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
Dependency supply chain review
nledford/engineering-review-board/skills/dependency-supply-chain-review Skill
0★ repoDependency and software supply-chain security review. Use for dependency audits, SBOM/SCA output, CVE/GHSA advisories, package or binary provenance, registry trust, manifests, lockfiles, checksums/signatures, install/postinstall scripts, vendored/generated code, transitive dependency risk, CI actions, container or base-image pinning, or package-manager security policy. Do not use for routine package-manager workflow, language-specific dependency implementation, or third-party API docs without a supply-chain risk question.
nledford/engineering-review-board/skills/git-commit Skill
0★ repoWrite high-quality git commits and commit messages. Use when the user asks to commit changes, split a working tree into logical commits, improve commit messages, prepare reviewer-friendly new commits, or apply Conventional Commits guidance in any plain git repository. Do not use for amend/fixup/autosquash, branch operations, integration, recovery, push, tags, or worktrees; use git-workflows.
nledford/engineering-review-board/skills/git-workflows Skill
0★ repoSafe Git branch, remote, history-inspection, integration, rewrite, conflict, recovery, tag, and worktree workflows. Use when switching or restoring, fetching/pulling/pushing, managing upstreams or remotes, inspecting history with log/blame/bisect, merging/rebasing/squashing/cherry-picking/reverting/resetting, resolving conflicts, recovering with reflog, or managing tags and worktrees. Do not use for commit grouping or message drafting, checked-in CI/release automation, code review, GitHub pull-request operations, or release-readiness decisions.
nledford/engineering-review-board/skills/performance-review Skill
0★ repoReview performance and scalability using workload, baseline, profiling, query-plan, rendering, concurrency, and resource evidence. Use for bottleneck audits, benchmark plans, capacity risks, or performance-sensitive changes; do not use for active unexplained regressions or implementation mechanics alone.
nledford/engineering-review-board/skills/prompt-engineering-review Skill
0★ repoReview and improve prompts and bounded agent-system instruction interfaces for Codex, OpenCode, Weave, Claude, and other coding agents. Use for prompt audits, rewrites, multi-agent roles, delegation and handoff contracts, acceptance criteria, and quality gates; do not use for application implementation, runtime architecture audits, or reusable SKILL.md authoring.
nledford/engineering-review-board/skills/review-verification-protocol Skill
0★ repoMandatory evidence gates for review findings. Load with code-review and any specialist review skill before reporting findings, or read/apply manually if the runtime hides this skill.
nledford/engineering-review-board/skills/rust-code-review Skill
0★ repoReview Rust code with Rust-specific rigor. Use with code-review when changes touch Rust ownership, lifetimes, traits, error contracts, crate boundaries, feature flags, tests, Rustdoc, async, Tokio, Axum, Leptos, SQLx, SeaQuery, SeaORM, Diesel, SQLite, unsafe code, macros, FFI, public APIs, design patterns, anti-patterns, or performance-sensitive behavior. Use sql-engineering, postgresql-sql-engineering, or sqlite-sql-engineering too for database-native schema, SQL, migrations, privileges, or query plans.
nledford/engineering-review-board/skills/rust-testing-quality Skill
0★ repoRust testing and quality-gate guidance. Use when writing, updating, running, filtering, or reporting Rust unit, integration, end-to-end, property-style, compile-fail, or Rustdoc tests; when applying TDD or BDD to Rust changes; or when using cargo fmt, cargo check, cargo test, cargo test --doc, cargo clippy, cargo-nextest, Bacon/bacon.toml feedback loops, and CI-oriented Rust validation. Do not use for checked-in hosted CI/release-provider configuration except the Rust commands and test lanes it invokes; use ci-release-engineering.
nledford/engineering-review-board/skills/security-review-evidence Skill
0★ repoCompanion evidence checklist for security-sensitive changes and reviews. Use only with security-review, threat-modeling, or dependency-supply-chain-review to keep evidence sanitized, scoped, and tied to repository policy. Do not use as standalone security analysis.
nledford/engineering-review-board/skills/security-review Skill
0★ repoSecurity review and audit guidance for concrete code, config, docs, and command-surface changes. Use when implemented changes touch authentication, authorization, crypto, certificates, tokens, signatures, secrets, passwords, sessions, session cookies, CORS, CSP, CSRF, OAuth/OIDC/SAML, redirect/callback handling, input validation, file paths, command execution, or other trust boundaries. Pair with code-review for review findings; use threat-modeling for design-time boundary analysis and dependency-supply-chain-review for supply-chain-specific review.
nledford/engineering-review-board/skills/ux-accessibility-review Skill
0★ repoReview UI and UX quality, visual polish, responsive behavior, interaction states, and WCAG accessibility. Use for focused interface audits of existing products or changes; do not use as the primary styling, frontend implementation, or browser-test workflow.
mustafa3252/vibe-ship-skills/skills/ship-it-check Skill
0★ repoA final pre-push checklist for vibe coders: tests, secrets, docs, rollback, and screenshots.
381487190/opengod/skills/real-engineering/engineering/code-review Skill
0★ repoReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
The same file is in 12 other repositories
381487190/opengod/skills/real-engineering/engineering/grill-with-docs Skill
0★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
The same file is in 19 other repositories
381487190/opengod/skills/real-engineering/engineering/prototype Skill
0★ repoBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
The same file is in 6 other repositories
381487190/opengod/skills/real-engineering/engineering/resolving-merge-conflicts Skill
0★ repoUse when you need to resolve an in-progress git merge/rebase conflict.
The same file is in 11 other repositories
381487190/opengod/skills/real-engineering/in-progress/batch-grill-me Skill
0★ repoA relentless interview that asks every frontier question at once, round by round.
The same file is in 3 other repositories
381487190/opengod/skills/real-engineering/misc/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.
The same file is in 18 other repositories
381487190/opengod/skills/real-engineering/misc/setup-pre-commit Skill
0★ repoSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
The same file is in 19 other repositories
381487190/opengod/skills/real-engineering/productivity/grill-me Skill
0★ repoA relentless interview to sharpen a plan or design.
The same file is in 19 other repositories
Hayatelin/devsecops-skills/skills/secure-code-review Skill
0★ repoRun a security-focused review pass over a diff, PR, or file. Trigger when the user says "security review this", "is this PR safe to merge", "review for vulnerabilities", or before merging code that touches auth, input handling, data access, or external requests.
chieaid24/skills/skills/setup-pre-commit Skill
0★ repoSet up stack-aware pre-commit hooks - format, lint, and test before every commit. JS/TS via Husky + lint-staged + Prettier; Python via the pre-commit framework (ruff); Rust/Go via a tracked git hook (fmt + lint + test). Use when the user wants pre-commit hooks, commit-time formatting/typechecking/testing, or when bootstrap-issues wires up a repo.
satejbidvai/skills/skills/update-pr-review Skill
no license0★ repoLearn from PR comments to improve the /pr-review skill
Suraj787/motif/skills/implementation-validation Skill
no license0★ repoUse as the final acceptance gate to confirm an interaction is accessible, performant, responsive, design-system-consistent, and fully recorded before it is considered done.
kyt19970215/codex-skill-evolution-framework/skills/research-verification Skill
0★ repoReusable external research and verification workflow for public tools, plugins, dependencies, APIs, OS behavior, browser/driver issues, version compatibility, security/anti-cheat claims, install/upgrade problems, exact error messages, stale claims, and research failure-learning rules. Use when the user asks to search, verify, compare current options, investigate a public project, remember or classify a public-source failure, or when local debugging hits an unclear environment/dependency/tooling issue.
kyt19970215/codex-skill-evolution-framework/skills/skill-evolution-validator Skill
0★ repoAudit an evolution skill system for structure, routing behavior, ledger alignment, privacy, and platform freshness. Use only for explicit health, cleanliness, regression, ledger, or release-readiness checks; do not use for routine edits or configured shortcuts.
xenonbyte/xsk/skills/check Skill
0★ repoReview a code change before it ships. Check scope drift, enforce hard stops, gate findings on evidence, then verify and sign off. Distilled from Waza /check.
RachidChabane/agentsync/skills/author-verify Skill
0★ repoFill in a repo's `verify` verb with its real fast checks (lint, typecheck, format). Use after scaffold-determinism creates a stub verify, or when a repo's commit gate has no real checks yet.
agentic-workflow-kit/technical-design/skills/review-technical-design Skill
0★ repoUse when a user wants to review a technical design, check an architecture, review a DDD design, or run review-technical-design. Emits structured suggestions without auto-editing, using architecture/enforceability, domain-correctness, and agreement-integrity lenses. Requires user disposition before design edits and treats settled as zero open blocking suggestions.
jpoindexter/design-engineering-canon/skills/dec-discovery-validation Skill
0★ repoProduct discovery and validation frameworks — Jobs To Be Done, Continuous Discovery / Opportunity Solution Tree, Lean UX / Build-Measure-Learn, Design Sprint, Working Backwards, Story Mapping, Crazy 8s. Use when scoping what to build, validating an idea before committing, structuring user research, or turning a fuzzy outcome into testable solutions.
The same file is in 1 other repository
NyXXiR/skillboard/examples/multi-source-skills/matt/grill-me Skill
0★ repoClarify vague requirements before implementation.
NyXXiR/skillboard/examples/multi-source-skills/omo/review-work Skill
0★ repoReview completed implementation work with strict verification.
NyXXiR/skillboard/examples/multi-source-skills/wshobson/security-review Skill
0★ repoSecurity review workflow skill.
NyXXiR/skillboard/examples/skills/grill-me Skill
0★ repoAsk strict clarifying questions before work begins.
NyXXiR/skillboard/examples/skills/grill-with-docs Skill
0★ repoRequirement clarification that also updates durable project docs.
shaxzodbek-uzb/laravel-guardrails/skills/laravel-multi-tenant-guard Skill
0★ repoThis skill should be used when the agent works in a multi-tenant / SaaS Laravel app — any time it writes or edits a model, controller, action, Policy, route, job, listener, command, API Resource, cache key, or file path that touches tenant-owned data. Load it when it sees or adds tenant_id / team_id / account_id / organization_id / company_id columns, a BelongsToTenant trait, global scopes, route-model binding (`/{post}`), Rule::exists / exists validation on a foreign key, Filament panel tenancy (->tenant()), or queued jobs that query tenant data; and whenever the user mentions multi-tenant, tenancy, tenant isolation, cross-tenant leak, data leak, IDOR, stancl/tenancy, or spatie/laravel-multitenancy. Loads the guardrails that prevent one tenant from reading or mutating another tenant's data.
shaxzodbek-uzb/laravel-guardrails/skills/laravel-n-plus-one-guard Skill
0★ repoThis skill should be used when the agent writes or edits Eloquent queries, controllers, API Resources, Blade/Livewire/Filament views, or jobs that iterate over a model collection and access a relationship (e.g. `$post->author`, `$order->items`, `@foreach`/`v-for` over models touching a relation, `->comments->count()`); when it sees `->get()`, `->all()`, `->paginate()`, `with()`, `load()`, `whenLoaded()`, `withCount`, `chunk`, `cursor`, `lazy`, accessors that query, Filament table relation columns, or `modifyQueryUsing`; or when the user mentions N+1, "slow query", "too many queries", lazy loading, eager loading, Telescope/Debugbar query counts, or DB load/timeouts under traffic. Loads guardrails that turn silent 1+N lazy-load explosions into eager-loaded, count-aggregated, strict-mode queries.
shaxzodbek-uzb/laravel-guardrails/skills/laravel-pint-formatting Skill
0★ repoThis skill should be used whenever the agent generates, edits, or finishes a batch of PHP in a Laravel project — before presenting changes or committing. Load it when it touches code style, formatting, a pint.json, a pre-commit hook, or CI for PHP; when it runs or should run ./vendor/bin/pint (--dirty / --test / -v / --bail); or when the user mentions Pint, PHP-CS-Fixer, code style, formatting, lint, "match house style", or noisy diffs. Loads the guardrail that keeps AI-generated PHP formatted to the project's Pint standard so diffs stay clean and reviewable.
yogeshg665/quill-trading-agent/skills/market-hours-guard Skill
0★ repoVeto orders placed while the US regular session (NYSE/Nasdaq, 9:30-16:00 ET) is closed, based on the deterministic snapshot timestamp, including weekends and exchange holidays. WHEN: "is the market open", "after hours", "pre-market order", "weekend trade", "exchange holiday", "trading session", "can we trade right now", "market closed".
yogeshg665/quill-trading-agent/skills/wash-sale-guard Skill
0★ repoFlag a buy that repurchases a security sold at a loss within the US IRS 30-day wash-sale window, so a disallowed loss is not triggered. Advisory by default; can be made blocking. WHEN: "wash sale", "30-day rule", "I just sold this at a loss", "tax-loss harvesting", "disallowed loss", "repurchase within 30 days", "IRS wash sale".
hztopcu/academic-research-skills-universal/ars_universal/assets/academic-pipeline Skill
no license0★ repoOrchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
hztopcu/academic-research-skills-universal/ars_universal/assets/deep-research Skill
no license0★ repoUniversal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, WHY HOW WHAT papers, 3W literature scan, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 三段式文獻掃描, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
SYMBaiEX/gpt-orchestration/skills/gpt-orchestration Skill
0★ repoCoordinate hierarchical coding-agent fleets for repository-wide audits, implementation sprints, migrations, and complex work that benefits from parallel specialists. Use when a user asks for subagents, a fleet, parallel delegation, GPT-5.6 Sol, Terra, or Luna routing, broad codebase completion, or independent implementation and verification passes. Enforce bounded ownership, concurrency-aware waves, dirty-worktree safety, runtime-honest model handling, and evidence-based integration.
The same file is in 1 other repository
Sarmkadan/dotnet-senior-skills/skills/ef-core-query-review Skill
0★ repoReview EF Core LINQ queries for N+1, cartesian explosion, tracking overhead, client-side evaluation, and over-fetching. Use when writing or reviewing any code that queries a DbContext.
Input validation and injection
Sarmkadan/dotnet-senior-skills/skills/input-validation-and-injection Skill
0★ repoEnforce input validation and prevent injection at API boundaries - SQL injection, over-posting, unbounded queries, and unvalidated input. Use when reviewing controllers, endpoints, and data-access code.
Sarmkadan/dotnet-senior-skills/skills/nullable-reference-discipline Skill
0★ repoEnforce nullable reference type discipline in C# - annotation honesty, null-forgiveness audit, boundary validation, and EF Core interaction. Use when writing or reviewing C# code in nullable-enabled projects or migrating projects to nullable.
Sarmkadan/dotnet-senior-skills/skills/performance-review Skill
0★ repoReview .NET code for allocation pressure, string handling, Span/pooling opportunities, LINQ costs, and caching - with explicit guidance on when performance work is and is not justified. Use when reviewing hot paths, optimizing .NET code, or evaluating performance claims.
Sarmkadan/dotnet-senior-skills/skills/security-review-dotnet Skill
0★ repoSecurity review checklist for ASP.NET Core - authorization vs authentication, IDOR, mass assignment, SQL injection through raw SQL and EF, secrets exposure, and unsafe deserialization. Use when reviewing endpoints, data access, or anything handling user input or credentials.
Sarmkadan/dotnet-senior-skills/skills/serialization-review Skill
0★ repoReview .NET serialization - System.Text.Json configuration, contract evolution, polymorphism, streaming large payloads, and deserialization security. Use when reviewing JSON handling, serializer options, or API/message contracts.
Sarmkadan/dotnet-senior-skills/skills/solid-review-checklist Skill
0★ repoApply SOLID principles concretely to C# code review - real smells, thresholds, and refactors rather than abstract definitions. Use when reviewing class design, service structure, or interface changes in C#.
Tsurai7/agentic-playbook/skills/git-safety Skill
0★ repoSafe git commit workflow. Use when the user asks to create a commit, or before running git commit. Covers staging, message style, HEREDOC format, amend rules, and hook failures.
Tsurai7/agentic-playbook/skills/plan-review Skill
0★ repoEngineering review of an implementation plan before any code is written: scope challenge first, then architecture, code quality, tests, performance. Use when asked to review/critique a plan, design doc, or proposed approach, or before approving a multi-file implementation plan. Skip for reviewing a code diff (staff-review), for deciding whether the idea is worth building at all (office-hours), and for single-step plans with an obvious shape.
Tsurai7/agentic-playbook/skills/staff-review Skill
0★ repoStaff-level code review method for a diff or branch: review against stated intent, confidence-calibrated findings, verify every finding against the code before reporting, fix-first protocol. Use when asked to review code like a senior/staff engineer, or when review findings must be high-precision. This is the review method — it complements harness-native review commands (e.g. /code-review), not replaces them. Skip for reviewing plans (plan-review) or vetting ideas (office-hours).
Verification before completion
Tsurai7/agentic-playbook/skills/verification-before-completion Skill
0★ repoRequire evidence before claiming work is complete, fixed, or tests pass. Use before commits, PRs, or any "done", "fixed", "works now", "should work", or "tests pass" statement.
gadost/regitize/skills/regitize-squash Skill
0★ repoAnalyze a Git branch for fixup, squash, checkpoint, WIP, typo-only, formatting-only, and tightly coupled follow-up commits, then produce a semantic squash plan without changing history. Use when the user invokes regitize-squash, asks which commits should be combined, wants a cleanup plan before interactive rebase, or needs noisy history grouped into reviewable changes.
gadost/regitize/skills/regitize Skill
0★ repoInspect a Git branch commit-by-commit, derive accurate commit messages from each actual diff, preview the complete old-to-new mapping, and safely rewrite the branch history after explicit approval. Use when the user invokes regitize, asks to repair vague or misleading commit messages, clean up commit-message history, or rename historical commits based on their contents.
LandonTomaine/LT-Agents/skills/ship-change Skill
0★ repoLightweight end-to-end coding workflow for taking a user request through analysis, a concise plan, implementation, validation, and handoff. Use when the user wants Codex to do a repo change from start to finish, especially when the work should be committed and pushed only after the user approves the final diff, commit message, and push target.
Systematic review orchestration
ruthannepai-tech/inflammatory-target-discovery-skills/skills/systematic-review-orchestration Skill
0★ repoOrchestrate an exhaustive, multi-database systematic literature review — taxonomy to tiered reference library to synthesis. Use when the ask is a comprehensive/exhaustive review of a disease or topic (not a single "what's the seminal paper" lookup). Layers on the base literature-review skill: query-matrix design, multi-DB retrieval (PubMed + OpenAlex + citation-graph), DOI dedup, LLM relevance screen, Tier-1/2/3 evidence rubric with topical-specificity guardrail, and the evidence-map figure. Disease-agnostic via a swappable taxonomy.
connordibble/dibble/plugins/design-verify/skills/design-verify Skill
0★ repoVerify UI changes actually look right by driving a browser and critiquing what renders, instead of assuming the code is correct. Use after implementing or editing any UI - a component, a page, a layout, a style change - and whenever asked to check responsive behavior, mobile layout, visual regressions, or "does this look okay". Especially use before calling frontend work done: generated markup compiles and still looks broken at 375px.
bingelp/skills/skills/grill-with-docs Skill
no license0★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go. Use when the user wants to stress-test a plan or design before committing to it, outside the normal /spec or /plan flow.