agentsclimarketplace

Review & quality

19,181 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

  • Laravel validation

    event4u-app/agent-config/dist/agent-src/skills/laravel-validation Skill

    19★ repo

    Use when writing validation — Form Requests, rules, custom rule objects, request-boundary design — even when the user just says 'validate this input' or 'check the request' without naming it.

  • Learning tutor

    event4u-app/agent-config/dist/agent-src/skills/learning-tutor Skill

    19★ repo

    Use when the user wants to learn a topic or verify real understanding — rapid-competence session, error drills, learning sprint, gap probe, Feynman check. Triggers 'teach me X', 'quiz me'.

  • Lint skills

    event4u-app/agent-config/dist/agent-src/skills/lint-skills Skill

    19★ repo

    Use when running the package's skill linter against all skills and rules to validate frontmatter, required sections, and execution metadata.

  • Md language check

    event4u-app/agent-config/dist/agent-src/skills/md-language-check Skill

    19★ repo

    Use BEFORE saving any .md under .augment/, dist/agent-src*/, or agents/ — scans umlauts, German function words, and German phrases outside DE:/EN: anchor blocks. Hard gate per language-and-tone.

  • Privacy review

    event4u-app/agent-config/dist/agent-src/skills/privacy-review Skill

    19★ repo

    Use when reviewing data flows, support macros, refund templates for GDPR/CCPA/HIPAA fit — regime, consent, PII redaction (email, order-id), breach triage. Triggers 'is this GDPR-safe', 'PII redact'.

  • Prompt validator

    event4u-app/agent-config/dist/agent-src/skills/prompt-validator Skill

    19★ repo

    Pre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'.

  • Readme reviewer

    event4u-app/agent-config/dist/agent-src/skills/readme-reviewer Skill

    19★ repo

    Use when reviewing a README for accuracy, usability, and alignment with the actual repository. Detects invented content, broken setup steps, and structural issues.

  • Receiving code review

    event4u-app/agent-config/dist/agent-src/skills/receiving-code-review Skill

    19★ repo

    Use when processing code review feedback (bot or human) before changing anything — triages, verifies, and pushes back with technical reasoning — even when the user just says 'fix the comments'.

  • Recursive verification

    event4u-app/agent-config/dist/agent-src/skills/recursive-verification Skill

    19★ repo

    Use to run a depth-bounded self-correction loop (attempt → critic verdict → re-attempt) as a tunable test-time compute knob — a do-and-judge specialisation, default off, capability-gated.

  • Requesting code review

    event4u-app/agent-config/dist/agent-src/skills/requesting-code-review Skill

    19★ repo

    Use when asking for a review or creating a PR — self-review first, frame the right context, test plan included — even when the user just says 'open a PR' or 'ready to merge'.

  • Review routing

    event4u-app/agent-config/dist/agent-src/skills/review-routing Skill

    19★ repo

    Use when preparing a PR description, suggesting reviewers, or flagging risk — produces owner-mapped roles plus historical bug-pattern matches from project-local YAML.

  • Skill reviewer

    event4u-app/agent-config/dist/agent-src/skills/skill-reviewer Skill

    19★ repo

    Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix recommendations.

  • Systematic debugging

    event4u-app/agent-config/dist/agent-src/skills/systematic-debugging Skill

    19★ repo

    Use on a bug, test failure, crash, or unexpected behavior — enforce reproduce → isolate → hypothesize → verify before any fix; fires even on 'this is broken' / 'quick fix'.

  • Using git worktrees

    event4u-app/agent-config/dist/agent-src/skills/using-git-worktrees Skill

    19★ repo

    Use when starting parallel work in isolation from the current branch — spawn a git worktree with ignore-safety checks and a clean test baseline — even when the user says 'try this on the side'.

  • Verify completion evidence

    event4u-app/agent-config/dist/agent-src/skills/verify-completion-evidence Skill

    19★ repo

    Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs.

  • Verify repair loop

    event4u-app/agent-config/dist/agent-src/skills/verify-repair-loop Skill

    19★ repo

    Use to iterate a change until tests/quality checks pass — bounded run→revise→re-run gated by a numeric threshold, then a judge confirms. Triggers 'iterate to green', 'keep fixing until tests pass'.

  • Adversarial review

    event4u-app/agent-config/src/skills/adversarial-review Skill

    19★ repo

    Every claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.

  • Agent security review

    event4u-app/agent-config/src/skills/agent-security-review Skill

    19★ repo

    Every claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.

  • Architecture review lens

    event4u-app/agent-config/src/skills/architecture-review-lens Skill

    19★ repo

    Use when a diff may break system boundaries, dependency direction, or cross-service contracts — fifth judge dispatched by /review-changes alongside the four standard judges.

  • Authz review

    event4u-app/agent-config/src/skills/authz-review Skill

    19★ repo

    Every claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.

  • Check refs

    event4u-app/agent-config/src/skills/check-refs Skill

    19★ repo

    Every claim machine-checked, including "zero runtime daemon" — governed skills, rules and replayable state. One contract, every host agent.

  • Code review

    event4u-app/agent-config/src/skills/code-review Skill

    19★ repo

    Use when the user says "review this", "check my code", or wants feedback on changes. Reviews for correctness, quality, security, and coding standards.

  • Contract review

    event4u-app/agent-config/src/skills/contract-review Skill

    19★ repo

    Use when reviewing a contract clause-by-clause from your party's side — buyer/seller/vendor/licensee. Triggers on 'review this contract', 'redline this MSA', 'is this clause a problem'.

  • Conventional commits writing

    event4u-app/agent-config/src/skills/conventional-commits-writing Skill

    19★ repo

    Use when writing commit messages or squash-merge titles — `feat:`, `fix:`, `chore:`, scopes, breaking changes — even when the user just says 'commit this' without naming Conventional Commits.

  • Decision review

    event4u-app/agent-config/src/skills/decision-review Skill

    19★ repo

    Use to audit a past architectural decision — did the chosen option hold up, what assumptions drifted, should the ADR be superseded? Backward review only; does not lock new choices.

  • Design review

    event4u-app/agent-config/src/skills/design-review Skill

    19★ repo

    Use when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.

  • Dpa review

    event4u-app/agent-config/src/skills/dpa-review Skill

    19★ repo

    Use when reviewing a DPA as controller or processor against GDPR Art. 28 — GREEN/YELLOW/RED gap frame, never a final call. Triggers on "review this DPA", "check this DPA".

  • Finishing a development branch

    event4u-app/agent-config/src/skills/finishing-a-development-branch Skill

    19★ repo

    Use when the feature is implementation-complete and the next step is 'ship it' — verifies, cleans up, and routes to merge/PR/park/discard — even when the user just says 'I'm done, what now?'.

  • Git workflow

    event4u-app/agent-config/src/skills/git-workflow Skill

    19★ repo

    Use when working with Git — branch naming, commit messages, PR creation, rebasing, or the code review process — even when the user says 'push this' or 'merge the branch' without naming Git.

  • Laravel validation

    event4u-app/agent-config/src/skills/laravel-validation Skill

    19★ repo

    Use when writing validation — Form Requests, rules, custom rule objects, request-boundary design — even when the user just says 'validate this input' or 'check the request' without naming it.

  • Learning tutor

    event4u-app/agent-config/src/skills/learning-tutor Skill

    19★ repo

    Use when the user wants to learn a topic or verify real understanding — rapid-competence session, error drills, learning sprint, gap probe, Feynman check. Triggers 'teach me X', 'quiz me'.

  • Lint skills

    event4u-app/agent-config/src/skills/lint-skills Skill

    19★ repo

    Use when running the package's skill linter against all skills and rules to validate frontmatter, required sections, and execution metadata.

  • Md language check

    event4u-app/agent-config/src/skills/md-language-check Skill

    19★ repo

    Use BEFORE saving any .md under .augment/, dist/agent-src*/, or agents/ — scans umlauts, German function words, and German phrases outside DE:/EN: anchor blocks. Hard gate per language-and-tone.

  • Privacy review

    event4u-app/agent-config/src/skills/privacy-review Skill

    19★ repo

    Use when reviewing data flows, support macros, refund templates for GDPR/CCPA/HIPAA fit — regime, consent, PII redaction (email, order-id), breach triage. Triggers 'is this GDPR-safe', 'PII redact'.

  • Prompt validator

    event4u-app/agent-config/src/skills/prompt-validator Skill

    19★ repo

    Pre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'.

  • Readme reviewer

    event4u-app/agent-config/src/skills/readme-reviewer Skill

    19★ repo

    Use when reviewing a README for accuracy, usability, and alignment with the actual repository. Detects invented content, broken setup steps, and structural issues.

  • Receiving code review

    event4u-app/agent-config/src/skills/receiving-code-review Skill

    19★ repo

    Use when processing code review feedback (bot or human) before changing anything — triages, verifies, and pushes back with technical reasoning — even when the user just says 'fix the comments'.

  • Recursive verification

    event4u-app/agent-config/src/skills/recursive-verification Skill

    19★ repo

    Use to run a depth-bounded self-correction loop (attempt → critic verdict → re-attempt) as a tunable test-time compute knob — a do-and-judge specialisation, default off, capability-gated.

  • Requesting code review

    event4u-app/agent-config/src/skills/requesting-code-review Skill

    19★ repo

    Use when asking for a review or creating a PR — self-review first, frame the right context, test plan included — even when the user just says 'open a PR' or 'ready to merge'.

  • Review routing

    event4u-app/agent-config/src/skills/review-routing Skill

    19★ repo

    Use when preparing a PR description, suggesting reviewers, or flagging risk — produces owner-mapped roles plus historical bug-pattern matches from project-local YAML.

  • Skill reviewer

    event4u-app/agent-config/src/skills/skill-reviewer Skill

    19★ repo

    Use when reviewing, auditing, or optimizing skills — validates against the 7 Skill Killers checklist and produces fix recommendations.

  • Systematic debugging

    event4u-app/agent-config/src/skills/systematic-debugging Skill

    19★ repo

    Use on a bug, test failure, crash, or unexpected behavior — enforce reproduce → isolate → hypothesize → verify before any fix; fires even on 'this is broken' / 'quick fix'.

  • Using git worktrees

    event4u-app/agent-config/src/skills/using-git-worktrees Skill

    19★ repo

    Use when starting parallel work in isolation from the current branch — spawn a git worktree with ignore-safety checks and a clean test baseline — even when the user says 'try this on the side'.

  • Verify completion evidence

    event4u-app/agent-config/src/skills/verify-completion-evidence Skill

    19★ repo

    Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs.

  • Verify repair loop

    event4u-app/agent-config/src/skills/verify-repair-loop Skill

    19★ repo

    Use to iterate a change until tests/quality checks pass — bounded run→revise→re-run gated by a numeric threshold, then a judge confirms. Triggers 'iterate to green', 'keep fixing until tests pass'.

  • Claim verification

    realnaka/alphaloop/skills/claim-verification Skill

    19★ repo

    核实二手信息真伪的方法论——把推文/小作文/新闻/研报/其他 AI 的结论降级为"假设",拆成原子声明,用一手源逐条验真并打标签。当用户提到 "核实/查证/验证一下"、"这个人说的对吗"、"哪些需要验证"、"小作文"、"推文/X/Twitter 说"、"别的 AI 说"、"fact-check"、"多头/空头 thesis 核验"、"消息靠谱吗"、转发一段新闻/研报/截图让你判断真假时使用。也用于投资/公司关系/技术声明的真伪判断。

  • Scope guard

    kpab/claude-fable-5-skills/skills/scope-guard Skill

    19★ repo

    Prevent Claude Fable 5 from taking unrequested actions — applying fixes when only asked to diagnose, sending or drafting messages nobody asked for, creating backup branches, or running state-changing commands on thin evidence. Use in ops/debugging sessions, shared environments, production-adjacent work, and any conversation where the user thinks out loud.

  • Melt

    paulnsorensen/easy-cheese/skills/melt Skill

    19★ repo

    Resolve git merge, rebase, or cherry-pick conflicts via a structural-merge cascade — mergiraf (AST-aware auto-resolve) → git rerere (replay remembered fixes) → kdiff3 (manual fallback). Use when conflicts exist and the user wants them resolved — phrases like "melt the conflicts", "fix the merge conflicts", "resolve the rebase conflicts", "what's conflicting after the merge", "/melt", "fix the cherry-pick", or any prompt that surfaces `<<<<<<<` markers, `CONFLICT (...)` git output, or a half-finished merge state. Use even when only one file is conflicting if the user wants the structural pass attempted before manual editing. Do NOT use for general git operations without conflicts. After `/cook` or `/cure` if a merge step blocked them; before retrying the gate that surfaced the conflict.

  • Plate

    paulnsorensen/easy-cheese/skills/plate Skill

    19★ repo

    Turn finished local work into a commit, an ordinary pull request, or a stacked pull-request chain. Use when asked to commit, save changes, open or update a PR, publish a branch, create/sync/restack/submit a PR stack, or run /plate. Owns all staging, committing, pushing, PR creation, and stack-aware mutation. GitHub inspection, review, comments, CI, issues, releases, and repository administration remain /gh.

  • Code review

    s-hiraoku/synapse-a2a/.agents/skills/code-review Skill

    no license19★ repo

    Perform structured code reviews focusing on correctness, readability, security, and maintainability. Use this skill when reviewing pull requests, evaluating code changes, or establishing review standards for a team.

  • Pr guardian

    s-hiraoku/synapse-a2a/.agents/skills/pr-guardian Skill

    no license19★ repo

    Continuously monitor a GitHub PR for merge conflicts, CI failures, and CodeRabbit review comments, then automatically fix any issues found. Polls every 5 minutes and loops until every check is green. Use this skill whenever a PR has just been created or code has been pushed to a PR branch — it should be the default follow-up action after any PR creation or push. Also trigger on: "watch this PR", "guard this PR", "monitor CI", "keep fixing until green", "PRを監視して", "CIが通るまで 直して", /pr-guardian. When a PostToolUse hook reports that a push or PR creation just happened, proactively invoke this skill to start monitoring without waiting for the user to ask.

  • Code review

    s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/code-review Skill

    no license19★ repo

    Perform structured code reviews focusing on correctness, readability, security, and maintainability. Use this skill when reviewing pull requests, evaluating code changes, or establishing review standards for a team.

  • Pr guardian

    s-hiraoku/synapse-a2a/plugins/synapse-a2a/skills/pr-guardian Skill

    no license19★ repo

    Continuously monitor a GitHub PR for merge conflicts, CI failures, and CodeRabbit review comments, then automatically fix any issues found. Polls every 5 minutes and loops until every check is green. Use this skill whenever a PR has just been created or code has been pushed to a PR branch — it should be the default follow-up action after any PR creation or push. Also trigger on: "watch this PR", "guard this PR", "monitor CI", "keep fixing until green", "PRを監視して", "CIが通るまで 直して", /pr-guardian. When a PostToolUse hook reports that a push or PR creation just happened, proactively invoke this skill to start monitoring without waiting for the user to ask.

  • Lead review

    chrisallenlane/claude-swe-workflows/skills/lead-review Skill

    18★ repo

    Autonomous comprehensive review. Once-through pipeline over /review-health, /review-arch, /review-security, /review-perf, /review-a11y, /review-test, /review-release. Operator-configurable ticket creation at startup — when ON, auto-approves sub-skill ticket proposals per the orchestrator-family contract; when OFF, uniformly declines and surfaces findings in the consolidated report. Auto-detects sub-skills that do not apply (no web content → skip /review-a11y; no tests → skip /review-test).

    The same file is in 3 other repositories

  • Review a11y

    chrisallenlane/claude-swe-workflows/skills/review-a11y Skill

    18★ repo

    Accessibility audit. Dispatches an accessibility auditor to identify WCAG conformance gaps, prioritize by user impact, and recommend fixes. Advisory only — no changes made.

    The same file is in 2 other repositories

  • Review arch

    chrisallenlane/claude-swe-workflows/skills/review-arch Skill

    18★ repo

    Architectural review workflow. Analyzes codebase organization via noun analysis and produces a target blueprint. Advisory only — does not implement changes. Always offers to cut tickets for the planned work; orchestrators receive the proposal and apply their own autonomy judgment to approve / edit / decline.

    The same file is in 2 other repositories

  • Review health

    chrisallenlane/claude-swe-workflows/skills/review-health Skill

    18★ repo

    First-pass strategic-orientation review of a repository. Produces an evidence-cited map (not a grade) calibrated to a reference class, helping the user decide where to engage, where to tread carefully, and where to leave alone. Advisory only — no changes made.

    The same file is in 2 other repositories

  • Review perf

    chrisallenlane/claude-swe-workflows/skills/review-perf Skill

    18★ repo

    Performance review. Detects project type and dispatches compute and/or web performance reviewers. Advisory only — no changes made.

    The same file is in 2 other repositories

  • Review release

    chrisallenlane/claude-swe-workflows/skills/review-release Skill

    18★ repo

    Pre-release readiness review. Scans for debug artifacts, version mismatches, changelog gaps, git hygiene issues, breaking changes, and license compliance. Runs tests and build verification. Presents consolidated findings for human review before release.

    The same file is in 2 other repositories

  • Review security

    chrisallenlane/claude-swe-workflows/skills/review-security Skill

    18★ repo

    White-box security audit. Blue-teamer and lead red-teamer run in parallel isolation for an independent first pass — neither sees the other's output during reconnaissance. A synthesis step categorizes findings into four prescriptive buckets (anchoring-suppressed, convergent, blue-flagged-unverified, divergent), producing a unified target list. Focused red-teamers then deep-dive each target. Iterates when exploit chains are discovered. Heavy and thorough by design. Advisory only — produces findings and proposes tickets; does not implement remediation.

    The same file is in 2 other repositories