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
lhbsaa/apex-discovery/skills/using-git-worktrees Skill
0★ repoUse 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
Verification before completion
lhbsaa/apex-discovery/skills/verification-before-completion Skill
0★ repoUse 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
lhbsaa/apex-discovery/skills/verification-loop Skill
0★ repoA comprehensive verification system for Claude Code sessions.
govza/gtd-skills/skills/weekly-review Skill
0★ repoRun the GTD weekly review — get clear, get current, get creative.
menot-you/n-soul/skills/review Skill
0★ repoPerform an adversarial, read-only review of the actual candidate against its base, contracts, tests, safety, and rollback.
zl3311/alpha-mining/.cursor/skills/cloud-review Skill
0★ repoOn-demand review orchestrator for both cloud agent runs and local manual sessions. Aggregates recent sessions, reads traces/transcripts, identifies lessons to promote to the knowledge base. Trigger on: review sessions, review cloud runs, review local sessions, session review, audit sessions, what did the agent do, weekly review.
blakebauman/skillist-validator/skills/skill-validation Skill
0★ repoValidate agent skills against the Agent Skills specification (agentskills.io) — SKILL.md frontmatter, name and description rules, character limits, directory layout, bundled file references, and progressive disclosure. Use when the user asks to validate, lint, check, or verify a skill or a directory of skills; when they ask whether a SKILL.md is spec-compliant or why a skill fails to load; before publishing or packaging skills; or when they are debugging a skill that an agent will not pick up. Applies to skills for any client — Claude Code, Cursor, Codex CLI, Gemini CLI — not just Claude.
rolson24/cad-sim-agent-skills/skills/cad-sim-project-intake Skill
0★ repoStep 1 of the reset CAD workflow. Use first when the user gives a rough product, CAD part, robotics, electromechanical, fixture, simulation, optimization, or software-connected hardware prompt and Codex must grill the user before authoring. Produces the run root, source boundary when needed, open questions, captured answers, autonomy-after-grill contract, maturity/analysis/external-capability envelopes, prototype handoff intent, primary_outcome_surface intent, project_brief.yaml review_contract, next_action_worthiness, stage_frontier, design/option-space coverage, and exemplar_calibrated_handoff intent, and review_rubric. Also use in narrow surface re-intake mode when a review loop cannot infer audience, depth, decision target, or tradeoff priority for an existing primary outcome surface. After initial intake, use cad-sim-design-orchestrator; do not revise an existing annotation_view except to update intake/review-contract state during surface re-intake.
rolson24/cad-sim-agent-skills/skills/cad-sim-quality-harness Skill
0★ repoInternal reset CAD helper for bootstrapping and auditing project-specific Quality Harness rows before serious CAD, simulation, optimization, prototype handoff, A+ review, or repeated fuzzy complaints. Use when intake, design orchestration, review/revise, reviewer lenses, or tooling scout need a small falsifiable evidence contract in quality/quality_harness.yaml, quality_harness_results.json, quality_harness_trace.md, or a Quality Reset seed.
rolson24/cad-sim-agent-skills/skills/cad-sim-rehearsal-agent Skill
0★ repoAct as a bounded smoke rehearsal operator for the reset experiment. Use for fresh-folder bootstrap rehearsals, global skill availability checks, front-door CAD intake, user grill answer, brief, CAD handoff, build/use readiness, autonomy-envelope or maturity-ladder behavior, reviewer-thread topology checks, and review-revise flow without launching solvers, optimization, old-project workers, or migration.
rolson24/cad-sim-agent-skills/skills/cad-sim-review-revise-loop Skill
0★ repoReview and revise an existing current engineering candidate until a validated route is reached. Use after intake and first authoring have produced handoff.json plus one canonical annotation_view; also use for reviewer feedback, evidence closure, maturity promotion, and fuzzy dissatisfaction such as continue, not convincing, links are not enough, or still weird.
rolson24/cad-sim-agent-skills/skills/cad-sim-reviewer-lenses Skill
0★ repoReview a current CAD, robotics, electromechanical, simulation, optimization, software-connected hardware, or engineering handoff packet and make one independent route-bearing judgment. Use when cad-sim-review-revise-loop launches the main reviewer; do not use for authoring or design repair.
Cad sim threaded rehearsal workflow
rolson24/cad-sim-agent-skills/skills/cad-sim-threaded-rehearsal-workflow Skill
0★ repoEnd-to-end reset CAD rehearsal launcher. Use instead of manually invoking cad-sim-project-intake, cad-sim-design-orchestrator, and cad-sim-review-revise-loop when the user wants a fresh-folder controller workflow with either a newly launched or already-current controller/monitor thread, Rehearsal Agent, one Meta-Agent, intake grill and simulated answers, first design pass, review/revise loop with separate reviewer thread(s), and optional post-hoc comparator. Use this for role-separation, global-skill bootstrap, raw-Codex-like autonomy, maturity-ladder, or comparator rehearsals; use the individual skills for a real project run in the same thread.
Daotin/dt-workflow/skills/dt-dev-review Skill
0★ repo轻量 AI 开发工作流:6 个 agent skill + 每项目几个 markdown,零 CLI 依赖、零 hook、零注入税。A lightweight AI dev workflow as agent skills — one hard gate, zero per-project scaffolding.
ProstDev/skills/plugins/dev/skills/accessibility-review Skill
0★ repoReview, audit, or fix the accessibility of web UI — HTML, CSS, JS/JSX, or any component that renders a visible or interactive surface. Use when the user asks to check accessibility / a11y / WCAG / ARIA compliance, or mentions screen readers, keyboard navigation, color contrast, focus management, or making something usable for people with disabilities. Covers ~30 WCAG 2.2 Level A & AA success criteria with detection and remediation guidance.
ProstDev/skills/plugins/dev/skills/commit-and-push Skill
0★ repoCommit whatever is currently staged (if anything) and push. Use when the user says "commit and push", "ship it", or similar. Pushes even when there's nothing new to commit, so it also ships already-made local commits. Does not stage anything. For commit-only, use commit.
ProstDev/skills/plugins/dev/skills/commit Skill
0★ repoCommit whatever is currently staged — commit only, no push. Use when the user says "commit", "commit this", "commit the staged changes". Does not stage anything and does not push. For committing AND pushing, use commit-and-push instead.
martonpaulo/skills/grill-and-document Skill
0★ repoStart a focused one-question-at-a-time interview that also preserves resolved domain vocabulary and genuinely consequential architectural decisions without creating tickets or implementing the plan.
martonpaulo/skills/grill Skill
0★ repoStart a focused one-question-at-a-time interview to pressure-test a plan or design without creating documentation or implementing it.
martonpaulo/skills/resolve-conflicts Skill
0★ repoResolve an in-progress Git merge, rebase, or cherry-pick conflict by reconstructing the intent of both sides, preserving compatible behavior, and validating the resulting code and history.
gitt510/agent-skills/skills/github-pr-reply-guard Skill
0★ repoOperational guard against replying to the wrong thread when responding to GitHub PR review comments. Use when replying to review comments, reporting fixes, or resolving threads — especially when a comment URL and comment ID are involved: confirm the ID from pulls/:pr/comments and verify in_reply_to_id after replying. Also covers the GraphQL fallback for when a pending review makes the REST reply API fail.
gitt510/agent-skills/skills/ponytail-review Skill
0★ repoCode review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.
gitt510/agent-skills/skills/publish-pr Skill
0★ repoPublish the current local changes to GitHub in one shot — confirm scope, commit, push, and open a ready pull request. Use whenever the user wants to ship finished local work to a PR ("open a PR for this", "publish this", "commit, push, and PR", "ship it"), even when the ask is terse, as long as there are local changes meant to go up. This is git + PR mechanics only: it does NOT merge (stop at opening the PR) and does NOT run tests/build/lint (correctness is a separate concern — see the boundary notes below).
gitt510/agent-skills/skills/weed-comment Skill
0★ repoRemove context-leak prose from comments and docstrings in AI-agent-written code: edit-history narration, reviewer-directed self-justification, session references, redundant code restatement, and commented-out code. Preserve durable contract documentation, constraints, non-obvious rationale, business rules, TODO/FIXME, and tool directives. Use after an agent coding session, before committing agent-written changes, when a diff review flags comment noise, or when the user says "clean up the comments", "remove AI comments", "comment slop", "コメント整理して", "コメント抜いて", or invokes /weed-comment. Edit comments and docstrings only; never change executable code or perform a general simplify pass.
ridermw/my-skills/skills/plan-exit-review Skill
0★ repoPortable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.
ridermw/my-skills/skills/plan-mega-review Skill
0★ repoPortable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.
VJDiPaola/skill-forge/git-workflows Skill
0★ repoGit beyond the basics: interactive rebase, bisect, history surgery, recovering lost work, and untangling messy branch states. Use when the user asks to clean up commits before a PR, find which commit broke something, undo a bad merge or rebase, split or combine commits, recover deleted work, or fix a detached HEAD. Trigger on rebase, bisect, cherry-pick, reflog, squash, amend, force push, or I messed up my branch.
VJDiPaola/skill-forge/scrutiny-feature-reviewer Skill
0★ repoCode review for a single feature during mission validation. Used only within missions. Use when a mission requires per-feature code review during validation.
VJDiPaola/skill-forge/user-testing-flow-validator Skill
0★ repoTest validation contract assertions through designated contract surfaces during mission validation. Used only within missions. Use when a mission requires validation contract assertions to be tested.
014-code/agent-skill-doctor/tests/fixtures/repo/alpha-review Skill
0★ repoUse this skill when asked to review a small service and summarize its important modules.
kevinb361/agent-skills/skills/review Skill
no license0★ repoPerform a read-only review of code changes for concrete bugs, security risks, regressions, performance problems, and missing tests. Use for staged, unstaged, commit, branch, or pull-request diffs.
kevinb361/agent-skills/skills/security-review Skill
no license0★ repoReview a change or subsystem using an explicit threat model. Use for authentication, authorization, untrusted input, secrets, external services, filesystem access, deployment, or other security-sensitive surfaces.
kevinb361/agent-skills/skills/verify-before-complete Skill
no license0★ repoRequire fresh, task-relevant evidence before claiming work is complete, fixed, passing, deployable, or ready to merge. Use at completion and release checkpoints.
stella-dust/autoxeo-marketplace/skills/autoxeo-quality-gate Skill
0★ repoGEO Quality Gate skill for validating generated or edited content before publishing, with section-level AI citation readiness checks.
jpoindexter/product-management-skills/skills/product-review Skill
0★ repoRun a structured review of a product bet, initiative, roadmap, launch, or evidence packet and return a decision with gaps and next actions. Use when the user asks for critique, a product review, a go/no-go decision, an executive review, or an audit across value, usability, feasibility, viability, evidence, and operations.
mrevjd/claude-review-suite/skills/review-go Skill
no license0★ repoUse when reviewing or auditing Go code - .go files, a go.mod module, "review this Go service", "check this handler before I merge", "audit this package" - covering nil dereference after an error, unchecked type assertions, goroutine and context leaks, SQL built by string concatenation, defer inside loops, ignored errors, and data races on shared state.
mrevjd/claude-review-suite/skills/review-php Skill
no license0★ repoUse when reviewing or auditing PHP code - .php files, a composer.json project, "review this PHP app", "audit this endpoint", "check this before I deploy" - covering superglobal data flow into sinks, unserialize on untrusted input, local and remote file inclusion, weak session configuration, SQL built by concatenation, and missing output escaping.
mrevjd/claude-review-suite/skills/review-vue-ts Skill
no license0★ repoUse when reviewing or auditing Vue or TypeScript front-end code - .vue, .ts or .tsx files, "review this component", "audit this front end", "look over this store before I merge" - covering v-html and innerHTML XSS sinks, missing CSRF handling on fetch, secrets shipped in the client bundle, unvalidated props crossing trust boundaries, prototype pollution, and any masking type errors.
mrevjd/claude-review-suite/skills/security-review Skill
no license0★ repoUse when the user asks whether code is safe or wants it audited for security - "security review", "audit this", "check for vulns", "is this exploitable", "any injection risk here", "threat model this endpoint" - covering authentication, authorisation, injection, secret handling, crypto, deserialisation, SSRF, and sensitive data exposure.
YZYY95K/test/skills/pr-reviewer Skill
no license0★ repoReview a tested candidate for correctness, security, scope, and approval policy. Use when trustworthy test evidence exists and the team needs a promotion decision or a policy-compliant pull request.
wdyt-page/skills/skills/wdyt-review Skill
0★ repoCollaborate through an existing wdyt.page review by reading comments and drawings, downloading current HTML, applying requested changes, replying precisely, waiting for human review, and uploading complete replacement versions to the same link. Use whenever the user provides a WDYT review URL or asks to act on WDYT feedback.
hashirventhodi/taskforge-skills/taskforge-review Skill
0★ repoIndependently review a taskforge task's implementation against its Specification and emit only the verdict — the review half of the split run workflow (docs/ADR-0001 Phase 6). Use when a task's readiness is "review" (an implementation awaits review). Runs in fresh context against the recorded reviewer prompt; produces one review artifact (approved, or rejected with a root_cause). The KERNEL routes on the verdict (approved -> done, rejected -> refine/explore/retry) — the review never emits a done or escalate signal.
hashirventhodi/taskforge-skills/taskforge-run Skill
0★ repoImplement a taskforge task against its active Specification and verify it with an independent fresh-context review subagent. Use when a task's readiness is "run", or when the user asks to run, implement, execute, build, or ship a taskforge task that has a specification. Covers the implement-review-retry loop, recorded-and-auditable reviewer isolation, root-cause escalation back to taskforge-refine or taskforge-explore, and scope discipline (out-of-scope discoveries become follow-up tasks). Tasks without an active specification route to taskforge-refine instead.
Flowxtra/career-agent/.agents/skills/verify-companies Skill
0★ repoUse when auditing the curated ATS rosters for stale entries, pruning dead boards or tenants, promoting candidates from unverified/ into internal/provider/*/companies.yaml, or when search_jobs_by_company errors on a company that used to work.
lubochka/xiigen-mvp-engine/.agents/skills/api-shape-verification Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/audit Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Conversation intent and self reflection
lubochka/xiigen-mvp-engine/.agents/skills/conversation-intent-and-self-reflection Skill
0★ repoClassify the CURRENT message before acting. Prevents six soft failures that the existing Critique-Response Protocol in agent-constitution does NOT catch on its own: answering direct questions late, defensive freeze, defensive self-reflection, action-as-relief drift, attention-budget drift, and entropy tolerance. Extends — does not replace — agent-constitution (Critique-Response, Session Start/End) and authority-chain (binding authority). Use before architect planning, plan review, governance/protocol/skill repair, sub-agent orchestration, or any response to a "why / where / who allowed / why shallow / return to analysis" message.
lubochka/xiigen-mvp-engine/.agents/skills/defense-in-depth Skill
0★ repoValidate at every layer data passes through to make bugs impossible
The same file is in 2 other repositories
lubochka/xiigen-mvp-engine/.agents/skills/dna-compliance-guard Skill
0★ repo9 DNA guard patterns for the XIIGen engine. Each pattern has a detection command, example violation, fix pattern, and test template. Run pre-commit on any new or modified TypeScript files.
lubochka/xiigen-mvp-engine/.agents/skills/plan-review-skill Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/self-verification Skill
0★ repoSelf-verification discipline for the XIIGen engine. 6 rules ensuring that fixes and changes are validated at the correct test level, with real fixtures, and with full cascade awareness before being declared done.
lubochka/xiigen-mvp-engine/.agents/skills/three-level-verification Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Verification before completion
lubochka/xiigen-mvp-engine/.agents/skills/verification-before-completion Skill
0★ repoRun verification commands and confirm output before claiming success
The same file is in 1 other repository
lubochka/xiigen-mvp-engine/.claude/skills/universal/claim-verification Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Conversation intent and self reflection
lubochka/xiigen-mvp-engine/.claude/skills/universal/conversation-intent-and-self-reflection Skill
0★ repoClassify the CURRENT message before acting. Prevents six soft failures that the existing Critique-Response Protocol in agent-constitution does NOT catch on its own: answering direct questions late, defensive freeze, defensive self-reflection, action-as-relief drift, attention-budget drift, and entropy tolerance. Extends — does not replace — agent-constitution (Critique-Response, Session Start/End) and authority-chain (binding authority). Use before architect planning, plan review, governance/protocol/skill repair, sub-agent orchestration, or any response to a "why / where / who allowed / why shallow / return to analysis" message.
lubochka/xiigen-mvp-engine/.claude/skills/universal/multi-reviewer-design Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.claude/skills/universal/plan-review Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.claude/skills/universal/plan-self-validation Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Subproject completeness checker
lubochka/xiigen-mvp-engine/.claude/skills/universal/subproject-completeness-checker Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Verification before completion
lubochka/xiigen-mvp-engine/.claude/skills/universal/verification-before-completion Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.