agentsclimarketplace

Review & quality

19,016 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

  • Skill lint

    mifunedev/skills/skills/skill-lint Skill

    0★ repo

    Score all skills for staleness using 5 dimensions (freshness, usage, integrity, format, dependencies). Reports CURRENT/STALE/BROKEN/DELETE verdicts with specific recommendations. TRIGGER when: asked to audit skills, check skill health, "are my skills stale", "skill lint", or periodically via heartbeat.

  • Worktrees

    mifunedev/skills/skills/worktrees Skill

    0★ repo

    Manage .worktrees/ lifecycle: create worktree, list worktrees, remove worktree, clean worktrees, stale worktrees audit, isolate work, project clone. TRIGGER when: any git worktree operation, branch isolation needed, stale worktrees review, project clone under .worktrees/project/, worktree cleanup.

  • Git log analysis

    jiangyinzuo/agentic-software-engineering/git-log-analysis Skill

    no license0★ repo

    My agent harness

    The same file is in 6 other repositories

  • Plan design grill

    LoogacyStudio/skills/.agents/skills/plan-design-grill Skill

    0★ repo

    Use when a user wants a plan, proposal, architecture, rollout, or design stress-tested through relentless branch-by-branch questioning that exposes assumptions, resolves forks, and ends with a shared understanding of decisions, risks, and next steps.

  • Benchmark review candidate

    LoogacyStudio/skills/.github/skills/benchmark-review-candidate Skill

    0★ repo

    Use when a wording, routing-policy, rubric, template, or other candidate revision needs a formal promotion review against target-suite gain, protected-suite regressions, invariance, robustness, mutation-surface rules, and official-adoption governance requirements.

  • Abstraction integrity review

    LoogacyStudio/skills/plugins/godot-dotnet/skills/abstraction-integrity-review Skill

    0★ repo

    Use when a Godot/.NET task needs a Layer 4 overlay review to prevent abstraction decay during feature work, flow extension, or touched-code refactoring, especially around flag creep, boundary leakage, compatibility creep, or responsibility drift.

  • Post change review

    LoogacyStudio/skills/plugins/godot-dotnet/skills/post-change-review Skill

    0★ repo

    Use when a Godot/.NET task needs a Layer 4 overlay completion review after a large refactor, multi-file implementation, or new feature, and the agent must assess layer boundaries, engine usage, docs or content sync, and verification evidence before the work should be treated as complete.

  • Scene architecture review

    LoogacyStudio/skills/plugins/godot-dotnet/skills/scene-architecture-review Skill

    0★ repo

    Use when a Godot/.NET task needs a Layer 4 overlay architecture review of a scene, gameplay system, or UI flow specifically to assess scene composition, node responsibility, script ownership, signal boundaries, autoload fit, and UI-to-gameplay coupling, and the agent must judge maintainability seams rather than primarily evaluating readability, focus, feedback, or other UX-only concerns.

  • Test strategy review

    LoogacyStudio/skills/plugins/godot-dotnet/skills/test-strategy-review Skill

    0★ repo

    Use when a Godot/.NET task needs a Layer 4 overlay validation plan for a feature, bug fix, refactor, migration, or UI change, and the agent must separate pure .NET tests from Godot runtime-dependent coverage, prioritize the highest-risk paths first, and return a minimal test matrix plus regression guidance.

  • Ui ux review

    LoogacyStudio/skills/plugins/godot-dotnet/skills/ui-ux-review Skill

    0★ repo

    Use when a Godot/.NET task needs a Layer 4 overlay UX review for a HUD, menu, overlay, prompt flow, or tool UI, and the agent must evaluate information hierarchy, focus, interaction clarity, feedback, readability, and cognitive load before returning concrete quick wins, structural improvements, and verification ideas.

  • Version upgrade review

    LoogacyStudio/skills/plugins/godot-dotnet/skills/version-upgrade-review Skill

    0★ repo

    Use when a Godot/.NET task needs a Layer 4 overlay upgrade review that evaluates engine, SDK, C# compatibility, addons/plugins, export pipeline, verification, and rollback risk, then returns a staged sequence instead of a risky all-at-once migration.

  • Svelte review

    j13z/j13z-svelte-essentials/agent-skills/dist/svelte-review Skill

    no license0★ repo

    Use this skill when reviewing, diagnosing, restructuring, or rewriting Svelte 5 / SvelteKit frontend code, especially when bugs or complexity stem from weak architecture, poor state ownership, reactivity problems, bad component boundaries, or accumulated technical debt. This skill is diagnosis-first, skeptical, and findings-first. It should question the current solution shape before fixing it, and it may recommend or drive a parallel clean rewrite when the status quo is no longer a good foundation.

  • Svelte review

    j13z/j13z-svelte-essentials/agent-skills/src/svelte-review Skill

    no license0★ repo

    Use this skill when reviewing, diagnosing, restructuring, or rewriting Svelte 5 / SvelteKit frontend code, especially when bugs or complexity stem from weak architecture, poor state ownership, reactivity problems, bad component boundaries, or accumulated technical debt. This skill is diagnosis-first, skeptical, and findings-first. It should question the current solution shape before fixing it, and it may recommend or drive a parallel clean rewrite when the status quo is no longer a good foundation.

  • Critique chapter

    abetatos/seed-grimoire/.claude/skills/critique-chapter Skill

    no license0★ repo

    Hard, structured critique of a written chapter against the book's own contract — beat sheet, canon, shadow, seed envelope, prose anti-patterns, dwelling techniques. Produces a written critique with prioritized issues and concrete fixes. Use this after a chapter is written and before `update-canon` locks it in. Invoke as "critique chapter N".

  • Critique grimoire

    abetatos/seed-grimoire/.claude/skills/critique-grimoire Skill

    no license0★ repo

    Adversarial structural review of `output/<series>/grimoire.md` — the world grimoire. Audits the foundational worldbuilding document BEFORE `book-setup` or `plan-book` run, so that the per-book plan never inherits a flawed foundation. Use this when the user says "audita el grimorio" / "critique the grimoire" / "is the grimoire ready?" Invoke after writing or revising the grimoire, and before running `book-setup` for a new book in the series.

  • Critique plan

    abetatos/seed-grimoire/.claude/skills/critique-plan Skill

    no license0★ repo

    Hard, structured critique of a finished book plan — setup, outline, shadow, seeds, arcs, canon — against rhythm, plot, foreshadowing, magic system completeness, and worldbuilding economy. Produces a written critique (`notes/critique-plan.md`) with prioritized findings and concrete fixes. Use this after `plan-book` and before `write-chapter 1`. Invoke as "critique the plan" / "audita el planteamiento".

  • Create mr

    muhammadrivaldy/agent-skills/create-mr Skill

    no license0★ repo

    Analyze code changes and create GitHub PRs or GitLab MRs with auto-generated title and structured description. Detects platform from remote URL, analyzes git diff against target branch, determines change type/scope/breaking changes. Generates description covering: summary, motivation, key changes, breaking changes, testing, related issues, deployment notes, and checklist. Use when user asks to create a PR, MR, pull request, or merge request.

  • Git commit

    muhammadrivaldy/agent-skills/git-commit Skill

    no license0★ repo

    Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

  • Grill me

    muhammadrivaldy/agent-skills/grill-me Skill

    no license0★ 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".

  • My council

    alexleekt/agents/skills/my-council Skill

    no license0★ repo

    **ALWAYS use when user mentions:** "review council", "multi-agent review", "parallel review", "team review", "full code review", "review with experts", "spawn reviewers", "council pattern", "review all dimensions", "code review", "review this", "PR review", "check my code", "critique", "how should I write this", "raise the bar". **ALWAYS use when:** a codebase has changed >5 files or ~100+ lines, or when the user wants a thorough review across multiple dimensions (security, performance, correctness, maintainability, tests, accessibility, architecture, types, research). **DO NOT use for:** single-file quick checks, asking how a specific function works, or debugging a known bug (use the appropriate debug skill instead).

  • My semantic release

    alexleekt/agents/skills/my-semantic-release Skill

    no license0★ repo

    **ALWAYS use when user mentions:** "release", "ship it", "cut a release", "changelog", "version bump", "semver", "conventional commit". **DO NOT use for:** daily VCS operations — use git. Automates semantic versioning, changelog generation, and release workflows.

  • My vcs hygiene

    alexleekt/agents/skills/my-vcs-hygiene Skill

    no license0★ repo

    **ALWAYS use when:** the user says commit, push, stage, ship, "looking good", "done", "wrap it up", or signals completion; when making commits; when starting a session with uncommitted changes or on a dirty main branch; when the user gives visual or UX feedback during building ("move this left", "make it smaller", "change the color"). Use whenever the user mentions committing, pushing, shipping, or wrapping up work — even if they don't explicitly use git terminology. Also use when deciding commit scope, handling monorepo cross-package changes, managing visual iteration loops, or amending commits. **DO NOT use for:** worktree switching or naming — use @skills/my-workflow. Plan/build/review phases — use @skills/my-project-lifecycle. `wt` CLI mechanics — use @skills/worktrunk.

  • Engine

    technomaton/edpa/plugin/skills/engine Skill

    0★ repo

    Run EDPA evidence-driven calculation for an iteration by invoking the vendored engine script (.edpa/engine/scripts/engine.py). The engine reads the materialized evidence[]/contributors[] persisted in each item's YAML (written by the post-commit hook / /edpa:materialize — it does not scan git at compute time), computes CW from cw_heuristics, calculates Score and DerivedHours, validates invariants, and writes results JSON + XLSX + a frozen snapshot. Use when closing an iteration, computing derived hours, or running "EDPA výpočet". Produces the input for the reports skill.

  • Backend api contract review

    yangshu2087/Codex/.agents/skills/backend-api-contract-review Skill

    no license0★ repo

    Use when a task involves backend services, API routes, database writes, auth, permissions, error semantics, or service contracts.

  • Frontend design review

    yangshu2087/Codex/.agents/skills/frontend-design-review Skill

    no license0★ repo

    Use when the task involves front-end page or component design quality, Figma or screenshot translation, spacing or typography refinement, responsive behavior, UI state validation, or visual polish before merge.

  • Product ux flow review

    yangshu2087/Codex/.agents/skills/product-ux-flow-review Skill

    no license0★ repo

    Use when a task involves user experience, product flow, onboarding, conversion, user journeys, friction points, or UI acceptance criteria.

  • Requesting code review

    yangshu2087/Codex/.agents/skills/requesting-code-review Skill

    no license0★ repo

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

  • Recipe front review

    yangshu2087/Codex/vendor/skills/skilltrust-curated/codex-workflows/recipe-front-review Skill

    no license0★ repo

    Use when explicitly running a frontend review recipe against React or TypeScript UI work and the operator wants the vendored SkillTrust reference flow.

  • Lf git branch

    twinfo-io/lifters-skills/skills/lf-git-branch Skill

    no license0★ repo

    Creates a new git branch across the main repo and selected submodules. Accepts the branch name as argument or asks interactively. Lists all submodules and lets the user select all or specific ones. Creates from current HEAD or a specified base ref. Optionally pushes to remote. Shows a confirmation plan before executing. Use when starting a new feature that spans multiple submodules.

  • Lf git checkout

    twinfo-io/lifters-skills/skills/lf-git-checkout Skill

    no license0★ repo

    Switches branches across the main repo and all submodules. Accepts the branch name as argument or lists available branches interactively. Shows which submodules have the target branch vs which will be aligned via git submodule update. Detects uncommitted changes and offers stash per submodule. Confirms before executing. Use when switching feature branches in a monorepo with submodules.

  • Lf git push

    twinfo-io/lifters-skills/skills/lf-git-push Skill

    no license0★ repo

    Pushes commits safely in the correct order: submodules first, then the main repo. Checks which repos have unpushed commits, shows a push plan with the commit list per repo, confirms before executing, and stops immediately on failure to avoid broken references in the remote. Use instead of pushing manually to prevent 'submodule not pushed' errors on the main repo.

  • Lf git status

    twinfo-io/lifters-skills/skills/lf-git-status Skill

    no license0★ repo

    Consolidated git status view across the main repo and all submodules. Shows branch, ahead/behind remote, and dirty/clean state for every repo in a single scannable report. Flags issues: detached HEAD, local-only commits, diverged branches, and pointer mismatches between main repo and submodules. Use instead of running git status in each submodule manually.

  • Lf git sync

    twinfo-io/lifters-skills/skills/lf-git-sync Skill

    no license0★ repo

    Pulls and synchronizes all git submodules with their remotes. Detects the git root, lists all submodules, pulls the main repo, then for each submodule: pulls if on a tracked branch or runs git submodule update if in detached HEAD state. Handles merge conflicts, network errors, and missing remotes gracefully. Shows a before/after summary with branch and commit state per repo. Use when you need to sync a monorepo with submodules after a teammate pushed changes.

  • Lf push

    twinfo-io/lifters-skills/skills/lf-push Skill

    no license0★ repo

    Pushes the current branch and creates or updates a PR against the project's base/staging branch (auto-detected, overridable), filling the body from the repo's PR template if present — falling back to a minimal template otherwise — with type/ticket already resolved, and automatically comments the PR link on the linked issue-tracker ticket (Linear or GitHub Issues) once the PR is created. Always confirms before pushing or creating/updating the PR. Use when the user asks to push the branch, open a PR, or says something like 'push this'/'abre o PR'. If there are uncommitted changes, suggests /lf-commit first.

  • Stripe webhook validation

    javicasper/memory-forge/examples/monorepo/apps/payments/.claude/skills/stripe-webhook-validation Skill

    0★ repo

    Fix for Stripe webhook signature validation failures in the payments app. Use when: "Stripe webhook signature verification failed", "Invalid signature", "No signatures found matching the expected signature", webhook 400 errors. Only loads when working in apps/payments/.

  • Git commit

    RileyCornelius/Code-Skills/skills/git-commit Skill

    0★ repo

    Generate well-structured git commit messages with a standard subject line and optional description. Use when committing staged changes, writing commit messages, or when the user asks to commit.

  • Git worktrees

    RileyCornelius/Code-Skills/skills/git-worktrees Skill

    0★ repo

    Create or manage isolated git worktrees for parallel feature work, experiments, reviews, or bug fixes without disturbing the current checkout. Use when the user wants a separate workspace or branch, asks to isolate work before implementation, or when working in the current tree risks conflicts or mixing unrelated changes.

  • Rebased

    dupe-com/skills/skills/rebased Skill

    0★ repo

    Rebase the current branch onto origin/main and intelligently resolve any conflicts that arise. Use when the user invokes /rebased or asks to rebase the current branch on main and resolve conflicts.

  • Architecture review

    lx-wnk/skills/skills/architecture-review Skill

    0★ repo

    Review system-level architecture of a PR, branch, namespace, or whole project — boundary violations, dependency cycles, layer breaches, ADR compliance, cohesion of modules and bounded contexts. Make sure to use this skill whenever the user asks to review the architecture, audit module boundaries, check for circular dependencies, verify domain structure, or says things like "architektur-review", "prüfe die struktur", "check architecture", "review namespace", "audit boundaries", "are our modules clean". Use this skill for HIGH-LEVEL structural review only — SOLID, class design, and method-level issues belong in `component-review`.

  • Branch review

    lx-wnk/skills/skills/branch-review Skill

    0★ repo

    Multi-agent code review EXCLUSIVELY of the diff between the current branch and a base branch (default main) — not a whole-repo audit, only diff-touched areas. Spawns parallel subagents for code quality, architecture, security (OWASP/CWE/CVSS), SEO, privacy/legal, UI/UX (WCAG), and performance, consolidated into a P0–P4 Findings.md. Optional `--apply-fixes` applies clear fixes and a `/simplify` pass behind a test/lint gate (`--no-simplify` opts out), and escalates design decisions. Use for "review this branch", "PR review", "diff review", "branch review", "review my PR", "review what changed", or German "review meinen branch", "review die änderungen", "schau dir den branch an", "PR-Review" — whenever a PR link, branch range, or diff is posted, even without the word "review" if context is clear. DO NOT trigger for a whole-project audit without branch context — use full-project-review. DO NOT trigger for several or all open PRs ("review my PRs", "fix PR issues", "alle PRs prüfen") — use review-and-fix.

  • Component review

    lx-wnk/skills/skills/component-review Skill

    0★ repo

    Review low-level component and class design — SOLID, cohesion, pattern correctness, interface design, method contracts, aggregate integrity, and domain-model health inside a PR, branch, namespace, or module. Make sure to use this skill whenever the user asks to review class design, check SOLID, audit a component, check if a pattern is used correctly, or says things like "component review", "class review", "prüfe das klassen design", "are these classes clean", "review the service", "solid check". Use this skill for DETAIL REVIEW only — module boundaries and dependency structure belong in `architecture-review`.

  • Full project review

    lx-wnk/skills/skills/full-project-review Skill

    0★ repo

    Comprehensive multi-agent audit of the ENTIRE project (all repos / full HEAD state). Spawns parallel subagents for code quality, architecture, security (OWASP/CWE/CVSS), SEO, privacy/legal, UI/UX (WCAG), and performance, and consolidates their reports into a complete Findings.md with P0–P4 prioritization and reasoned recommendations. Use this skill for "review the entire project", "full project audit", "audit the codebase", "comprehensive review", "code audit", "security audit", "compliance audit", "review everything", "DSGVO audit", "OWASP audit", or German equivalents "vollumfängliches review", "review das ganze projekt", "audit das projekt", "kompletter code-audit", whenever a systematic audit without branch/diff context is requested — even when no changes are pending, no PR exists, or the branch is empty. PR/diff status is NOT a blocker. DO NOT trigger when only branch changes should be reviewed — use branch-review for that.

  • Branch name

    neumie/almanac/skills/git/branch-name Skill

    0★ repo

    Use when naming or renaming the current git branch from its contents. Triggers: name this branch, rename branch, or working on default branch (main) with uncommitted work.

  • Commit

    neumie/almanac/skills/git/commit Skill

    0★ repo

    Use when committing changes. Analyzes diff, writes a conventional commit message, commits immediately without confirmation. Triggers: commit, save my work, done with this change.

  • Commits squash

    neumie/almanac/skills/git/commits-squash Skill

    0★ repo

    Use when squashing commits on the current branch into fewer logical commits. Triggers: squash, clean up commits, combine commits, tidy history before push or PR.

  • Pr create

    neumie/almanac/skills/git/pr-create Skill

    0★ repo

    Use when creating a GitHub pull request. Pushes branch if needed, generates title + description from commits, creates PR via gh CLI. Triggers: create/open/submit PR.

  • Rebase

    neumie/almanac/skills/git/rebase Skill

    0★ repo

    Use when rebasing the current branch onto main or another base. Auto-detects base, handles conflicts, supports squashing. Triggers: rebase, sync with main, clean history before PR.

  • Code review

    neumie/almanac/skills/other/code-review Skill

    0★ repo

    Use when reviewing changes since a fixed point (branch, commit, tag, or PR base). Runs independent behavior, architecture, security, and verification/operations reviews.

  • Grill me

    neumie/almanac/skills/productivity/grill-me Skill

    0★ repo

    Use when stress-testing a plan, design, or architecture through relentless questioning. Walks each branch of the decision tree one question at a time; hand the resolved decisions to /spec-create to persist.

  • Grill with docs

    neumie/almanac/skills/productivity/grill-with-docs Skill

    0★ repo

    Use when stress-testing a plan against the existing domain model + decisions. Challenges terminology, cross-references code, updates CONTEXT.md and ADRs inline as decisions crystallize.

  • Session recap

    neumie/almanac/skills/productivity/session-recap Skill

    0★ repo

    Use when summarizing the current branch or session. Gathers git log, diff, branch, PR status, uncommitted changes. Triggers: recap, catch me up, what did I do, where was I.

  • Test case formatter

    jovd83/test-design-orchestrator/test-case-formatter Skill

    0★ repo

    Compatibility bridge for the old test-design-orchestrator formatter entrypoint. Prefer the standalone `test-artifact-export-skill` skill for formatting existing test cases, BDD/TDD/plain-text rendering, and tool-export artifacts.

  • Python modernize

    albedo-c/custom-skills/skills/python-modernize Skill

    no license0★ repo

    Comprehensively modernize a Python project — upgrade Python version (EOL awareness, 3.14 free-threaded/no-GIL guidance), migrate to uv + pyproject.toml (PEP 621) + ruff, modernize Docker (multi-stage, slim-bookworm, non-root), and run security/vulnerability audits (pip-audit, bandit, trivy). Use when user asks to "modernize Python", "upgrade Python version", "migrate to uv", "set up ruff", "fix Docker", "security audit", "check vulnerabilities", or "PEP 621".

  • Grill

    aylee/agent-os/.agents/skills/grill Skill

    0★ repo

    Relentlessly but constructively interview the user when they say “grill me,” “grill this,” or ask to stress-test a plan, design, decision, or proposal. Resolve one material decision at a time before implementation.

  • Weekly review

    aylee/agent-os/.agents/skills/weekly-review Skill

    0★ repo

    Run the deliberate weekly review ritual when the user explicitly invokes it. Persist a durable review, reconcile priorities and commitments, and preserve history without depending on Git or deleting source records.

  • Code review agent

    TheWatcher01/skills/.claude/skills/code-review-agent Skill

    0★ repo

    Systematic AI-powered code review. USE when: reviewing PRs, auditing code quality, checking for security vulnerabilities, validating architecture, analyzing Rust/Python/JS/TS code, reviewing config files, or when the user says "review this code", "check this PR", "find bugs", "is this code safe". Covers: security (OWASP), performance, maintainability, correctness. Optimized for fast review with Haiku 4.5.

  • Commit

    TheWatcher01/skills/.claude/skills/commit Skill

    0★ repo

    Quick commit and push with minimal, clean messages

  • Data freshness check

    TheWatcher01/skills/.claude/skills/data-freshness-check Skill

    0★ repo

    Systematic verification of data accuracy and freshness during web research. Use when gathering factual data about organizations, legal entities, statistics, regulations, or any factual claims. Ensures every fact is sourced, timestamped, and cross-referenced. Triggers on: researching organizations, verifying legal/fiscal data, compiling dossiers, auditing existing data, any task involving factual claims from web sources.

  • Differential review

    TheWatcher01/skills/.claude/skills/differential-review Skill

    0★ repo

    Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.

    The same file is in 4 other repositories

  • Fp check

    TheWatcher01/skills/.claude/skills/fp-check Skill

    0★ repo

    Systematically verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug.

    The same file is in 1 other repository