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
mj-deving/pai-skills/skills/GitWorkflow/DeployChecklist Skill
no license0★ repoPre-deployment verification checklists customized to your stack. USE WHEN deploy checklist, pre-deploy, ready to ship, deploy verification, release checklist, go-no-go, deploy readiness, before deploying, ship it, production deploy, rollback plan, sops, secrets check, encrypted config, pre-deploy secrets.
mj-deving/pai-skills/skills/GitWorkflow Skill
no license0★ repoGit workflow and versioning — atomic commits, save point pattern, worktrees for parallel agents, commit conventions, change summaries. USE WHEN git workflow, commit strategy, branching, git conventions, commit message, worktree, parallel work, save point, git bisect, version control, how to commit, when to commit, split commits, act, local actions, test workflow, git-cliff, changelog, release notes.
mj-deving/pai-skills/skills/TDD/APITesting Skill
no license0★ repoDeclarative API testing and HTTP probing — Hurl for multi-step API workflows with assertions, httpx for concurrent endpoint discovery. USE WHEN API testing, HTTP test, endpoint testing, Hurl, httpx, REST API, API validation, request chaining, batch URL, probe endpoints, API assertions, status code check, hurl file, test API, API smoke test, endpoint probe, bulk URL check, HTTP probing, API workflow test.
mj-deving/pai-skills/skills/Utilities/Browser Skill
no license0★ repoVisual verification and browser automation via Playwright. Headless or headed Chrome. USE WHEN browser, screenshot, debug web, verify UI, troubleshoot frontend, automate browser, browse website, review stories, run stories, recipe, web automation.
mj-deving/pai-skills/skills/Utilities/n8n/n8n-validation-expert Skill
no license0★ repoInterpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities. Consult this skill whenever a validate_node or validate_workflow call returns errors or warnings — it knows which warnings are false positives and which errors need real fixes.
The same file is in 2 other repositories
mj-deving/pai-skills/skills/VisualExplainer Skill
no license0★ repoGenerate self-contained HTML pages for diagrams, diff reviews, slide decks, data tables, and visual plans. USE WHEN generate diagram, visual explanation, diff review, code review visualization, generate slides, slide deck, visual plan, project recap visualization, fact check report, web diagram, architecture diagram, flowchart HTML, data table visualization, visual documentation, render as HTML instead of ASCII, or share diagram. Replaces ASCII tables and text diagrams with interactive browser-rendered HTML.
narenaryan/agent-skills/skills/git/conventional-commits Skill
0★ repoUse when writing or validating Conventional Commits v1.0.0 messages — choosing between `!` and `BREAKING CHANGE:` footer, formatting git-trailer footers (Token-with-dashes vs `BREAKING CHANGE`), scope syntax, mapping types to SemVer bumps, prepending gender-neutral gitmoji-style icons (feat ⚡ / fix 🐛 / refactor ♻️ / docs 📝), or handling revert/multi-paragraph body rules
narenaryan/agent-skills/skills/git/git-advanced-merging Skill
0★ repoUse when resolving non-trivial merge conflicts, choosing a merge strategy, or undoing a merge — covers -X options, diff3 markers, strategy vs option, reset vs revert -m, and re-merging reverted branches
narenaryan/agent-skills/skills/git/git-bisect-forensics Skill
0★ repoUse when hunting a regression across many commits or tracing the origin of a line/function/string — covers automated bisect, skip, replay, blame -L/-C/-w, and pickaxe search (-S/-G)
narenaryan/agent-skills/skills/git/git-data-recovery Skill
0★ repoUse when commits or branches seem lost — after hard reset, force-push, branch delete, or botched rebase — to locate dangling objects via reflog and fsck before gc prunes them
narenaryan/agent-skills/skills/git/git-hooks Skill
0★ repoUse when writing, debugging, or configuring git hooks (pre-commit, commit-msg, pre-push, pre-receive, etc.) — covers firing order, arguments, exit-code effects, and core.hooksPath for team distribution
narenaryan/agent-skills/skills/git/git-rerere Skill
0★ repoUse when the same merge conflicts keep recurring across rebases or long-running integration branches — enables automatic replay of previously-recorded resolutions
narenaryan/agent-skills/skills/git/git-reset-mechanics Skill
0★ repoUse when undoing commits, unstaging files, or choosing between reset/checkout/restore — clarifies which tree each variant touches and when --hard is unsafe
narenaryan/agent-skills/skills/git/git-revisions-syntax Skill
0★ repoUse when selecting commits, ranges, or historical refs in git — covers ^, ~, .., ..., @{N}, @{time}, --not, and pickaxe content selectors
narenaryan/agent-skills/skills/git/git-rewriting-history Skill
0★ repoUse when editing past commits — amending, splitting, squashing, reordering, dropping, or bulk-rewriting history with interactive rebase or filter-repo
narenaryan/agent-skills/skills/git/git-submodules Skill
0★ repoUse when working with git submodules — cloning, updating, pinning a branch, pushing safely, branch switching that adds/removes submodules, or resolving submodule conflicts
narenaryan/agent-skills/skills/git/git-worktrees Skill
0★ repoUse when needing multiple checked-out branches simultaneously without re-cloning — review a PR while keeping WIP, per-branch build caches, or hotfix alongside feature work
frodo2647/triptych/.claude/skills/check Skill
0★ repoMilestone challenge — push back on a result before it becomes load-bearing. Runs /whats-missing first (surface unstated assumptions and gaps), then /redteam (challenge what's there). Both are calibrated against false positives — empty findings is a valid, encouraged answer when the work is sound. Fourth of five core commands (start → explore → work → check → wrap). Use at major results, before write-up, or when the user says "push back on this" / "challenge this."
frodo2647/triptych/.claude/skills/literature-review Skill
0★ repoStructured paper search and synthesis — search papers, extract key claims, build annotated bibliography, identify gaps. Use when asked to find papers, review literature, or understand a research area.
frodo2647/triptych/.claude/skills/math-in-triptych Skill
0★ repoMentor for math work in Triptych — wires sympy-mcp, desmos-mcp, show_latex, init_research, and /verifier into the canonical order, and surfaces the four pitfalls that bite first-person mathematics (type/domain check, small-case verify, counterexample-search before proof attempt, symbolic-first). Use when the user is proving, computing, manipulating algebraic expressions, working with limits/series/integrals, or any "let's prove" or "let's compute" turn.
frodo2647/triptych/.claude/skills/peer-review Skill
0★ repoStructured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.
The same file is in 4 other repositories
frodo2647/triptych/.claude/skills/verifier Skill
0★ repoDrain the verification queue — pick up unverified claims emitted by the working agent, spawn isolated verifier subagents to check them, write results back to the log. Paired with /watcher. Use with /loop 60s /verifier while the main agent is emitting claims.
BlizzardBlast/frey-skills/iterative-self-review Skill
0★ repoUse only when explicitly invoked for an issue ledger, remediation request, repeated fix-and-recheck loop, or post-review repair. Accepts code-review findings or user-specified issues, fixes them in bounded passes, compares against a resolved task/default-branch baseline, and reports scoped verification without claiming the whole repository is clean.
antonioshaman/aura-companion/.agents/skills/council-review Skill
0★ repoPerform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Telegram UX Expert, Backend/Python Expert, Brandur Leach (PostgreSQL/Alembic), systemd/VPS Deploy Expert, Simon Willison (LLM pipelines), Karri Saarinen (UI quality), Vitaly Friedman (UX quality), Kent Beck (test quality). Uses parallel subagents for deep, independent review. Produces prioritised P1/P2/P3 findings. Stack: Python 3.11+ / aiogram 3.x / SQLAlchemy sync / PostgreSQL + Alembic / OpenAI SDK via ProxyAPI.
antonioshaman/aura-companion/.agents/skills/critique Skill
0★ repoEvaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, and overall design quality with actionable feedback.
antonioshaman/aura-companion/.agents/skills/review-with-kb Skill
0★ repoCode review that cross-references changes against the knowledge base — catches known gotchas, validates compliance with recorded decisions, and flags anti-pattern violations.
eooo-io/ai-native-engineering-doctrine/examples/imported-into-project/.claude/skills/code-review Skill
0★ repoReview code for correctness, maintainability, security, performance, and test quality.
scikrikci/skills/skills/validation Skill
no license0★ repoRegister shell commands as named validation steps (like CI checks) that can be triggered and monitored to verify code quality.
The same file is in 24 other repositories
douglasborthwick-crypto/insumer-agent-skills/skills/insumer/insumer-jwks-verify Skill
0★ repoOffline ES256 verification of InsumerAPI signed responses against the public JWKS. Use when the user receives a signed attestation from /v1/attest, /v1/trust, or /v1/trust/batch and needs to verify the signature without trusting the JSON body. Covers both the JWT path (jose / PyJWT / go-jose) and the raw sig path (ES256 over the canonical attestation/trust object).
xy23d/agent-skills/skills/git Skill
0★ repo複数のgit worktreeを一括操作するスキル。worktreeの状態確認や特定コミットの検索で複数回コマンドを叩いているときに使う。 `/git worktrees [dir]` で全worktreeのブランチ・ahead/behind・未追跡ファイルを一括表示。 `/git find <hash> [dir]` で特定コミットが各worktreeに含まれるか検索。 `/git untracked [dir]` でignoredを含むgit管理外ファイル・ディレクトリを一覧表示。 `/git rebase <parent> [child]` でrebase(コンフリクト時のルールあり)。 `/git remove-worktree <branch|path>` でworktreeを削除(失敗時は自己判断で突破せずユーザー報告)。 以下のときに必ず使うこと: 「worktreeの状態を確認したい」「各ブランチのリモートとの差分を見たい」→ `/git worktrees` 「このコミットがどのブランチに入っているか調べたい」→ `/git find` 「ignoredを含むgit管理外ファイルを確認したい」→ `/git untracked` 「rebaseして」→ `/git rebase` 「worktreeを削除して」→ `/git remove-worktree`
xy23d/agent-skills/skills/persist-check Skill
0★ repoメモリにフィードバック(行動ルール・振る舞いの変更)を書き込んだ直後に呼ぶ。書き込まれた内容がセッション終了後も機械的に強制されているかを確認し、不足があればCLAUDE.md更新・フック追加・skill更新の具体的な対応を提案する。新しい行動ルールを宣言した後は必ずこのスキルを使うこと。
kjuhwa/skills-hub/skills/agent-sdk/bash-ast-permission-validator Skill
0★ repoValidate agent bash commands by parsing them into an AST (bash-parser) and evaluating each subcommand of a pipeline/&&/|| chain against an allowlist, instead of regex-matching strings.
Evidence driven claim validator
kjuhwa/skills-hub/skills/agent-sdk/evidence-driven-claim-validator Skill
0★ repoReject LLM-generated root-cause claims that aren't supported by the actual evidence dict — claim mentions "memory" but no host_metrics? mark not-validated. Uses a per-keyword evidence requirement table and outputs a confidence score.
Draft release notes from git log
kjuhwa/skills-hub/skills/agents/draft-release-notes-from-git-log Skill
0★ repoKeep a non-destructive [Unreleased] changelog draft in sync with the actual diff since the last tag, using git log + GitHub's generate-notes API.
kjuhwa/skills-hub/skills/ai/codex Skill
0★ repoOpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
Lease epoch fencing token monotonic guard
kjuhwa/skills-hub/skills/algorithms/lease-epoch-fencing-token-monotonic-guard Skill
0★ repoReject stale leader writes using a monotonic epoch/fencing token rather than just liveness checks
kjuhwa/skills-hub/skills/arch/git-tag-registry-versioning Skill
0★ repoAdd semver rollback and pinning to any git-backed asset registry (skills, prompts, commands, snippets) using namespaced annotated tags per item and per-release bundle.
Dependency check install precondition gate
kjuhwa/skills-hub/skills/automation/dependency-check-install-precondition-gate Skill
0★ repoGate a multi-step workflow behind a scripted dependency probe that emits machine-readable `INSTALL_REQUIRED:<dep>` / `INSTALL_OPTIONAL:<dep>` lines, paired with an install script that detects OS/package manager and prefers user-local (no-sudo) installs, falling back to sudo-or-manual-instructions on exit code 2.
kjuhwa/skills-hub/skills/backend/divide-by-zero-rate-guard Skill
0★ repoGuard rate/percentage calculations against zero denominators to prevent NaN from poisoning downstream metrics and serialization.
kjuhwa/skills-hub/skills/backend/init-deadline-guard Skill
0★ repoWatchdog that force-exits a Spring Boot service if startup initialization (external discovery, topic creation, warmup) does not complete within a deadline
kjuhwa/skills-hub/skills/backend/ip-allowlist-cidr-validator Skill
0★ repoValidate client IPs against user-supplied allow-lists accepting mixed notations — plain IPv4, CIDR, octet wildcards (192.168.*.*), and octet ranges (192.168.10-20.*)
Mongodb datetrunc binsize zero guard
kjuhwa/skills-hub/skills/backend/mongodb-datetrunc-binsize-zero-guard Skill
0★ repoGuard MongoDB $dateTrunc binSize against 0 when your interval may be auto/unset; coerce to 1 to avoid runtime error
Cmake cuda extension with git submodule vendoring
kjuhwa/skills-hub/skills/build-system/cmake-cuda-extension-with-git-submodule-vendoring Skill
0★ repoBuild a PyTorch CUDA extension with CMake, vendoring CUTLASS and fmt as git submodules, plus a pre-built-wheel fast path for CI via GitHub releases.
Pyproject strict ruff with per file ignores
kjuhwa/skills-hub/skills/build/pyproject-strict-ruff-with-per-file-ignores Skill
0★ repoStrict ruff config (E, F, I, S = pycodestyle errors, pyflakes, isort, security) plus targeted per-file-ignores for assert-in-tests, vendored upstream code, and infra helpers that legitimately use subprocess.
Argparse subcommand validator chain
kjuhwa/skills-hub/skills/cli/argparse-subcommand-validator-chain Skill
0★ repoStructure multi-mode CLI with nested subcommands and a composable chain of pure-function validators
kjuhwa/skills-hub/skills/cli/git-guardrails-claude-code Skill
0★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
kjuhwa/skills-hub/skills/cli/github-hmac-webhook-verify Skill
0★ repoVerify a GitHub webhook's `X-Hub-Signature-256` using HMAC-SHA-256 over the raw body with `timingSafeEqual`, with a same-length guard, prefix-masked logs on mismatch, and a 200-then-async processing pattern.
kjuhwa/skills-hub/skills/cli/gstack/browse Skill
0★ repoFast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)
kjuhwa/skills-hub/skills/cli/gstack/canary Skill
0★ repoPost-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)
kjuhwa/skills-hub/skills/cli/gstack/codex Skill
0★ repoOpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
kjuhwa/skills-hub/skills/cli/gstack/cso Skill
0★ repoChief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack) Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".
kjuhwa/skills-hub/skills/cli/gstack/design-review Skill
0★ repoDesigner's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site. (gstack)
kjuhwa/skills-hub/skills/cli/gstack/devex-review Skill
0★ repoLive developer experience audit. Uses the browse tool to actually TEST the developer experience: navigates docs, tries the getting started flow, times TTHW, screenshots error messages, evaluates CLI help text. Produces a DX scorecard with evidence. Compares against /plan-devex-review scores if they exist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to "test the DX", "DX audit", "developer experience test", or "try the onboarding". Proactively suggest after shipping a developer-facing feature. (gstack) Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".
kjuhwa/skills-hub/skills/cli/gstack/guard Skill
0★ repoFull safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)
kjuhwa/skills-hub/skills/cli/gstack/health Skill
0★ repoCode quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell linter), computes a weighted composite 0-10 score, and tracks trends over time. Use when: "health check", "code quality", "how healthy is the codebase", "run all checks", "quality score". (gstack)
kjuhwa/skills-hub/skills/cli/gstack/openclaw/skills/gstack-openclaw-ceo-review Skill
0★ repoCEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to review a plan, challenge this, CEO review, poke holes, think bigger, or expand scope.
kjuhwa/skills-hub/skills/cli/gstack/plan-ceo-review Skill
0★ repoCEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of a plan, or when the plan feels like it could be thinking bigger. (gstack)
kjuhwa/skills-hub/skills/cli/gstack/plan-design-review Skill
0★ repoDesigner's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to "review the design plan" or "design critique". Proactively suggest when the user has a plan with UI/UX components that should be reviewed before implementation. (gstack)
kjuhwa/skills-hub/skills/cli/gstack/plan-devex-review Skill
0★ repoInteractive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to "DX review", "developer experience audit", "devex review", or "API design review". Proactively suggest when the user has a plan for developer-facing products (APIs, CLIs, SDKs, libraries, platforms, docs). (gstack) Voice triggers (speech-to-text aliases): "dx review", "developer experience review", "devex review", "devex audit", "API design review", "onboarding review".
kjuhwa/skills-hub/skills/cli/gstack/plan-eng-review Skill
0★ repoEng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review", "technical review", "plan engineering review".