agentsclimarketplace

Review & quality

19,178 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

  • Woo webhook health check

    navarroido/Woocommerce-skill/skills/store-management/woo-webhook-health-check Skill

    5★ repo

    Read-only: List all webhooks with delivery URL, status, and failure count.

  • Tb review

    itsadrianxv/tradeblazer_skills/skills/tb-review Skill

    no license5★ repo

    Use when reviewing, debugging, or improving TBQ3/TB language code for trading correctness, Bar strategy behavior, order direction, position state, sizing, costs, backtest realism, event timing, multi-symbol logic, or function documentation consistency.

  • Opencode review

    shyuan/skills/skills/opencode-review Skill

    5★ repo

    A curated collection of Agent Skills for Claude Code and compatible agents.

  • Aipom portfolio quarterly review

    deanpeters/ai-product-operating-model-skills/skills/aipom-portfolio-quarterly-review Skill

    no license5★ repo

    Run a recurring AI portfolio review that reallocates capital and capacity using strategy, outcomes, economics, readiness, production evidence, dependencies, and learning.

  • Aipom production evidence review

    deanpeters/ai-product-operating-model-skills/skills/aipom-production-evidence-review Skill

    no license5★ repo

    Run a recurring review of AI behavior, workflow, human, outcome, control, incident, and affected-party evidence to continue, change, constrain, roll back, or retire.

  • Meta review

    stefanoskarakasis/Product-Marketing-Skills/pmm-meta/meta-review Skill

    5★ repo

    Skill quality audit engine with auto-fix mode, trending dashboard, and CI/CD integration. Scores PMM skill outputs (GTM briefs, positioning, beachhead, etc.) against quality rubrics informed by Pawel Huryn's positioning rigor (unique value clarity) and 2026 GTM best practices (adoption curves, cross-functional alignment, enablement timing). Auto-detects output type, applies tier-specific quality gates, generates fix recommendations, tracks quality trends, and logs persistent learnings for team-wide calibration. Trigger on: "review this output", "quality check", "is this good enough", "audit this", or any request to validate PMM outputs.

  • Meta verify

    stefanoskarakasis/Product-Marketing-Skills/pmm-meta/meta-verify Skill

    5★ repo

    Second-pass quality check on T1 skill output. Reads output cold — without the context of how it was produced — and checks it against the originating skill's operating rules and quality gate criteria. The difference between a skill self-grading and an independent evaluator. Start with T1 skills: pre-mortem, go-to-market-strategy, positioning-messaging. Trigger on: "verify this output", "check this brief", "is this pre-mortem complete", "second opinion on this", "quality check this", or any request to independently validate a skill output before acting on it.

  • Pmm resume

    stefanoskarakasis/Product-Marketing-Skills/pmm-toolkit/skills/pmm-resume Skill

    5★ repo

    PMM Skills Marketplace: 25+ agentic skills — from growth experiments to Go-To-Market strategy, execution, CI, and market research.

  • Sequence qa reviewer

    First-Touch-Inc/firsttouch-agent-skill-packs/plugins/revops-pack/skills/sequence-qa-reviewer Skill

    5★ repo

    Review a FirstTouch LinkedIn campaign/sequence for risk and quality before it launches - checking send safety, messaging quality, personalization depth, duplicate risk, and compliance with the FirstTouch messaging framework. Produces a risk-scored review with specific fixes. Use when the user wants to QA a campaign, review a sequence before launch, check if outreach is safe/good, or audit existing live campaigns.

  • Sequence qa reviewer

    First-Touch-Inc/firsttouch-agent-skill-packs/skills/sequence-qa-reviewer Skill

    5★ repo

    Review a FirstTouch LinkedIn campaign/sequence for risk and quality before it launches - checking send safety, messaging quality, personalization depth, duplicate risk, and compliance with the FirstTouch messaging framework. Produces a risk-scored review with specific fixes. Use when the user wants to QA a campaign, review a sequence before launch, check if outreach is safe/good, or audit existing live campaigns.

  • Native validation

    BjornMelin/dev-skills/archive/skills/native-validation Skill

    no license5★ repo

    Use this skill for Validation for native motion changes: Expo Doctor, expo install --check, EAS/development build risk, Jest/Reanimated setup, RN tests, platform smoke, and audit report closeout. Trigger on Expo Doctor, expo install --check, EAS build validation, native motion validation, Reanimated Jest, development build proof. Do not use for near-miss tasks outside these boundaries; route to adjacent motion or platform skills when they own the implementation.

  • Claude subagent creator

    BjornMelin/dev-skills/plugins/claude-core/skills/claude-subagent-creator Skill

    no license5★ repo

    Author, validate, and install custom Claude Code subagents as .claude/agents Markdown files. Use when the user asks to create a subagent, custom agent, or .claude/agents role; define a reusable reviewer, explorer, planner, or worker persona; set an agent's model or tool allowlist; or turn a recurring workflow into a delegatable role. Produces Markdown agent files with YAML frontmatter (name, description, model, tools) plus a focused system-prompt body, scoped to the smallest tool surface that does the job (read-only by default). Covers naming, description wording for autonomous delegation, model policy (Opus for reasoning/review, inherit for scans), tool scoping, project vs user scope, and a smoke test. Pairs with fan-out, which delegates to these roles. Not for one-off ad-hoc delegation (use fan-out) or authoring Agent Skills (SKILL.md files).

  • Pr thread resolver

    BjornMelin/dev-skills/plugins/claude-core/skills/pr-thread-resolver Skill

    no license5★ repo

    Fetches, fixes, and resolves unresolved GitHub PR review threads with the gh CLI. Use when addressing reviewer feedback, clearing blocking conversations before merge, or applying GitHub suggested changes. Verifies each finding against current code and resolves only what it fixed.

  • Autoreview

    BjornMelin/dev-skills/skills/autoreview Skill

    no license5★ repo

    Run a Codex-only structured code review closeout for local, branch, or commit diffs. Use when the user asks for autoreview, Codex review, structured closeout review, final review before commit/ship, or review after non-trivial code edits.

  • Batch grill with docs

    BjornMelin/dev-skills/skills/batch-grill-with-docs Skill

    no license5★ repo

    Batch-grill a plan or design round by round: whole settled frontier per round, recommended answers + close-call scores, ADRs + a glossary via domain-modeling, /pre-mortem handoff on irreversible calls.

  • Codex review

    BjornMelin/dev-skills/skills/codex-review Skill

    no license5★ repo

    AgentSkills library: reusable skills for AI coding agents (AI SDK, Codex, LangGraph, Supabase, Docker, Vitest, pytest, Streamlit, Zod).

  • Commit

    BjornMelin/dev-skills/skills/commit Skill

    no license5★ repo

    Stage + commit changes in semantic + reviewablegroups. Use when user wants to commit changes, organize commits, or clean up a branch before pushing.

  • Gh pr review fix

    BjornMelin/dev-skills/skills/gh-pr-review-fix Skill

    no license5★ repo

    Fix unresolved GitHub PR review threads with codex-dev: fetch hosted state, verify, patch, validate, commit, push, and close out.

  • Grill me

    BjornMelin/dev-skills/skills/grill-me Skill

    no license5★ 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".

  • Multi model review

    BjornMelin/dev-skills/skills/multi-model-review Skill

    no license5★ repo

    Pre-PR multi-model review, parallel opus and codex exec adversarial lanes, then adversarial verification of merged findings. Read-only. Use before shipping nontrivial diffs.

  • New branch

    BjornMelin/dev-skills/skills/new-branch Skill

    no license5★ repo

    Create and switch to a new conventional-commit and semver-compliant branch before doing any work, then present the full execution plan for that branch and its pull request. Use when the user wants a branch prepared first and a clear plan in chat before implementation.

  • Review remediation

    BjornMelin/dev-skills/skills/review-remediation Skill

    no license5★ repo

    Fix local review (Codex, Zen, notes) w/ verify. Not gh-pr-review-fix or passive PR monitoring.

  • Ship branch

    BjornMelin/dev-skills/skills/ship-branch Skill

    no license5★ repo

    Finalize a branch by staging only task-related files, splitting work into semantic reviewable conventional commits, pushing to remote, and opening a PR into main with a conventional-commits title and reviewer-ready body. Use when the user asks to commit, push, and open a PR, or to scaffold missing repo PR/release defaults on request.

  • Code review expert

    kevinlin/skills/code-review-expert Skill

    5★ repo

    Expert code review with a senior engineer lens — covers architecture, SOLID principles, security vulnerabilities, performance, error handling, testing gaps, and API contract changes. Use this skill whenever the user asks to review code, check changes, audit a diff, look over a PR, find bugs in their work, or wants feedback on code quality. Also trigger when the user says things like 'review my changes', 'check this before I push', 'what do you think of this code', 'any issues with this?', 'code review', 'look this over', or 'is this ready to merge'. Works with any programming language and any size of change.

  • Spec lint

    kevinlin/skills/spec-lint Skill

    5★ repo

    Lint the project's specification docs (requirements / design / plan / task markdown): orphan specs, dead cross-doc links, index and naming drift, empty sections, stale TODOs, and — most importantly — reverse consistency between layers (design must cover its requirements, plans must cover their design). Auto-detects which spec-driven framework is in use — Kiro IDE, Superpowers, OpenSpec, GitHub spec-kit, BMad Method, GSD, or a generic default profile — and applies that profile's rules. Use when the user asks to lint, audit, or health-check spec docs ("/spec-lint", "check the specs", "spec health check"), asks whether design covers requirements or plans match the design, reports orphan specs or broken spec links, or names a supported framework in a context that implies auditing its spec artefacts.

  • Verify

    alessiomarcone/agent-fieldbook/plugins/knowledge-pack/skills/verify Skill

    5★ repo

    Fact-checks and stress-tests AI answers or artifacts with claim-level evidence, uncertainty, anti-hallucination, and anti-sycophancy checks. Use for brief or detailed requests to check, verify, or review an answer before sending or publishing, and for consequential legal, financial, technical, or customer-facing decisions.

  • Content review

    0xF4ng/aether-growth-fieldwork/pmm/content-review Skill

    no license5★ repo

    Scores content pieces and experiment specs before publication or launch. Part A: content scoring (8 dimensions, 0.0–1.0 each). Part B: experiment spec scoring (8 dimensions). Calibrated examples anchor scores across sessions. Verdict: APPROVE / REVISE / REJECT.

  • Launch readiness review

    0xF4ng/aether-growth-fieldwork/pmm/launch-readiness-review Skill

    no license5★ repo

    Launch gate. Runs a software or hardware checklist against the launch brief after Phase 1 QA. Blocks GO status until all applicable items pass. Verdict: GO / CONDITIONAL-GO / NO-GO.

  • Positioning review

    0xF4ng/aether-growth-fieldwork/pmm/positioning-review Skill

    no license5★ repo

    Artifact gate for positioning output. Runs a binary checklist against the positioning artifact produced by /positioning. Blocks FINAL status until all items pass. Verdict: FINAL / REVISE / BLOCK.

  • Code review

    chinkan/RustFox/.agents/skills/code-review Skill

    5★ repo

    Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

    The same file is in 12 other repositories

  • Finishing a development branch

    chinkan/RustFox/.agents/skills/finishing-a-development-branch Skill

    5★ 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 17 other repositories

  • Grill me

    chinkan/RustFox/.agents/skills/grill-me Skill

    5★ repo

    A relentless interview to sharpen a plan or design.

    The same file is in 19 other repositories

  • Grill with docs

    chinkan/RustFox/.agents/skills/grill-with-docs Skill

    5★ repo

    A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    The same file is in 19 other repositories

  • Prototype

    chinkan/RustFox/.agents/skills/prototype Skill

    5★ repo

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    The same file is in 6 other repositories

  • Receiving code review

    chinkan/RustFox/.agents/skills/receiving-code-review Skill

    5★ 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

    chinkan/RustFox/.agents/skills/requesting-code-review Skill

    5★ repo

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

    The same file is in 3 other repositories

  • Resolving merge conflicts

    chinkan/RustFox/.agents/skills/resolving-merge-conflicts Skill

    5★ repo

    Use when you need to resolve an in-progress git merge/rebase conflict.

    The same file is in 11 other repositories

  • Using git worktrees

    chinkan/RustFox/.agents/skills/using-git-worktrees Skill

    5★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

    The same file is in 12 other repositories

  • Verification before completion

    chinkan/RustFox/.agents/skills/verification-before-completion Skill

    5★ 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

  • Finishing a development branch

    chinkan/RustFox/.cursor/skills/finishing-a-development-branch Skill

    5★ 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 17 other repositories

  • Receiving code review

    chinkan/RustFox/.cursor/skills/receiving-code-review Skill

    5★ 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

    chinkan/RustFox/.cursor/skills/requesting-code-review Skill

    5★ 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

    chinkan/RustFox/.cursor/skills/using-git-worktrees Skill

    5★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

    The same file is in 12 other repositories

  • Verification before completion

    chinkan/RustFox/.cursor/skills/verification-before-completion Skill

    5★ 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

  • Compliance checker

    Gingg7260/affiliate-skills/skills/meta/compliance-checker Skill

    5★ repo

    Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check before publishing", "disclosure audit", "review my ad copy".

    The same file is in 1 other repository

  • Purple cow audit

    Gingg7260/affiliate-skills/skills/research/purple-cow-audit Skill

    5★ repo

    Score product remarkability 1-10 to decide if it's worth promoting. Seth Godin's Purple Cow test. Triggers on: "is this product worth promoting", "should I promote", "product audit", "purple cow", "remarkable product", "is it remarkable", "rate this product", "product quality check", "worth my reputation", "product evaluation", "would I recommend without commission", "product remarkability score", "evaluate this affiliate product", "quality gate for promotion".

    The same file is in 1 other repository

  • Django verification

    khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-lang/django-verification Skill

    no license5★ repo

    Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

    The same file is in 4 other repositories

  • Laravel verification

    khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-lang/laravel-verification Skill

    no license5★ 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

  • Springboot verification

    khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-lang/springboot-verification Skill

    no license5★ repo

    Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

    The same file is in 7 other repositories

  • Verification loop

    khanhhuyenngo985-sys/character-scene-design-skills/skills/.archive/ECC-testing/verification-loop Skill

    no license5★ repo

    A comprehensive verification system for Claude Code sessions.

    The same file is in 8 other repositories

  • Critique

    khanhhuyenngo985-sys/character-scene-design-skills/skills/critique Skill

    no license5★ repo

    Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

  • Security review

    khanhhuyenngo985-sys/character-scene-design-skills/skills/security-review Skill

    no license5★ 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

  • Verify

    valsteen/write-code-by-hand/skills/verify Skill

    5★ repo

    Editor primitive for running exact human-selected verification commands. Use inside write-code-by-hand mode when the user asks to run tests, lint, build, format, or execute a specific command.

  • Code review

    lteawoo/skills/skills/code-review Skill

    no license5★ repo

    Perform a general code review. Use it to inspect PRs, commits, diffs, or local changes for functional bugs, regressions, security issues, performance degradation, missing tests, and maintainability risks. Apply it when the user asks for a code review, PR review, risk check, or merge-readiness assessment.

  • Commit creator

    lteawoo/skills/skills/commit-creator Skill

    no license5★ repo

    Generate Korean Conventional Commit messages from a change summary or diff. Use it when you need to write, refine, or propose commit message candidates.

  • Integration checker

    lteawoo/skills/skills/integration-checker Skill

    no license5★ repo

    Inspect the integration points between frontend, backend, database, and external APIs. Use it to detect contract mismatches, missing environment variables, broken assumptions, or setup-order issues.

  • Pull request creator

    lteawoo/skills/skills/pull-request-creator Skill

    no license5★ repo

    Structure reviewable Pull Request descriptions from a set of changes. Use it when you need purpose, change summary, validation, risks, and self-review checkpoints.

  • Structure first

    perhapsspy/project-legibility/plugins/project-legibility/skills/structure-first Skill

    5★ repo

    Use for code generation, feature work, bug fixes, refactoring, and code review when a change creates or reshapes a multi-step flow, state lifecycle, side-effect or decision ownership, cross-unit composition, or boundary contract. Also use it when an existing structural problem makes those elements hard to trace or verify. Structural change is optional. Mechanical edits, throwaway experiments, and coherent local changes stay with their current owner and focused verification.

  • Ui design rigor

    perhapsspy/project-legibility/plugins/project-legibility/skills/ui-design-rigor Skill

    5★ repo

    Review and improve existing product interfaces. Use for read-only UI critique, bounded refinement that preserves screen purpose and page-level structure, or a component or region inside an already-settled interface. Check hierarchy, grouping, interaction clarity, component behavior, accessibility cues, responsive robustness, and task completion. Skip new landing pages, dashboards, major flows or redesigns; page-level product decisions; exact mechanical edits; and standalone graphics, documents, or slides.

  • Grill me

    TommyBez/skillsboard/.agents/skills/grill-me Skill

    5★ repo

    A relentless interview to sharpen a plan or design.

    The same file is in 19 other repositories