agentsclimarketplace

Review & quality

19,000 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

  • Loop review

    rossinsilico/loop-anything/.agents/skills/loop-review Skill

    0★ repo

    Review a loop iteration as an independent checker before proof, commit, push, merge, deploy, or completion claims.

  • Loop review

    rossinsilico/loop-anything/templates/loop-pack/skills/loop-review Skill

    0★ repo

    Review a loop iteration as an independent checker before proof, commit, push, merge, deploy, or completion claims.

  • Pr ready

    HM-IT-CODE/forge-skills/skills/engineering/pr-ready Skill

    0★ repo

    Prepares the current branch into a clean, reviewable pull request. Use when the user says "open a PR", "make this PR-ready", "prepare a pull request", "clean up my commits", or is about to push for review. Produces conventional commits, a self-review, and a PR description.

  • Ren review

    HubertBiyo/ren-flow/plugins/ren-flow/skills/ren-review Skill

    0★ repo

    代码评审 —— 以怀疑态度独立检查代码的规范合规、潜在 bug、架构分层、可维护性。支持主动审计(扫模块列问题清单),以及接收评审(处理别人对你代码的 review 意见)。触发:用户说「review 一下」「评审代码」「提交前 check」「扫一下问题」「收到 review 意见了」「别人说我代码有问题」。

  • Ren ship

    HubertBiyo/ren-flow/plugins/ren-flow/skills/ren-ship Skill

    0★ repo

    提交收尾 —— 生成规范的 commit message、整理改动范围、按需起 PR 描述。触发:用户说「提交」「commit message」「给我提交说明」「准备 PR」。

  • Ren verify

    HubertBiyo/ren-flow/plugins/ren-flow/skills/ren-verify Skill

    0★ repo

    交付验收 —— 逐条核对规格的验收契约,运行命令收集证据,判断这次改动能不能交。触发:用户说「验收」「能提交了吗」「做完了」「检查一下交付」,或 ren-build 实现完成后进入。

  • Wiki history checker

    jimyoshida/generic-agent-skills/.agents/skills/wiki-history-checker Skill

    no license0★ repo

    Use when the user provides the wikitext of a MediaWiki/Wikipedia article (a .wikitext/.txt file or pasted markup) and wants to find events its chronology is MISSING. Works on dedicated "Timeline of ..." pages AND on the History section of any ordinary article. Parses the existing dated entries, numbers them, researches notable events for the theme, cross-checks against the latest version/release info, and reports gaps as suggested new entries with the entry number each would take. Triggers on "find missing events", "gaps in this timeline", "check this history", "what's missing from this history/timeline", "research this timeline", "suggest events for this timeline".

  • Ethics compliance reviewer

    lensetek/Digital-Marketing-Agent_Skills/skills/ethics-compliance-reviewer Skill

    0★ repo

    Reviews claims, privacy, credential exposure, platform rules, legal risk, bias, and reputation risk before publishing.

  • Upstream fix and pin

    krkrkrr/skills/skills/deps/upstream-fix-and-pin Skill

    no license0★ repo

    自分の依存ライブラリにバグや欠けている機能があり、上流に PR を出して取り込まれるまで下流プロジェクトを動かしたいときの運用。git ref pin(branch HEAD SHA → merge SHA)、`link:` への退避判断、SHA 取り扱い、pnpm v10 の build script gating まで含む。

  • Frontend review ci

    krkrkrr/skills/skills/frontend/frontend-review-ci Skill

    no license0★ repo

    Use when CI is slow (>10 min), flaky, or the user asks to optimize GitHub Actions for a frontend project. Analyzes `gh run list` history, identifies bottleneck steps, proposes sharding / cache / concurrency improvements. Runs `scripts/audit-ci.sh`.

  • Frontend review deps

    krkrkrr/skills/skills/frontend/frontend-review-deps Skill

    no license0★ repo

    Use when auditing dependency health — outdated packages, CVE triage with attack-vector weighting, deprecated/declining library detection (trend-watch). Runs `audit-deps.sh` and `audit-trend-watch.sh`. Pairs with `frontend-review-security` for the full security picture.

  • Frontend review hygiene

    krkrkrr/skills/skills/frontend/frontend-review-hygiene Skill

    no license0★ repo

    Use when assessing code quality hygiene — TypeScript strictness, lint violations, dead code, and duplication. Runs `audit-typescript.sh`, `audit-lint.sh`, `audit-similarity.sh`. Does NOT cover dependency freshness or CVE audit — use `frontend-review-deps` for that.

  • Frontend review performance

    krkrkrr/skills/skills/frontend/frontend-review-performance Skill

    no license0★ repo

    Use when reviewing React rendering performance — profiler-first diagnosis, memo/useCallback/useMemo correctness, virtual scroll, useTransition/useDeferredValue, and canvas/WebGL separation for data-heavy UIs. Covers checklist 24-rendering-performance.md.

  • Frontend review security

    krkrkrr/skills/skills/frontend/frontend-review-security Skill

    no license0★ repo

    Use when conducting a frontend security review — static analysis (risky HTML patterns, env var exposure), authentication/authorization audit (token storage, route guards, logout), and AI self-penetration testing. Runs `scripts/audit-security.sh`. For CVE triage and deprecated library detection, use `frontend-review-deps`.

  • Frontend review state

    krkrkrr/skills/skills/frontend/frontend-review-state Skill

    no license0★ repo

    Use when reviewing state management architecture — classifying state types (server/URL/form/UI), checking for over-globalization, Jotai/Zustand/Redux patterns, derived state, and logout/cache invalidation. Covers checklist 23-state-management.md.

  • Frontend review testing

    krkrkrr/skills/skills/frontend/frontend-review-testing Skill

    no license0★ repo

    Use when auditing test infrastructure — vitest coverage, playwright configuration, VRT setup, coverage merging. Produces recommendations for Week 2 testing phase. Runs `scripts/audit-coverage.sh`.

  • Frontend review triage

    krkrkrr/skills/skills/frontend/frontend-review-triage Skill

    no license0★ repo

    Use when starting a frontend review engagement or when the user asks for an initial assessment ("triage", "day 0", "what's the state of this repo"). Reads package.json, README, gh issues, and produces a scorecard covering lockfiles, TypeScript strictness, testing, CI, and known issues. Runs `scripts/audit-triage.sh`.

  • Frontend review weekly

    krkrkrr/skills/skills/frontend/frontend-review-weekly Skill

    no license0★ repo

    Use for the weekly AI review. Orchestrates all frontend-review-* skills in order, dispatches the 5 perspective sub-skills in parallel, diffs against last week's KPIs, and produces a weekly report that feeds the ratchet.

  • External api tos check

    krkrkrr/skills/skills/meta/external-api-tos-check Skill

    no license0★ repo

    Use before writing or modifying code that integrates, embeds, or calls any third-party API/SDK/service (video/stream embeds like YouTube or Twitch, payment providers, LLM APIs, maps, ads SDKs, auth providers, etc.). Trigger whenever a task adds a new external provider, changes embed/autoplay/player behavior, upgrades an SDK across a major version, or touches code under a provider-named directory (e.g. src/youtube/, src/twitch/) — even if the user does not say "terms of service" or "ToS". Confirms the provider's official Terms of Service / Developer Policy / Developer Agreement allows the planned behavior before implementation, and records material constraints as an ADR.

  • Grill with docs

    vincendiary/agents/skills/grill-with-docs Skill

    no license0★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 256 other repositories

  • Prototype

    vincendiary/agents/skills/prototype Skill

    no license0★ repo

    Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

    The same file is in 11 other repositories

  • Api contract testing

    agent-packs/registry/skills/api-contract-testing Skill

    no license0★ repo

    Verify API correctness through contract tests, integration tests, and schema validation. Use when building or consuming REST or GraphQL APIs, or when integrating services that must agree on a shared interface.

  • Code review and quality

    agent-packs/registry/skills/code-review-and-quality Skill

    no license0★ repo

    Review code across correctness, maintainability, tests, security, and user-visible behavior. Use before merge or when assessing a change.

  • Code review workflow

    agent-packs/registry/skills/code-review-workflow Skill

    no license0★ repo

    Review pull requests and code changes for behavioral regressions, risks, missing tests, and maintainability issues. Use when asked to review code, inspect diffs, or assess PR quality.

  • Git workflow and versioning

    agent-packs/registry/skills/git-workflow-and-versioning Skill

    no license0★ repo

    Use atomic commits, trunk-based development, branch hygiene, and versioning practices. Use when making or shipping code changes.

  • Performance hotspot check

    vishnujchandran/.agents/skills/performance-hotspot-check Skill

    no license0★ repo

    Evidence-first performance analysis skill that identifies high-impact bottlenecks in app code, database access, and API calls with safe, minimal-diff optimization plans.

  • Git guide me

    smanaton/git-coach/skills/git-guide-me Skill

    0★ repo

    Guide a user through an everyday git operation, teaching the command as it runs: show the literal command before running it, run safe operations, hand destructive ones to the user, then echo what ran and how to undo it. Use when the user roughly knows what they want — stage and commit, make a branch, merge, switch, stash, push — and wants the command shown and explained as it runs. Skip when the user is lost or needs to diagnose their state (use git-next).

  • Git next

    smanaton/git-coach/skills/git-next Skill

    0★ repo

    Diagnose the current git state and recommend the single best next command. Scans status, branch tracking, stash, reflog, and in-progress merge/rebase/cherry-pick, names the situation, then gives the next command plus its undo. Use when stuck or lost in git, mid-operation, in detached HEAD, facing a merge conflict, or unsure what to do next. Read-only and suggest-only, never runs destructive recovery. Skip when the user already knows the operation they want, which is git-guide-me, or wants a concept explained, which is git-explain.

  • Git setup

    smanaton/git-coach/skills/git-setup Skill

    0★ repo

    Onboarding and environment setup for the git-coach skill set. Assesses your git experience level, checks your environment (git installed, version, Node.js for drills), and guides you to the right starting skill. Use when you're new to git-coach, want to set up git, need to check your environment, or when the current directory is empty and not a git repo. Triggers on 'teach me git', 'git setup', 'how do I get started with git', or when no git repo exists and the user seems to be a beginner. Skip when you already know which skill you need and the environment is ready.

  • Pr readiness

    newesp/my-skills/pr-readiness Skill

    no license0★ repo

    Use when a feature, module, or otherwise meaningful chunk of work is fully implemented and about to be handed off for human review — NOT after every small fix, one-line tweak, or intermediate push within an in-progress feature. Trigger on phrases like "這個功能做完了", "ready for review", "PR 準備好了", "before I open a PR", "before merging this feature", or when the agent itself is about to signal that a substantial piece of work is finished. Covers documentation updates, dead-code cleanup, build/lint/test verification, secrets/PII scanning, focused self-review, and an optional user-requested three-reviewer dispatch. Applies regardless of which user or project.

  • Llm endpoint

    payne0420/claude-ultracode-agents/llm-endpoint Skill

    0★ repo

    Call a configured OpenAI-compatible (`/v1/chat/completions`) or Anthropic-compatible (`/v1/messages`) HTTP endpoint as a lightweight model backend — a raw completion call, not an autonomous agent. Use as an alternative to the codex/cursor/opencode CLI harnesses when you want to hit an arbitrary model behind a gateway/router/proxy (e.g. for a second opinion, a quick review of pasted/piped context, or text generation), or to plug such an endpoint into an ultracode workflow. The base URL and API key are read from local config and are never hardcoded. Works with any `/v1` chat or `/v1/messages` endpoint. Triggers: "use my llm endpoint", "call my openai-compatible endpoint", "hit /v1/chat/completions", "use the /v1/messages endpoint", "use my model gateway / router / proxy", "second opinion from my endpoint", "run this through my API endpoint".

  • Opencode

    payne0420/claude-ultracode-agents/opencode Skill

    0★ repo

    Drive the opencode CLI non-interactively via `opencode run` to delegate coding work to a second, independent agent. Use this skill when the user wants a second opinion on a design or bug, an independent implementation plan, an independent code review of a diff or GitHub PR, a self-contained implementation task run headlessly, parallel/background work on a sub-task, or cross-checking your own work against another model (opencode is model-agnostic and can run many providers). Also use when the user explicitly mentions "opencode", "opencode run", or asks to "have opencode plan / look at / build / review" something. Triggers: "ask opencode", "get a second opinion from opencode", "have opencode plan this", "have opencode review this", "run opencode on X", "delegate this to opencode", "opencode run ...".

  • Ultracode external agents

    payne0420/claude-ultracode-agents/ultracode-external-agents Skill

    0★ repo

    Author ultracode workflows whose agent() steps are executed by an EXTERNAL coding CLI — OpenAI Codex, Cursor, or opencode — instead of (or alongside) regular Claude subagents. Use this to run an individual agent() step on a different model/provider; that one bridged step drops into ANY workflow shape — a single second-opinion step in a pipeline, one off-budget implementation step, a design probe, or (when you want disagreement) a fan-out panel. The shape is the Workflow tool's job; this skill only changes what one agent() runs on. Explains the bridge (a thin Claude adapter shells out to the CLI), gives copy-paste delegation helpers, per-backend invocation recipes, structured-output mapping, worktree isolation for parallel writes, and a full runnable example workflow. Applies only inside an ultracode/Workflow authoring turn — the Workflow tool must be active; if it is not, this skill has nothing to do and should not be selected. Triggers: "use codex/cursor/opencode in a workflow", "ultracode with codex", "run my workflow on GPT/Composer instead of Claude", "multi-model workflow", "delegate workflow agents to an external CLI", "multi-model review panel", "external agents in a workflow", "fan out to different models".

  • Iac review

    stevancris/sre-ai-agent/skills/iac-review Skill

    0★ repo

    Review Infrastructure as Code changes for correctness, security, and operational safety. Use when reviewing Terraform, Pulumi, CloudFormation, Kubernetes manifests, Helm charts, or Ansible playbooks before applying them. Covers security misconfiguration, resource drift, cost impact, and blast radius. Trigger keywords: Terraform, IaC, infrastructure as code, Kubernetes manifest, Helm chart, CloudFormation, Pulumi, Ansible, tf plan, terraform plan, k8s yaml, review infra, apply this, should I apply, is this safe, infra change, eks, rds, s3, iam role, security group.

  • Production readiness review

    stevancris/sre-ai-agent/skills/production-readiness-review Skill

    0★ repo

    Review a service or feature for production readiness before launch. Use when a new service is about to go live, when an existing service is adding a major new capability, or when onboarding a service to SRE ownership. This is the primary shift-left skill — catching reliability, observability, and operational gaps before they become incidents. Trigger keywords: production readiness, PRR, launch readiness, ready to launch, ready for production, going to prod, new service, onboard service, pre-launch, launch review, is this ready, can we ship, pre-production checklist, launch checklist, go live checklist, service handover, SRE handoff.

  • Branch sync

    TheophilusChinomona/idev/skills/branch-sync Skill

    0★ repo

    Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

  • Build check

    TheophilusChinomona/idev/skills/build-check Skill

    0★ repo

    Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

  • Commit style

    TheophilusChinomona/idev/skills/commit-style Skill

    0★ repo

    Team commit-message conventions. Use when writing a commit message, committing or amending changes, or when asked about the project's commit format. Reads the per-project style from .claude/idev/commit-style.md.

  • Post creation verify

    TheophilusChinomona/idev/skills/post-creation-verify Skill

    0★ repo

    Claude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.

  • Self review

    TheophilusChinomona/idev/skills/self-review Skill

    0★ repo

    Code-quality checklist run on Claude's own output before reporting done: unused imports, missing error handling, naming consistency, security issues. Use after completing any code changes.

  • Sheepdog review

    filipores/sheepdog/skills/sheepdog-review Skill

    0★ repo

    Review a diff or target for agentic architecture drift and boundary-law violations. Use for sheepdog review, architecture drift review, god orchestrator review, layer-boundary review, or before merging AI-generated code. Report only; do not edit.

  • Loam linting memory

    scchearn/loam/skills/loam-memory/loam-linting-memory Skill

    0★ repo

    Run a health check on existing memory (the wiki substrate) and goal artifacts. Use this when the user wants to lint the wiki, health-check the knowledge base, find orphan pages, spot broken or missing cross-links, clean up stale claims and unresolved wikilinks with safe local fixes, consolidate a legacy root `overview.md` into `index.md`, or health-check goal artifacts. Not for adding new material; use /loam::adding-to-memory or /loam::learning-from-session for that.

  • Research

    OpenBioHack/openbiohack/skills/research Skill

    0★ repo

    General-purpose first-principles research engine that enforces genuine reasoning through structural gates — not advice to "think harder" but mandatory steps that prevent authority bias, lazy analogies, survivorship narratives, and summary-as-analysis. Use this skill whenever the user needs rigorous analysis of a complex question, strategic research, market viability analysis, technology assessment, competitive analysis, scenario planning, psychology research, processing studies, verifying clinical claims, or any deep research where getting it wrong has real consequences. Also trigger when the user says "research this deeply", "first principles", "think this through", "analyze this properly", "don't just summarize", "psych research", "find studies on", "verify this claim", or any variant suggesting they want genuine depth rather than plausible-sounding text. Especially important for novel or unprecedented questions where pattern-matching from historical precedent is unreliable. Includes specialized psychology/clinical research workflows (topic exploration, source processing, claim verification, zettelkasten connections).

  • Kometa debug review

    nichtlegacy/kometa-skill/skills/kometa-debug-review Skill

    0★ repo

    Use whenever the user asks why Kometa YAML fails, asks for review, has indentation problems, has the wrong top-level key, mixed up file types, missing connectors, or wants a broken config repaired. Use this skill aggressively for any Kometa troubleshooting or review request.

  • Cross model review

    Neznakometz/StackForge/core/skills/cross-model-review Skill

    0★ repo

    Mandatory re-check of the code by an external model (Codex/ChatGPT and/or Gemini) acting as an independent reviewer. Apply on every task after the internal reviewers and on the diff at the end of a phase.

  • Lens studio preview verify

    zajalist/zajal-skills/skills/lens-studio-preview-verify Skill

    0★ repo

    Use when running, previewing, and verifying a Lens Studio project edited over MCP — applying scene edits to the running lens, screenshotting the preview, checking that TypeScript compiled, and working around log/compile timeouts. Includes the "no Save tool" reality.

    The same file is in 1 other repository

  • Review

    Skillroy-AI/skillroy/.claude/skills/review Skill

    0★ repo

    Lint a skill (or a whole collection) against skillroy conventions and the Agent Skills standard, and report what to fix. Checks frontmatter validity, name-equals-folder, the metadata.skillroy block, naming and tier rules, canonical-token usage, the two-front-doors principle, and the phase-appropriate quality bar (evals, license, no plaintext secrets). Use when reviewing, linting, auditing, or checking a skill for compliance, before advancing a skill's phase, or before publishing a skill or collection. Pairs with `create`, which authors compliant skills.

  • Canary watch

    goharabbas321/zeoel/skills/canary-watch Skill

    no license0★ repo

    Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or dependency upgrades. Smoke / canary / post-deploy verification.

    The same file is in 2 other repositories

  • Changelog generator

    goharabbas321/zeoel/skills/changelog-generator Skill

    no license0★ repo

    Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

    The same file is in 14 other repositories

  • Flutter dart code review

    goharabbas321/zeoel/skills/flutter-dart-code-review Skill

    no license0★ repo

    Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.

    The same file is in 3 other repositories

  • Git workflow

    goharabbas321/zeoel/skills/git-workflow Skill

    no license0★ repo

    Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.

    The same file is in 3 other repositories

  • Laravel verification

    goharabbas321/zeoel/skills/laravel-verification Skill

    no license0★ repo

    Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

    The same file is in 5 other repositories

  • Network config validation

    goharabbas321/zeoel/skills/network-config-validation Skill

    no license0★ repo

    Pre-deployment checks for router and switch configuration, including dangerous commands, duplicate addresses, subnet overlaps, stale references, management-plane risk, and IOS-style security hygiene.

    The same file is in 3 other repositories

  • Security review

    goharabbas321/zeoel/skills/security-review Skill

    no license0★ repo

    Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

    The same file is in 3 other repositories

  • Using git worktrees

    goharabbas321/zeoel/skills/using-git-worktrees Skill

    no license0★ 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 loop

    goharabbas321/zeoel/skills/verification-loop Skill

    no license0★ repo

    A comprehensive verification system for Claude Code sessions.

    The same file is in 8 other repositories

  • React performance review

    nbsp1221/skillpin/test/fixtures/skills/react-performance-review Skill

    0★ repo

    Reviews React components for avoidable rerenders.

  • React performance review

    nbsp1221/skillpin/test/fixtures/skills/search-library/react-performance-review Skill

    0★ repo

    Reviews React components for avoidable rerenders and performance regressions.

  • Contributing framework changes

    vemodalen-x/VEMO_SKILLS/skills/governance/contributing-framework-changes Skill

    0★ repo

    Contribute a local improvement to a governance framework back to that framework's repo via a pull request. Use when a local framework or skill-home change should be proposed upstream. Works for any contributor — write-access holders push a branch to the repo directly; contributors without write access fork and open a cross-repo PR. The path is chosen at runtime by probing the actual permission; no identity, org, or account is hardcoded.

  • Packaging device sdk releases

    vemodalen-x/VEMO_SKILLS/skills/orchestration/packaging-device-sdk-releases Skill

    0★ repo

    Assemble an algorithm library into a deliverable on-device (mobile) SDK release package — the release version is assigned by `bumping-library-versions` (referenced, not restated), plus a standard package layout (minimal public headers / per-ABI libs / models each license-annotated / RELEASE_NOTES / USAGE doc / a compilable examples/ source / THIRD_PARTY), and two ship-along reports (quality + performance) that REUSE the eval-report and on-device-validation skills rather than re-spec them. Owns the package-specific parts: the memory = system-delta measurement method, license-boundary annotation, and a manifest + sha + unpack-reverify check (incl. verifying the version surfaces agree). Packaging is NOT releasing — shipping the package outward is a human/lead decision. Use when an algorithm lib must become a versioned, auditable phone SDK package. Identity-decoupled — lib name, version, platform, group are caller parameters.