Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Run first when working with any CodeceptJS 4 project — before writing, debugging, refactoring, or migrating tests. Teaches the framework's non-obvious rules and runs four-step discovery (`check` → read config → `list` → `dry-run`) reporting which helpers, plugins, page objects, custom actions, and tests are active. Other CodeceptJS skills depend on this output.
Triage and fix failing Buildkite CI checks for RisingWave pull requests by extracting concrete failing tests, diffs, and error messages from Buildkite build/job logs and artifacts, then applying focused code or test fixes. Use when users ask to diagnose red Buildkite checks, investigate flaky/failing CI jobs, understand why a Buildkite build failed, or provide Buildkite/GitHub check URLs and want a concrete fix.
Maintain repository integrity and documentation. Use for auditing structure, checking config validity, and reviewing inventory. Use proactively to validate the repository or sync documentation. Examples: - user: "Validate the repo" → run audit_repo.py - user: "Check agents" → run audit_repo.py, review errors - user: "Update documentation" → run sync_docs.py - user: "Check for issues" → run full audit
Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing a feature or fixing a bug where correctness matters and a test can pin the behavior. Says "TDD", "test first", "red green refactor", "write the test first".
Use when preparing ANY app for App Store submission, responding to App Review rejections, or running a pre-submission audit. Covers privacy manifests, metadata requirements, IAP review, account deletion, SIWA, age ratings, export compliance, first-time developer setup.
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development. Use when the user writes, reviews, or refactors code and wants to apply cross-cutting, framework-agnostic conventions (naming, structure, typing, error handling, readability). For targeted React/Next advice, use react-best-practices; for Node/Express/API backends, use backend-patterns.
Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.
Use when a code hotfix, rollback alternative, production/security/legal fix, launch blocker, or hard external deadline claims expedited review or relaxed process. TRIGGER on "emergency change", "hotfix", "prod incident", "major security hole", "must ship today", "hard deadline", "bypass review", or "fast-track this PR" for qualification only. DO NOT TRIGGER for ordinary urgency, soft deadlines, Friday timing, manager pressure, time-zone delay, or review unless emergency status is disputed.
Use when handling code review feedback as the change author, addressing reviewer comments, drafting replies, resolving disagreements, or summarizing updates. TRIGGER on "address review feedback", "respond to this review comment", "reviewer asked", "I disagree with reviewer", "what should I reply?", or "apply PR comments". If role is unclear, ask reviewer or author. DO NOT TRIGGER for reviewer comment writing, full code review, or PR descriptions unless author-response behavior is requested.
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".
Use when writing unit tests, integration tests, creating test fixtures, or running tests with bench run-tests. Prevents flaky tests from missing fixtures, incorrect test isolation, and wrong test base classes. Covers frappe.tests.utils, IntegrationTestCase, UnitTestCase, test fixtures, bench run-tests flags, test naming conventions. Keywords: unit test, integration test, IntegrationTestCase, fixtures, bench run-tests, frappe.tests, test_*.py, how to write test, test fixtures, run tests, test fails, bench run-tests example.
Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, [email protected]) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the explicit spend opt-in. Requires a metaharness repo checkout (`--repo` or $METAHARNESS_REPO) — without one it reports `checkout-required` with clone instructions. Degrades gracefully when metaharness is absent.
Reviews a code change's telemetry during authoring or code review — checks business-context attributes and cardinality placement, telemetry duplication, RED/USE/queue/fan-out coverage, and alert-driven scrutiny of code guarded by existing alerts and SLOs. Writes findings into the O11y Change Context manifest and hands fixes off to oodle-monitors, oodle-drop-rules, and oodle-log-metrics. Use when reviewing or authoring instrumentation changes.
Operate Playwright for browser automation end to end: author and debug E2E test suites (robust locators, network interception and mocking, parallel workers, accessibility snapshot checks), wire them into CI, and drive headless browsing and scraping with an extract -> validate -> save loop. Use when writing, running, fixing, or scraping with Playwright, when a Playwright CI failure or JSON report needs triage, or when the bundled pwrun script should analyze a run. Do not use for QA strategy or test framework selection (route to qa-methodology), for frontend component or architecture design (route to frontend-engineering), or for Cloudflare/DDoS-GUARD challenge bypass (use flaresolverr).
Read a partner's agent codebase, score it across the 12-dimension catalog, and emit an evidence-cited markdown plus branded scored HTML report. Use for a first-touch audit: assess/review/audit our agent, where to improve, spot low-hanging fruit, an honest read of what's weak, what Ratel would notice, or `/ratel-assessment`. Static-only unless a live telemetry sample (any OTLP/OTel backend — Ratel, Langfuse, LangSmith) is MCP-wired; writes to <repo>/.ratel/ without editing code; routes into follow-up Ratel skills.
Deep-audit ONE Rust crate end to end — read every file, don't sample: enumerate and read the whole crate, run its `cargo test`, check the existing `.ulpi/issues/<crate>.md` to avoid duplicates, then write or append evidence-backed findings (correctness, panic, validation, race, data-corruption, coverage gaps) each with severity and exact file:line — runs as a forked analysis workflow with its own reasoning budget, isolated from the main flow. Only valid if it actually read the entire crate; grounds every finding in real file:line evidence, labels uncertain claims INFERENCE, and never invents issues from intuition or writes outside this repository's issue file. Use when the user asks for a deep review of a single Rust crate.
Use when reviewing/judging a finished feature specification to decide if engineering can plan and build from it — an acceptance gate, not authoring. Below the PRD. Judges it against a single-sourced 10-condition implementability + testability bar: each feature traces to a PRD need (no orphans/gaps); behavior unambiguous + observable; I/O + states complete (a state-transition table where stateful); each edge case names its handling; acceptance criteria testable (Given/When/Then, or a metric-threshold for a probabilistic/ML feature); singular + consistent; load-bearing non-functional requirements carry numeric targets; an amend reviewed delta-scoped; open questions surfaced. EARS, decision tables, and archetype overlays are authoring aids judged by outcome, never demanded. Emits exactly `VERDICT: approve|revise` plus findings — approves a spec meeting the bar (no false-revise on a thin one), revises only on a real, named gap. Not for authoring, the upstream PRD, design docs (ADR/RFC), or other types.
Sets up professional Python library projects with modern tooling (pyproject.toml, uv, ruff, pytest, pre-commit, GitHub Actions). Use when creating new Python libraries, modernizing existing projects to pyproject.toml, configuring linting/testing/CI, or setting up Makefiles and pre-commit hooks.
Evaluate Agent Skills (SKILL.md directories) and answer \"is this skill any good / safe to install\" — spec compliance with security scanning, with/without behavior comparison, and description trigger testing, ending in a clear install / fix-first / reject verdict. Use this skill whenever the user asks to evaluate, audit, test, review, or score an Agent Skill or a skill collection, wants to know whether a skill actually helps or is safe, or wants to check if a skill's description triggers correctly, even if they just ask \"is this skill any good\".
Use this skill when reviewing Swift code for runtime-level performance costs, including heap allocation, ARC traffic, stack vs heap storage, closure capture contexts, method dispatch, protocol witness dispatch, existentials vs generics, opaque types, copy-on-write, SIL optimizer output, unsafe memory boundaries, or module-boundary optimizer visibility. Do not use it for Swift Concurrency scheduling, SwiftUI rendering, app launch, or profiling workflows unless the question is specifically about Swift runtime costs.
Run a structured WCAG 2.1 AA accessibility audit on a design, screen, component, or page. Produces a prioritized issue list — each finding cites the violated WCAG criterion, a severity rating (Critical/Major/Minor), and a concrete fix. Use when auditing for a11y compliance or as a validation step after generating UI.
Runs a 25-point quality control test on a supplier sample before mass production. Catches the defects that turn into 18% return rates and stranded inventory. Produces a back-message to the supplier with specific fixes required before greenlighting the PO. Use when a user mentions Alibaba sample, supplier sample, sample QC, or before mass production. Trigger phrases: "Amazon supplier sample", "Alibaba sample evaluation", "sample QC", "before mass production", "supplier quality test". Works with zero tools.
Audits whether ADK API reference docs and version-pinned strings are up to date across all language SDKs. Compares in-repo versions against upstream releases and package registries, then reports what needs bumping and which process to follow, and emits an executable plan only when asked. Triggers on "audit API reference", "check API ref docs", "are API docs up to date", "bump API doc versions", "check SDK doc versions".
Audits web UI quality across accessibility, interaction, forms, typography, navigation, layout, performance, motion, and microcopy. Use when reviewing or refining frontend UI before merge or release, or when the user asks for a UI, UX, or accessibility audit.
Language-specific best practices, code quality standards, and framework detection rules. Use when executing refactoring workflows, applying code quality rules, detecting frameworks, or checking language-specific patterns for TypeScript, Python, Go, Swift, or React.
Automate browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to: - Navigate websites and interact with web pages - Fill forms and click buttons - Take screenshots of web content - Test web applications - Extract information from web pages - Debug frontend issues in the browser - Monitor console logs and network requests - Record browser sessions as video This skill uses agent-browser for comprehensive browser automation. RECOMMENDATION: Disable Chrome DevTools or Playwright MCP when using this skill to save context.
Detects code smells and anti-patterns — long methods, large classes, feature envy, data clumps, primitive obsession, dead code, magic numbers, deep nesting, and more. Uses configurable thresholds from .codeprobe-config.json when available. Trigger phrases: "code smells", "smell check", "anti-patterns", "clean code review".
Use when a CodeceptJS 4 test fails, flakes, or behaves unexpectedly. Trigger on run errors and stack traces from `npx codeceptjs run`, intermittent failures, locator drift, timing issues, "works locally fails in CI", "why does this fail", trace/screenshot/console mentions, and breakpoint / step-through / "pause at step N" requests.
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.