Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
This skill should be used to run an Agent-Ready Codebase Assessment — scoring a codebase across 8 dimensions with parallel agents, producing a weighted score (0-100), band rating, and improvement roadmap. Supports Ruby, Python, PHP, TypeScript, JavaScript, Go, Java, Scala, and Rust.
Decides whether work may be called done. Use before saying a task is complete, finished, ready, working, or fixed; before making a 'verified'/'PASS'/'tested' claim about your own deliverable; when wrapping up a session, calling it a day, picking work back up tomorrow, or about to commit; before drafting a yes/no confirmation question about a change that touches destructive operations, trust boundaries, or unattended automation; and after any failure. Covers what counts as verification per artifact type, which checks the producer may run and which need fresh context, the honest three-part delivery message, failure counting, and the end-of-session wrap-up order.
Design and audit data quality observability for analytics events, product metrics, warehouses, imports, pipelines, dashboards, AI datasets, billing data, and operational reports. Use when teams need freshness, completeness, accuracy, schema drift detection, lineage, backfill safety, alerting, incident ownership, and metric trust.
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly coupled modules, or make a codebase more AI-navigable.
Transform user-provided coding specification files into a layered governance plan and validated SonarQube plugin workflow. Automatically classify each requirement into L1/L2/L3/L4, implement L1-L2 as PMD rules for supported languages, route L3 to automation tooling, route L4 to human or AI review, package rules into a custom sonar-pmd plugin, and verify with Docker Sonar + real project scans.
Set up or repair Entrix guardrail specs in the current repository by discovering real quality signals, generating docs/fitness, and iterating with entrix validation until the result is executable. Use when the user asks to bootstrap entrix, add or split fitness dimensions, repair invalid guardrail specs, or make docs/fitness actually runnable.
Run Expo's configured AI code reviewer on local changes or an expo/expo pull request, summarize findings and reviewer coverage, retain PR previews by default for later posting, and post only when explicitly requested. Use when the user invokes /expo-review or asks Claude Code to run the repository's Expo code-review CLI.
Prevent, detect, and repair AI coding slop and dirty engineering in repositories. Use for planning features, writing code, changing tests, reviewing pull requests, refactoring, hardening CI, debugging regressions, or auditing agent-generated changes. Enforces behavioral contracts, focused diffs, test integrity, repo conventions, security boundaries, and evidence-based completion.
Senior Frontend QA Engineer with 10+ years JavaScript/TypeScript testing experience. Use when writing unit tests for React components, creating integration tests with React Testing Library, testing custom hooks, mocking APIs, or following TDD for frontend.
Use this skill when writing or running frontend unit and component tests with Vitest and Testing Library. Covers render/screen/fireEvent patterns, vi.mock for mocking, and the AAA (Arrange-Act-Assert) test structure. Apply when adding test coverage for Svelte components, debugging test failures, or setting up test utilities.
Diagnose and fix the most recent failing GitHub Actions CI run on the current branch. Fetches the failing run's logs via the GitHub CLI, locates the root cause (failing test, compile error, lint violation, etc.), applies a targeted fix in the local working tree, and — only after user confirmation — commits and pushes. Use when someone says 'fix the CI', 'fix the failing action', 'the build is red', 'javítsd a CI hibát', 'piros a build', or pastes a failing Actions run URL for the current branch. Refuses to run on protected branches (main, master, develop).
Review a GitLab merge request: fetch MR (default repo = project name), analyze the diff, and optionally post review comments. Use when asked to review an MR, do a code review on GitLab, or when the user wants MR feedback. Triggers on: review MR, review merge request, review this MR, code review GitLab, glab mr review.
Use when reviewing code that claims to use GoF patterns — phrases like "is this Observer used correctly", "review this for design pattern smells", "this is named *Strategy but doesn't look right", "audit this Singleton". Walks the target code through the catalog of pattern misuses with severity-tagged findings and citations to the relevant pattern skill.
Review a diff for what Honey would cut — over-engineering (speculative generality, hand-rolled stdlib, single-caller abstractions) and over-verbosity (dead code, narration, redundant comments). Outputs a terse delete-list, one line per finding, with the line count each cut saves. Use when asked to review, trim, or de-bloat a change, or before opening a PR. Quality lever only — it finds waste, not correctness bugs.
Run stepped HTTP load tests with ab/wrk, ramping concurrency levels to collect p50/p90/p99 latency, detect performance inflection points, and recommend optimal concurrency. Triggered by requests like 'load test this URL', 'benchmark my API', 'find the max concurrency', or mentions of p99 latency, throughput saturation, or capacity planning.
Integrates AFL++ coverage-guided fuzzing into CI/CD pipelines, covering harness construction, AFL++/AddressSanitizer/CmpLog instrumentation builds, and persistent-mode fuzzing to discover memory-corruption and input-handling vulnerabilities in C/C++ code. Use when adding automated fuzz testing to a build pipeline or hunting for memory-safety bugs in native/compiled applications.
Translates game design prose into engine-neutral implementation invariants and validation checks. Use when implementing or reviewing game mechanics where idle, hold-only, mashing, spam, safe waiting, or repeated scoring pulses must be prevented from dominating skilled play.
This skill should be used when comparing Lisa's source templates against a target project's implementation to identify drift. It validates the Lisa directory, detects project types, scans template directories, compares files, categorizes changes, and offers to adopt improvements back into Lisa. This is the inverse of lisa:review-implementation.
Audit code comments and docstrings quality across 6 categories (WHY-not-WHAT, Density, Forbidden Content, Docstrings, Actuality, Legacy). Use when code needs comment review, after major refactoring, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.
Guides developers and testers in writing, fixing, and structuring Locust load test scripts in Python. Use this skill whenever the user mentions Locust, locustfile, HttpUser, TaskSet, load testing with Python, virtual users, spawn rate, wait_time, catch_response, LoadTestShape, ramp-up stages, or wants to benchmark an API or service using Locust — even if they do not explicitly say "Locust" or "load test".
Authors GitHub Actions CI for Node projects - version matrices derived from engines, setup-node caching, pnpm setup without corepack, a fail-closed all-checks aggregator, merge_group support, concurrency. Use when the user asks to set up CI, add a Node test matrix, cache installs, or fix required checks and merge queues. Not for release/publish pipelines or dependency-update policy.
Always use when creating, modifying, reviewing, or debugging OpenHarmony graphic_2d graphic_test pixel comparison tests; whenever the user mentions RSGraphicTest, GRAPHIC_TEST, GRAPHIC_TESTS, GRAPHIC_N_TEST, Rosen rendering tests, RSCanvasNode, RSSurfaceNode, Drawing::Canvas, PixelMap, screenshot tests, the graphic_test directory, or /data/local/graphic_test images, you must use it.
A C/C++ stability code review framework covering 5 stability categories (exception handling, concurrency stability, resource management, boundary conditions, graphics stability) with 34 rules in total. Trigger scenarios: dedicated full-repository stability scans, local review before committing code, stability audits, failure-prevention reviews, code reviews, OpenHarmony stability scans, and any case where the user asks to check C/C++ code stability risks.
Use when generating unit tests for ETS/ArkTS static API classes in OpenHarmony graphic_3d module, when adding new test cases for MaterialETS, CameraETS, SceneETS or similar wrapper classes, or when setting up test environment for GTest-based ETS unit tests
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.
Build, review, debug, configure, migrate, or plan Playwright browser automation and E2E tests with current docs. Use for @playwright/test, playwright, playwright.config, locators, getByRole, locator.visible, frameLocator, assertions, fixtures, Page Object Model, storageState auth, test locks, retryStrategy, network mocking, HAR, traces, UI Mode, codegen, CI sharding, Docker, APIRequestContext, stories/galleries component testing, accessibility, screenshots, visual comparisons, AbortSignal, and Playwright MCP or CLI agent tooling.
Two agent-readiness scanners in one terminal: every check isitagentready.com and is-agentic.com run, plus copy-paste fixes, CI gating, scan history, and a local store neither web UI has an answer for. Trigger phrases: `scan my site for agent readiness`, `is my site agent-ready`, `what's my agent readiness level`, `what does is-agentic say about my site`, `cross-check my agent readiness score`, `compare both agent readiness scanners`, `how do I make my site ready for AI agents`, `fix my site for AI agents`, `check llms.txt and MCP discovery on this site`, `use isitagentready`, `run isitagentready`.
Reviews all comments on the current pull request, evaluates whether each one still needs action, and decides whether to address it or resolve it. Holds remarks written by AI review agents to a stricter evidence bar, because they judge a diff without the context a human reviewer carries. Use when the user asks to triage PR comments, review feedback, resolve review threads, or decide which PR comments still matter.
Performs comprehensive code reviews for Python files following PEP 8 and Google Python Style Guide standards. Checks code quality, best practices, security, performance, maintainability, and style compliance. Use when reviewing Python code or when asked to check, audit, or improve Python code quality.
Use when the user asks for QA analysis, test planning, test cases, or root-cause analysis of a defect. Also use for post-merge PR review analysis: auditing recent closed PRs for Devin/GitHub/security bot comments, verifying whether requested corrections were applied, and turning pending fixes into SPECs.
Maintain the .qa/ knowledge base of cross-session QA knowledge (quirks, flaky verdicts, defect patterns, contract changes); read before test tasks. Not for: pipeline state, case files (test-case-writing). 维护被测项目 .qa/ 跨会话知识库（环境怪癖、flaky、缺陷模式、契约变更）读写治理；任务前先读取。不用于：流水线状态、用例文件读写（test-case-writing）。
Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
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.