Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Verify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and an immediate-fix review-finding route. Triggers: "triage-issue", "triage issue N", "triage this finding", "is this trigger met".
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
Audit an iOS app's source, distribution archive, runtime behaviour, and App Store Connect setup for a planned submission. Use for explicit App Store/TestFlight readiness reviews of native, React Native, or Expo apps. Distinguish verified blockers from checks that still need build, device, account, or policy evidence.
Use to develop a feature or bug fix end-to-end through a TDD git-worktree workflow — interactively (developer-led) or unattended (autonomous-mode, driven by the dispatcher). Triggers on phrases like "implement issue #N", "fix this bug", "add a feature", "create a worktree", "write test cases", "push and open a PR", "check CI", "address review comments", "resolve review threads", "/q review", "/codex review", "implement this autonomously", or any partial step in the design → worktree → tests → implement → verify → review → PR → CI → E2E lifecycle. Interactive mode asks for decisions; autonomous mode makes decisions per autonomous-mode.md and posts progress comments to the GitHub issue.
Use to perform an end-to-end PR review and reach an approve/request-changes verdict — including verifying acceptance criteria, running E2E tests via browser automation, resolving merge conflicts, and (when verdict passes) merging the PR. Triggers on phrases like "review this PR", "decide whether to approve and merge", "run E2E verification", "resolve merge conflicts on PR #N", or when the dispatcher hands off a PR labeled `pending-review` / `reviewing` for autonomous review. Distinct from in-flight dev-side self-review (that lives in autonomous-dev's pr-review step).
Load this skill when writing, reviewing, or interpreting behavioral accessibility automation — tests that manipulate a rendered page (resizing the viewport, pressing real keys, capturing and comparing screenshots) rather than only inspecting static markup or a single computed accessibility tree. Covers Reflow risk (SC 1.4.10) and Focus Visible risk (SC 2.4.7) checks. Absolutely always report indicator results separately from confirmed failures. Under no circumstances treat a clean behavioral scan as WCAG conformance, or collapse `cantTell`/test-error/indicator outcomes into a single pass/fail signal.
Generate and upsert a Ticket-scoped QA Report (PROGRESS or COMPLETION) for any CawPlan Ticket (anchor) + Version: collect anchor-relative subtree/relation/execution data, apply result rules, render ticket-qa-report.1 template, and persist via existing Portal qa_report POST/PUT. Use when: SQA asks for a test progress or completion QA report for a ticket and version (Story, requirement sub-ticket, or BUGFIX); republish/update an existing linked report; include related/blocking tickets in report scope. NOT for: Version Quality Report or AQA automation rollup; release risk assessment (use A5 separately); importing cases (A1), plan layout (A2), or defect filing (A4). V1 zero-BE: Agent-side upsert; approximate coverage; anchor-relative subtree depth ≤ 3.
Go performance analysis expert. Analyzes CPU/memory performance bottlenecks, gives high-performance coding advice, and optimizes GC/allocator/compiler/cache performance. Covers benchmark, pprof, escape analysis, compiler optimizations (BCE/inlining), concurrency performance, memory layout, CPU cache friendliness, data-driven optimization methodology, and performance differences across Go versions. Trigger words: Go performance, benchmark, pprof, memory allocation, escape analysis, compiler optimization, inlining, BCE, bounds check, CPU cache, cache line, false sharing, sync.Pool, GC optimization, GOGC, compiler optimization, performance analysis, pprof profiling, benchstat, allocation optimization, stack vs heap, string concatenation performance, slice preallocation, struct layout optimization, concurrency performance, Go performance, profile, escape analysis, optimization advice.
CodeStable usage feedback loop. Use only when the user explicitly asks to record or report that the cs skill went off track, a tool failed, the rules were unclear, or the agent was corrected; collect local evidence and prepare a confirmable public issue.
Bring a blocked React Router community pull request across the finish line. Use when the user invokes `/finish-line` or `$finish-line`, provides a PR number or URL, and asks Codex to resolve merge blockers such as a missing change file, missing documentation, missing tests, or stale contributor follow-up. Handles evaluating the blocker and pushing small maintainer fixes onto a contributor PR branch when authorized.
Run repeated build -> QA -> retro -> re0-work cycles while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.
Select a supported Kitaru adapter or build a project-local one for an unsupported Python or TypeScript agent framework. Use when a user wants to record or replay framework-native agent runs in Kitaru, needs a custom adapter, has no supported Kitaru integration for their framework, or needs to assess whether public framework hooks and the installed Kitaru SDK can support an adapter.
Migrate a CodeceptJS 3.x project to 4.x. Trigger when `package.json` pins `codeceptjs` at 3.x or is missing `\"type\": \"module\"`, when test files still use CommonJS (`require()` / `module.exports`) against CodeceptJS APIs, when config references removed helpers (`Nightmare`, `Protractor`, `TestCafe`, `AI`, `SoftExpectHelper`, `Mochawesome`) or removed plugins (`autoLogin`, `tryTo`, `retryTo`, `eachElement`, `commentStep`, `fakerTransform`, `enhancedRetryFailedStep`, `allure`, `htmlReporter`, `wdio`, `selenoid`, `screenshotOnFail`, `pauseOnFail`, `stepByStepReport`), or when 3.x APIs are in use (`ai.request` function, Joi schemas in `seeResponseMatchesJsonSchema`, `restart: 'browser'`, `I.retry()`, `I.limitTime()`, Playwright `customLocators`).
Audit whether code that still has consumers really needs to keep existing, focusing on wrappers/facades, compatibility layers, stale public APIs, defensive branches, fallbacks, default values, configuration, duplicate sources, and hypothetical extension points. Use for code that is used but not necessary, legacy compatibility cleanup, meaningless wrappers, defensive code removal, cleanup with no compatibility requirements, deep necessity checks, and "is this still needed?" requests; do not use it as a pure unused/dead-code proof tool.
Parses complex OpenAPI specs and generates Drift test cases from them. Use whenever the user wants to generate, write, or scaffold Drift tests from an OpenAPI spec — especially when the spec contains complex schemas: anyOf/oneOf/allOf, discriminators, polymorphism, inheritance, $ref chains, regex patterns, enums, or optional fields. Use when the user asks to "create tests for an endpoint", "cover all response variants", "generate test cases from the spec", or says anything like "each viable combination of responses". Use when the user is trying to understand what values are valid for a complex schema field, or when they paste a spec path and ask what tests to write.
Use when modernizing PHP code: PHP 8.1-8.5 features, PSR/PHP-FIG/PER-CS compliance, PHPStan/Rector/PHP-CS-Fixer/PHPat tooling, DTOs/enums/readonly/property hooks, type safety. Triggers: PHP modernization, type safety, PHPStan, Rector, PHP-CS-Fixer, enum, DTO, readonly, strict_types, property hooks, PHP 8.4, PHP 8.5.
Manage pre-commit hooks with preference memory and template-based configuration. Use when installing, configuring, enabling/disabling, or checking status of pre-commit hooks. Supports templates for python, javascript, typescript, go, rust, and generic projects.
Install and configure Testomat.io reporting in a test automation project when a user needs to integrate their tests with Testomat.io. Detect the testing framework (e.g., Playwright, CodeceptJS, Jest, Mocha, WebdriverIO, JUnit, Pytest, XML, etc) and automatically set up the appropriate reporter so test results are sent to the Testomat.io TMS.
Write and debug React Native Harness tests for app code. Use when the user asks to create or fix tests that import from react-native-harness, mock modules, spy on functions, render React Native components on-device, use setupFiles or setupFilesAfterEnv, or add optional UI tests with @react-native-harness/ui.
Internal scope/classification engine composed by review-change (and reused by the audit skills): consumes the synthesized findings table, verifies every applicable axis is represented, and classifies each finding into a decision table (fix-now / replan-in-unit / decision-required / proposal / ignore). Findings only — never refactors.
Test Riverpod providers and widgets; ProviderContainer.test, unit tests, widget tests with ProviderScope, tester.container(), mocking with overrides, container.listen for auto-dispose, awaiting .future. Use when writing unit or widget tests for Riverpod code, mocking providers, or testing with overrides. Use this skill when the user asks about testing Riverpod, mocking providers, or ProviderContainer in tests.
Set 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.
Creates, audits, and validates agent skills following the Agent Skills open standard. Covers YAML frontmatter, description writing, progressive disclosure, directory structure, 9-phase audits, severity classification, and manifest-implementation drift detection. Use when creating new skills, writing skill descriptions, auditing existing skills, detecting version drift, validating implementations match manifests, or debugging skill discovery issues.
Synchronize test scenarios and cases between a local project and Testomat.io. Use this skill whenever the user wants to pull/export/download tests from Testomat.io; or push/import/sync new or updated test cases back to the TMS in corresponding `*.test.md` format. Supports custom directories, markdown test format and advanced import/export workflows.
Code quality guidelines and best practices for writing clean, maintainable code. Covers naming, structure, error handling, testing, and code review standards. Use when writing code, reviewing, refactoring, or asking "how should I name this", "best practice for", "clean code".
Generate and validate API tests based on the real OpenAPI, route implementation, and existing tests. Use when the user asks to test endpoints, add integration tests, validate the API contract, generate regression cases, or troubleshoot API compatibility; distinguish the authorization for "generating tests" from "executing requests", do not guess status codes, response structures, or SLAs, and do not send write requests in unconfirmed environments.
Audit cross-document coherence: docs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-convention violations — and reports them ranked by severity, fixing only low-risk items on request. Model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "check doc consistency", "are the docs in sync", "audit the docs", "doc coherence review", "did the docs drift", "validate the roadmap".
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.