Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Analyzes Copilot Studio evaluation results using Practical Guidance on Agent Evaluation's 10-step playbook (Steps 6, 7, and 9) plus Microsoft's triage diagnostics. Returns a gate-based SHIP / ITERATE / BLOCK verdict with root cause classification, remediation, and pattern analysis.
Senior Frontend Code Reviewer with 12+ years JavaScript/TypeScript experience. Use when reviewing React/TypeScript code, checking code quality and style, verifying accessibility compliance, ensuring test coverage, or configuring linting tools (ESLint, Prettier).
A high-intensity questioning interview about a plan or design (adversarial design review / grill session) that exposes flawed assumptions and missing constraints, while maintaining a domain model (glossary and ADRs) throughout. Invoke manually with /grill-me.
Convert repeated heuristics into deterministic behavior: validator scripts, normalizer tools, generators, fixtures, manifests, CI jobs, and hook-ready checks. Use to codify learnings and prevent future guessing. Do NOT use for pure brainstorming or one-off edits.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
Use when writing E2E tests with Cucumber BDD and Playwright, setting up BDD test infrastructure, writing Gherkin feature files, implementing step definitions, configuring hooks and World, or integrating Cucumber with CI/CD. Invoke for Cucumber, BDD, Gherkin, feature files, step definitions, Given When Then, hooks, tags, World, scenario outline, @cucumber/cucumber.
Address review comments on your own pull request: implement valid suggestions, reply to invalid ones, and resolve threads. Covers inline review threads, review body comments, and plain PR timeline comments. Use when: user says "address PR comments", "implement PR feedback", "respond to review comments", "handle review feedback", "process PR review comments", "fix review feedback", "handle bot review comments", "process Copilot suggestions", "address Claude review", or wants to work through open review threads on their pull request. Gives credit to commenters in commit messages.
Default entry of the debug skill family when runtime observation is needed: static analysis stalled, a fix did not work, logs look correct but behavior is wrong, or fix verification needs before/after evidence. Covers escalation decision, targeted instrumentation (not shotgun logging), MRE reproduction, evidence tiers, confidence gating, escape hatches, and fix verification; composes with browser-debug-toolkit / hybrid-debug / channel enablers without demoting them. Triggers — 「打点调试」「打日志调试」「运行时调试」「运行时验证」「复现验证」「日志分析根因」「根因置信度不足」「静态分析碰壁」「修了还是不行」「日志正常但行为不对」「偶现」「调试默认入口」 / runtime evidence debugging, instrumentation debugging, escalate to runtime, evidence-driven debugging, fix didn't work, intermittent bug.
Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection, security scanning, token analysis, enterprise checks, or Eval Kit generation; use skill-check-pro for those. Do NOT use for LinkedIn skill engagement; use skillcheck-engage for that.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent execution loop, (2) debugging a bug or test failure — triggers systematic root-cause process, (3) user says "let's build", "help me plan", "I want to add X", or "this is broken", (4) completing a feature branch — triggers test verification + merge/PR options. NOT for: one-liner fixes (just edit), reading code, or non-code tasks. Requires exec tool and sessions_spawn.
Emulated Twilio REST APIs for local development and testing. Use when the user needs to test Twilio Messaging, Verify, Voice, phone numbers, webhooks, status callbacks, inbound SMS simulation, or Twilio SDK integrations without hitting the real Twilio service.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing screenshots, or setting up Maven test projects. Supports Chrome, Firefox, and Edge. Keywords: Selenium WebDriver, Java, JUnit 5, Page Object Model, explicit waits, Maven, screenshots.
Receives the path of a fix task file in review-fixes/ (e.g. review-fixes/fix-R01-critico-senha.md), implements the fix, runs the test suite and updates the file status. Use when do-execute-review generated fix task files and the user wants to resolve a specific issue. Do not use for batch fixes — invoke once per file. Do not use for QA, fixing QA bugs (use do-execute-qa-bugfix) or implementing new features.
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.
Use this skill when the user's Copilot Studio agent evaluations have come back and they need to interpret scores, diagnose root causes of underperforming test cases, find remediation steps, or analyze patterns to improve their agent. Always use this skill when the user mentions: "eval failed", "why did this fail", "triage", "diagnose failure", "low pass rate", "fix evaluation results", "not passing", "failing test cases", "evaluation results", "improve my eval scores", or any situation where eval scores need interpretation and action.
Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation strategies. Triggers on phrases like "design ablation", "plan experiment", "what experiments should I run", "baseline comparison", or "experiment matrix".
This skill should be used when writing tests, fixing bugs, adding features, or modifying the gateway layer. Use when you need guidance on testing architecture, working with fakes, implementing ABC gateway interfaces, or understanding the defense-in-depth testing strategy. Essential for maintaining test quality and understanding where different types of tests belong.
Audits and improves GitHub repository quality — README structure, community health files, .github directory setup, issue/PR templates, metadata, releases, and branch hygiene. Use this skill whenever the user asks to improve, audit, review, or set up a GitHub repository, or when they mention things like "make my repo look professional", "add contributing guidelines", "set up issue templates", "improve my README", "clean up my repo", "prepare my repo for open source", or "make my GitHub project look good". Also trigger when working inside a git repository and the user asks about best practices for documentation, community files, or repository structure. If the user is in a repo directory and mentions README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT, LICENSE, .github, templates, or release tags, use this skill.
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.