing code until asked.

  • Repo organizer

    RashiD2801/Skills/repo-organizer Skill

    no license1★ repo

    Audits and reorganises a local GitHub repository into a clean, standard structure — proper folders (data/, models/, frontend/, backend/), all API keys moved to .env (which is added to .gitignore), hardcoded paths made agnostic, and missing files (README, PRD, requirements.txt, .gitignore) generated. Does NOT commit or push — user handles git.

  • Proofreading style check

    busyeugene/content-marketing-skills/proofreading-style-check Skill

    1★ repo

    Use when the user wants to proofread, style-check, or QA an article against editorial guidelines. Reads an article file and an editorial-guidelines.md, returns an inline diff plus a findings report. Optional LanguageTool layer for grammar.

  • Experiment design

    ramanbamba/10x-pm/skills/experiment-design Skill

    1★ repo

    Design an A/B test or product experiment with a falsifiable hypothesis, guardrail metrics, sample-size sanity check, and pre-committed decision rules. Use when the user says "design an experiment", "A/B test for", "how should we test this", "is this result significant", or wants to validate a product change with data.

  • Memory attribution lint

    cerebrocybersolutions/libro/skills/memory-attribution-lint Skill

    1★ repo

    Validate and auto-inject the 11-key provenance frontmatter contract on memory files at write time. Use when authoring memory entries, running lint passes on memory directories, or backfilling missing attribution fields. Enforces a uniform provenance schema (name, description, type, source_surface, host, tool, session_id, written_at_utc, source_path, confidence, lifecycle) so every memory entry is traceable to its origin surface, tool, and session.

  • Orchestrator mode

    cerebrocybersolutions/libro/skills/orchestrator-mode Skill

    1★ repo

    [LEGACY 2026-07-26 — retired upstream, shipped for reference only. Do NOT invoke against a live API key: the cloud path bills a real request against a beta unexercised since April 2026, on superseded model pins. The durable tier heuristic is preserved in the banner below.] Sequential chain routing — decomposes a compound task into subtasks, routes each subtask to its optimal tier (via advisor-mode underneath), runs a quality-gate check after each step, and escalates to a higher tier on gate failure. Complements council-mode (parallel comparison). Orchestrator is the "route around failure" thesis applied sequentially: keep each subtask on the cheapest tier that passes, escalate only when the gate fails. Trigger on: "orchestrator mode", "chain this", "break this into subtasks", "route each step", "escalation pipeline", "run this as a chain", "decompose and route", "quality- gated routing", "sequential tier routing", "run the orchestrator".

  • Sessionstart

    cerebrocybersolutions/libro/skills/sessionstart Skill

    1★ repo

    Session opening ritual v2.4 — adds Stage 0 session-continuity probe (short-circuits full brief on same-day reopens within 1h break window), single-shot Stage 2 brief loader (one Bash call surfaces dept CLAUDE.md, latest session, pending decisions, dashboard header, memory index, and infrastructure state), runs ground-truth verification against filesystem (including a recursion guard so corrections themselves verify before firing), auto-corrects stale memory, delivers a Department Head Brief plus Infrastructure Snapshot, captures session intent, and renders the same brief to an HTML archive. Use when the user types /sessionstart or says they're getting started, picking up where they left off, or starting a new session.