Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use when a CodeceptJS test needs login, user roles, or session reuse — or when another CodeceptJS skill identifies authorization is required. Also on auth-related test failures. Trigger on login, sign-in, sign-up, authentication, sessions, "logged in", admin/editor/user roles.
Evidence-led debugging for unexpected, silent, intermittent, or regressed behavior, including slowdowns and leaks. Use when tracing a bug to its root cause, finding what broke something that used to work, adding or removing targeted debug logs, or verifying a fix. Not for known one-line fixes, code review of a diff, runtime review of deployed services, or PM bug triage.
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
Apply the Opquast Digital Quality Framework (245 rules, 14 categories) when building, reviewing, or auditing websites and web applications. Use for web development quality assurance, accessibility compliance, security hardening, privacy implementation, e-commerce best practices, and holistic digital quality checks.
Audit a Penpot design for design-system / token GOVERNANCE issues (distinct from accessibility): hardcoded colors where a token exists, off-grid spacing, orphan/unresolved/unused tokens, duplicated values, and detached parts that should be component instances. Produces a severity report and suggests semantic-token swaps. Triggers: 'audit tokens', 'find hardcoded colors', 'token governance', 'check design system consistency', 'find off-grid spacing', 'detect raw values', 'are we using tokens correctly'.
Generate test cases and checklists for software testing. Use this skill whenever the user asks to create test cases, test scenarios, test plans, checklists, QA documentation, or mentions testing activities like "write tests for feature", "create a test checklist", "generate test scenarios from requirements", or similar. This skill works better if user provides documentation, requirements, etc., or it can create test cases based on the user prompt without any additional context.
Review a GitHub PR, then automatically request changes for any findings or approve a clean review. Use on a PR URL when the ask is to produce and submit findings; when findings already exist and the ask is to act on them, use /fix-pr-review. Batch mode covers 2+ PRs or "review all open PRs". For local uncommitted changes, use /parallel-review.
Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to mention Robin. Also use for explicit Robin requests, PR feedback triage, unresolved review threads, or waiting for PR checks.
Automate the EvenHub glasses simulator via its HTTP API. Use when testing or controlling the simulator programmatically — sending glasses input (up, down, click, double click), capturing screenshots, or reading browser console logs
Use this skill when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use it to identify code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and create comprehensive technical debt documentation
Automated code review for Arduino/ESP32/RP2040 projects focusing on best practices, memory safety, and common pitfalls. Use when user wants code feedback, says "review my code", needs help improving code quality, or before finalizing a project. Generates actionable checklists and specific improvement suggestions.
Use when comparing two or more code implementations against a spec or requirements doc. Triggers on “which repo is better”, “compare these implementations”, “evaluate both solutions”, “rank these codebases”, or “judge which approach wins”. Also covers choosing between competing PRs or vendor submissions solving the same problem. Does NOT review a single codebase for quality — use code review skills instead. Does NOT evaluate strategy docs — use strategy-review. Requires a spec file and 2+ repo paths.
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.
Optimizes Python library performance through profiling (cProfile, PyInstrument), memory analysis (memray, tracemalloc), benchmarking (pytest-benchmark), and optimization strategies. Use when analyzing performance bottlenecks, finding memory leaks, or setting up performance regression testing.
Playtest and QA Roblox experiences for mobile and tablet. Use for device simulator checks, touch controls, safe areas, thumb zones, text readability, orientation, HUD overlap, first-action friction, and mobile performance verification through Studio MCP.
Close a workstream and ship it to production with ONE approval point: it independently checks what will ship (syntax, tests, secrets in the diff, outdated base), shows once exactly what goes to production and whether the push publishes on its own, and only after the user's OK does it commit, integrate, publish and verify. Use from inside the workstream folder when the user says 'release', 'publicar', 'subir para produção', 'fechar a frente' or 'integrar'. It is the other end of the sdd-new-session skill.
[AUTO-INVOKE] MUST be invoked BEFORE writing or modifying any test files (*.t.sol). Covers test structure, naming conventions, coverage requirements, fuzz testing, and Foundry cheatcodes. Trigger: any task involving creating, editing, or running Solidity tests.
Audit and improve an existing software project's automated tests as regression protection. Use when Codex needs to assess test quality, map tests to user-visible capabilities or documented contracts, find implementation-coupled, over-mocked, dead, duplicate, fragile, or low-value tests, reduce CI cost, design a test migration plan, or refactor tests while preserving meaningful coverage. Applies to unit, integration, contract, component, and end-to-end suites across languages and frameworks.
Use this skill to ensure Jetpack Compose performance numbers reflect production reality by measuring against a release variant with R8 enabled, Live Literals disabled, and Compose Compiler reports read from the release output directory. Covers why debug builds lie (interpreted Compose runtime, JIT warmup, Live Literals constant-getters), how to set up a release-with-symbols measurement build, and how to wire Macrobenchmark, Compose Compiler reports, Layout Inspector, simpleperf, and Android Studio Profiler against it. Cited result is roughly 75 percent startup gain and 60 percent frame-render gain debug to release. Use when the developer reports "slow startup", "jank", "dropped frames", "high recomposition count", or quotes timings from `assembleDebug`, Layout Inspector, or `CompilationMode.None`. Use when reviewing a perf bug, setting up a CI perf gate, or before filing a perf regression.
Run a structured usability audit of any UI against Nielsen's 10 heuristics. Produces a severity-rated, prioritized issue list — each finding tagged with the violated heuristic and a concrete fix. Use when auditing a screen, flow, or component for usability problems, or as a validation step after generating UI.
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallbacks, or large intermediates. CPU-only code and absent GPU dependencies are normal unless NVIDIA is prohibited. Exclude required cross-vendor or CPU-only deployment, vendor-lowered dense or NN layers, general Warp API questions, and already-selected Warp kernels. Contribution policy alone is not exclusion.
Create or edit a document that an agent reads, and prove that it changes behavior. Put a lesson that agents keep learning again into structure. Read this skill before you write or edit a skill, AGENTS.md, CLAUDE.md, a system prompt, or other text for agents. Use it to verify such a document before it ships. Use it also when the user corrects the same agent mistake a second time
Comprehensive ABAP code quality checking using abaplint (automated static analysis) and Clean ABAP principles (manual code review). Use when users ask to check, lint, validate, review, or analyze ABAP code for syntax errors, clean code compliance, code quality, best practices, or adherence to Clean ABAP guidelines. Also use for abaplint setup, configuration, and execution. Triggers include "check this ABAP code", "lint my ABAP", "run abaplint", "configure abaplint", "is this clean ABAP", "review my ABAP", "analyze ABAP code quality", "code quality check", or "ABAP best practices".
Use when implementing, reviewing, or debugging a Gherkin acceptance-test pipeline with mutation testing. Covers parser, JSON IR, generator, runtime, step handlers, test runner, mutator, value mutation rules, execution, result classification, reporting, project layout, conformance, and agent setup. Based on Uncle Bob's Acceptance Pipeline Specification. Trigger even when the user mentions Gherkin parsing, acceptance test generation, mutation testing for acceptance tests, or building a portable test pipeline.
Audits any API documentation site by crawling every endpoint page and scoring each one across 5 checks: description quality, OpenAPI spec presence, body param descriptions, response codes, and response schema completeness. Produces a polished interactive HTML report with a summary scorecard, site-wide pattern analysis, ranked top issues, and per-endpoint findings with specific fix guidance. Trigger this skill whenever a user provides a documentation URL and asks to audit, review, analyse, or check their API docs. Also trigger for: "do the same audit for X", "audit docs.company.com", "check the API docs at X", "run the API docs audit on X", "review the docs for Y API", or pastes a URL alongside words like audit, review, crawl, check, analyse, quality, completeness, or gaps. Always use this skill — do not attempt the audit without following this structured crawl-score-report workflow.
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
HCCL (Huawei Collective Communication Library) performance testing for Ascend NPU clusters. Use for testing distributed communication bandwidth, verifying HCCL functionality, and benchmarking collective operations like AllReduce and AllGather. Covers MPI installation, multi-node pre-flight checks (SSH/CANN version/NPU health), and production testing workflows.
Use when working with Roborazzi screenshot tests on Android/JVM — setting up the Roborazzi Gradle plugin, running record/compare/verify tasks, writing tests with captureRoboImage or RoborazziRule, Compose Preview screenshot testing (ComposablePreviewScanner), Compose Multiplatform (iOS/desktop) screenshots, AI-powered image assertions, roborazzi.* Gradle properties, or troubleshooting Roborazzi/Robolectric screenshot test failures.
The scientific method as a universal problem-solving algorithm — goal-first, plural falsifiable hypotheses, designed experiments, and honest measurement, scaling from TDD to feature validation to MVP launch. USE WHEN think about, figure out, experiment, iterate, optimize, hypothesis, science, full cycle, quick diagnosis, structured investigation, how do we test, analyze results. NOT FOR multi-angle lens passes (use IterativeDepth).
This skill should be used when the user asks for a security-focused review of a codebase. Triggers: "security audit", "find vulnerabilities", "check for security issues", "pentest this code", "security review", "secure code review", "vulnerability assessment", "threat model this code", "OWASP audit", "find injection vulnerabilities", "check authentication", "check authorization", "find secrets", "find hardcoded credentials", "check for XSS", "check for CSRF", "check for SSRF", "find IDOR", "find IDOR / BOLA", "check for SSTI", "review JWT handling", "review crypto", "find deserialization issues", "check for path traversal", "review for prototype pollution", "audit dependencies for CVEs", "supply chain audit", "review Dockerfile security", "review CI/CD security".
Owns the `tests/` folder of an ML workspace and the pairing rule between an experiment and its tests. Lightweight router: every test category has its own subskill (`smoke-test-ml-pipeline` is the only one for v1; `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` etc. plug in as siblings as the workspace grows). This skill places an empty `tests/<category>/` folder, enforces the stem-pairing rule between `tests/<category>/test_NN_<short_name>.py` and `experiments/NN_<short_name>.py`, and dispatches to the matching subskill when the user asks for a test. TRIGGER when: a new design note was just approved by `iterate-ml-experiment` and the matching test has to be drafted before the experiment can be marked done; the user asks "write the smoke test for `02`", "add the regression test", "do we have a test for X?"; an experiment script was edited and the paired test needs revisiting; about to run `pytest tests/` and one of the expected paired tests is missing. SKIP when: the design note does not yet exist (route to `iterate-ml-experiment` first); the test is for the package's internal helpers and unrelated to a specific experiment (regular unit tests live wherever the project's `pytest` config picks them up — out of scope here); the question is *what does the test result mean* rather than *should the test exist* (route to the matching subskill). HOW TO USE: this skill is a router. Read the dispatch table to figure out which subskill owns the test category the user is asking about, then hand off. Do not write the test body yourself — that belongs to the subskill. Do place the empty test file with the matching stem and the pytest scaffolding, then hand control over
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.