Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Audit the developer experience of any platform that sends outbound webhooks or event destinations to its customers, and produce a structured YAML audit file with scored findings and prioritized recommendations. Use whenever the task is to review, assess, grade, or critique a company's webhook/event- delivery DX: their signup and onboarding, signing and verification, retry and delivery semantics, event catalog and payloads, setup surfaces (UI/API/CLI/IaC/SDK), consumer-facing observability, local dev, and local-to-production transition. Trigger this for a 'webhook DX review', 'event destinations audit', or an 'outbound webhook assessment', even if the user names a specific company (e.g. 'review Acme's webhooks') rather than the word audit. The output is a YAML audit file conforming to `schema/audit.schema.yaml`; whoever consumes it downstream renders their own presentation.
Performs complete code reviews of GitLab merge requests, analysing code quality, security, performance, and best practices. Use when the user says "code review" or asks to review merge requests or analyse a branch's changes before merging.
Review new or updated Coral source manifests and source PRs for content, style, product fit, query ergonomics, documentation quality, and consistency with existing Coral sources. Use when Codex is asked to review a sources/core/name or sources/community/name source directory, a manifest.yaml, or a GitHub PR that adds or changes a Coral source.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Expert code review for embedded/firmware projects with dual-model cross-review (Claude + Codex via ACP). Detects memory safety, interrupt hazards, RTOS pitfalls, hardware interface bugs, and C/C++ anti-patterns. Trigger when user asks to review embedded/firmware/MCU code changes, diffs, or PRs. Examples: 'review firmware-pro2 的改动', 'review the NFC changes', '/embedded-review ~/path/to/repo', '/embedded-review ~/path/to/repo HEAD~5..HEAD', '/embedded-review <github-pr-url>'. Target environments: bare-metal MCU (STM32, nRF, ESP32, RP2040), RTOS (FreeRTOS/Zephyr/ThreadX), Linux embedded, mixed C/C++ firmware.
Lightning.skill: speed up a website or app the way Anthropic made claude.ai 3x faster in two weeks. Define "open to usable", measure a baseline, find countable metrics and prove they tie back to felt experience, optimize step by step, and use a ratchet to lock in that things can only get better. Use when someone says the site is too slow, speed it up, performance optimization, first screen, instant load.
Reviews generated implementation plans against best practices including task sizing (30m-2.5h), style anchors, TDD requirements (AI audience), drift prevention (AI audience), and quality constraints. Validates milestones.yaml and task files for completeness, alignment, and development readiness. Adjusts review criteria based on target audience (AI, human, or hybrid).
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window optimization.
MSW (Mock Service Worker) best practices for API mocking in tests (formerly test-msw). This skill should be used when setting up MSW, writing request handlers, or mocking HTTP APIs. This skill does NOT cover general testing patterns (use test-vitest or test-tdd skills) or test methodology.
Diagnose and fix measured startup, rendering, scrolling, memory, media, or network regressions in Expo React Native apps. Use for a reproducible performance problem or an explicit performance audit, not speculative library swaps or blanket memoisation.
Simulates a multi-role PRD/prototype review board, giving review conclusions from six perspectives: product, engineering, QA, design, operations, and legal. Triggered when the user says "帮我评审一下这个 PRD", "看看这个需求有没有问题", "模拟评审会", "review 一下这个文档", "这个需求能不能过评审", "帮我查漏补缺". Also applies when: the user uploads a PRD, requirements doc, prototype screenshot, or feature spec and asks for a check; the user mentions "评审", "review", "过会", "需求评审", "方案评审" or similar keywords; the user asks whether a requirement is feasible from an engineering or QA perspective. Not for: writing PRDs (use pm-prd-writer), pure code review (use code-review), or pure design walkthroughs (use design-critique).
Use when setting up Git hooks for a polyglot or monorepo project with Lefthook — wiring fast format/lint checks on staged files at pre-commit and slower type-check/test gates at pre-push, across mixed-language subtrees (e.g. TypeScript and Python) from a single lefthook.yml, in parallel. Covers install + activation, the lefthook.yml schema (commands/jobs, glob, root, run with {staged_files}/{push_files}, stage_fixed, skip/only, parallel), a genuinely polyglot worked example, the hooks-vs-CI division of labor, and the --no-verify bypass. Teaches the hook wiring; references the per-tool skills (biome, ruff, ty, typescript-typecheck) and turborepo rather than re-teaching them. Keywords: git hooks, pre-commit, pre-push, lefthook, staged files, monorepo hooks, polyglot lint format.
Constraint transparency: analyzes an artifact structurally, then analyzes what its own analysis concealed. Produces a conservation law AND a constraint report showing what was maximized, what was sacrificed, and what to investigate next. The only AI skill that knows what it can't see.
Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.
Systematic test design with boundary value analysis, equivalence partitioning, decision tables, state transition testing, and combinatorial testing. Use when designing comprehensive test cases, reducing redundant tests, or ensuring systematic coverage.
Read or resolve a pull request's Qodo review using Qodo managed tools through MCP or the CLI — fetch structured status, reviewed commit SHA, and findings for ANY PR as JSON, with optional extended details and citation evidence for audits, then optionally resolve open findings and record outcomes, once or until clean. Use this — never `gh`/`curl` scraping of review comments — for "is the review clean on PR #N", "get Qodo's findings for <pr> as JSON", "audit the review evidence", "show finding citations", "what did Qodo flag", "is this review up to date with head", "check before merging", "resolve my PR review", "fix the review findings", or "babysit this PR until it's clean".
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
"Audits Move contracts for security vulnerabilities before deployment using 7-category checklist. Triggers on: 'audit contract', 'security check', 'review security', 'check for vulnerabilities', 'security audit', 'is this secure', 'find security issues'."
Take one feature request from prompt to reviewed, audited delivery in a SINGLE autonomous pass — one runnable Workflow that plans, reviews the plan, builds task by task, cross-reviews the build, and optionally runs a launch audit, then RETURNS the verified findings rather than looping (the user decides any fix round; a Workflow can't ask mid-run, and an autonomous fix-loop is what caused multi-hour grinds). It chains the existing skills — plan-to-task-list-with-dag (a specialist agent per task) → plan-founder-review → a specialist engineer/reviewer build across the DAG → a full claude ∥ codex/kiro cross-review → go-live-audit — and FOLLOWS the graph strictly: every task declares its dependencies, layers must be a topological order, plan review blocks a mis-ordered graph, and a task NEVER builds before its dependencies integrate (no building on a broken base). Per-task review is SLICE-SCOPED (judges only that task's own change against its acceptance criteria, attributing whole-codebase end-state gaps to the task that owns them) so the build isn't drowned in false blocks, and impl review is the end-state gate. Gates FAIL CLOSED — a reviewer that didn't actually run is never counted clean, and a died codex/kiro reviewer falls back to a native review, never a fabricated block. Durable and resumable: each run writes a live status file (overall + per-phase + per-task) with a journal reader for status/stop/resume, and resume rebuilds integration state from GIT ground truth so an interrupted run never loses or re-loses already-landed tasks. Code writing and each review independently pick native / codex / kiro (reviews can skip; writer and reviewer can differ), so the user controls quality vs token cost.
Reviews sqlx database code for compile-time query checking, connection pool management, migration patterns, and PostgreSQL-specific usage. Use when reviewing Rust code that uses sqlx, database queries, connection pools, or migrations. Covers offline mode, type mapping, and transaction patterns.
Use when authoring, reviewing, or debugging harness-backed vitest-evals suites, custom Harness adapters, first-party ai-sdk or pi-ai harness integrations, judges, replay, reporter-facing normalized run data, or examples and docs for these APIs.
Vitest 5 reference for the Vite-native testing framework. test, describe, it, expect, vi.fn, vi.mock, vi.spyOn, vi.when; beforeEach / afterEach; test.extend fixtures; test tags / annotations; coverage (v8 / istanbul); snapshots; vitest.config.ts; projects (formerly workspace); Vitest Browser Mode (vitest-browser-react, locators, expect.element); UI mode; bench fixture.
Provides comprehensive guidance for Vitest testing framework including fast test execution, Vite integration, component testing, mocking, and configuration. Use when the user asks about Vitest, needs to write fast unit tests, test Vue/React components, or configure Vitest with Vite projects.
Validate GitHub Actions workflow files for syntax errors, invalid references, and common mistakes. Auto-detects actionlint binary or guides installation. Checks project config or falls back to sensible defaults. Use when creating or modifying GitHub Actions workflows, validating CI/CD pipelines, or catching workflow errors before pushing.
Use when authoring or modifying a Datex Studio backend test (configurationTypeId=24, *-backendTest.json suffix) on a branch — mocha test suite with four hook flows (before_suite/after_suite/before_each/after_each) and a testCaseFlows array. Owns the action-as-test refactor pattern and the missing runtime-mock seam as Platform TODO. Triggers: "create a backend test", "create an xxx_test", "add a test suite", "mocha test suite", "add a test case to xxx_test", "modify a backend test", "refactor xxx_action into a backend test", "backend test won't run", "before_suite never fires", "suite hooks not firing".
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
Run code quality checks (ruff, mypy, pytest) and optionally simplify code. This skill should be used when the user wants to check code quality, run linters, run tests, or simplify recently modified code. Triggered by /lint, /check, or /code-quality commands.
Validate commit messages against the Conventional Commits specification. Auto-detects and installs commitlint CLI if missing. Checks project config or falls back to sensible defaults. Use when validating commit messages, preparing PRs, or enforcing commit conventions.
Use when auditing a Datex Studio component file before merge — final gate after authoring or modifying any component (action, function, grid, hub, form, editor, selector, storage, customType, backendTest, datasource). Generic dispatcher: reads the component file, picks the matching creator skill's rule set by file suffix, and runs the audit per those rules. Output is a structured punch-list (Blockers / Warnings / Nits). Triggers: "audit a component", "check it before merge", "final gate after authoring or modifying". For grid-specific gotchas (envelope shape, text-display coercion) use grid-validator instead.
Use this skill to read device logs for test failures, debug, smoke testing, and CI repros. Covers `adb logcat` (stream), `adb logcat -d` (dump and exit), `adb logcat -c` (clear), buffer selection (`-b main|system|crash|events|radio|kernel|all`), priority ladder (V/D/I/W/E/F/S), filter expressions like `MyApp:D *:S`, format flags (`-v threadtime`, `-v json` on Android 11+), `--pid $(adb shell pidof -s pkg)`, time/count filters (`-T '01-01 12:00:00.000'`, `-t 100`), buffer rotation (`-r <kbytes>`, `-n <count>`, `-f <file>`), buffer sizing (`-G`, `-g`), and stripping `Log.d` calls in release builds via R8 `-assumenosideeffects`. If the user mentions "logcat filter only my app", "events buffer am_proc_start", "logcat json format", "grep logcat expensive", "missing logs after restart", "stripping Log.d release", or "logcat -f writes to host or device", use this skill.
Use when auditing a Datex Studio grid configuration before merge or diagnosing grid rendering/filter/sort/toolbar bugs — the mandatory final gate after grid-creator. Carries grid-specific gotchas the generic component-validator doesn't catch: envelope shape, text-display coercion, five-location dynamic-filter wiring sync, imperative cell API mismatches, and tailored vs custom provenance conformance. Triggers: "audit a grid", "check a grid before merge", "diagnose grid rendering / filter / sort / toolbar bugs", "final gate after grid-creator". For non-grid components, use component-validator.
Detect project linting and validation tools, build an execution pipeline, run all tools to zero errors, and fix issues using an atomic fix protocol. Auto-detects Makefile targets, package.json scripts, Go tools, Python tools, and other common linters. Use when fixing linting errors, running validation pipelines, or ensuring code quality before committing.
Use after editing or writing any Datex Studio component file — invoked by every creator skill's closer ("After your edit, invoke post-edit-verification"). Runs the verification stack cheapest-first: Edit/Write tool succeeded → JSON parses → description is non-null, non-empty, ≤100 chars (platform limit) → grep for obvious typos. Escalates to component-validator subagent for non-trivial edits. Replaces Mitch's PostToolUse validate-component.py hook with a skill-based pattern. Triggers: invoked by every component-creator's closer; rarely invoked directly by users.
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.