Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan plus code changes; for external checks (e.g. Buildkite), only report the details URL and mark them out of scope.
Audit and improve Jetpack Compose runtime performance from code review and architecture. Use when asked to diagnose slow rendering, janky scrolling, excessive recompositions, or performance issues in Compose UI.
Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity and specific fixes. Use when the user wants an accessibility check, contrast verification, keyboard/screen-reader review, or wants to confirm a component meets POUR.
Patterns for using Testcontainers in .NET integration tests to spin up real dependencies like databases and message queues. Use when writing integration tests that require real databases, testing with message brokers like RabbitMQ or Kafka, or isolating test dependencies with Docker containers.
You MUST use this when a change needs an independent review before it moves on — a finished task, feature branch, pull request, work in progress, uncommitted changes since a given ref, or a spec or plan document that needs review — in any programming language. Replaces devflow review-request. Pins the exact target and its tree fingerprint, gathers intent and constraints, and dispatches a read-only reviewer that returns separate verdicts and evidence-backed findings.
Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says \"it crashes on empty data\" / \"there's no loading state\" / \"harden this\". Invoke when the user asks for harden on their UI, or mentions 'harden' alongside design / UI / frontend work.
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says "what's wrong with my app", "why is my eval failing", "analyze errors", "root cause analysis", "diagnose failures", or wants to understand production failure patterns.
Expert GDScript landmine guidance: static typing opcodes, signal-up/call-down, %UniqueName/@onready lifecycle, Callable bind/unbind, await sequences, typed collections, and safe Dictionary iteration. Use for code review, refactoring hot paths, or project standards. Trigger keywords: static_typing, signal_architecture, unique_nodes, @onready, class_name, signal_up_call_down, Callable.bind, typed_collections, await_sequence
Rust security skill for supply chain safety and memory-safe development. Use when auditing dependencies with cargo-audit, enforcing policies with cargo-deny, reviewing RUSTSEC advisories, writing memory-safe FFI patterns, or integrating fuzzing and Miri into a security review pipeline. Activates on queries about cargo-audit, cargo-deny, RUSTSEC advisories, supply chain security, Rust CVEs, safe FFI, or fuzzing for security.
Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Use this skill when the user wants to set up linting, configure auto-checking after edits, create a deploy checklist, set up pre-push checks, configure a CI pipeline, add quality gates, set up a hook for typechecking, enable post-edit validation, or auto-validate code changes. Triggered by phrases like “set up linting,” “auto check after edits,” “deploy checklist,” “pre-push checks,” “CI pipeline,” “quality gates,” “hook for typecheck,” “post-edit validation,” “auto-validate.”
Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'independent code review', 'what does codex think', 'get codex to review'.
Keep iterating on code changes until the tests pass, the build succeeds, or linting is clean. Runs in a tight loop of fix → run → check → repeat. Use when you want the agent to autonomously grind through test failures or build errors.
Expert performance engineer specializing in system optimization, bottleneck identification, and scalability engineering. Masters performance testing, profiling, and tuning across applications, databases, and infrastructure with a focus on achieving optimal response times and resource efficiency.
Comprehensive security vulnerability scanner for Next.js and TypeScript/JavaScript projects. Detects OWASP Top 10 vulnerabilities, XSS, injection flaws, authentication issues, hardcoded secrets, and Next.js-specific security problems. Audits dependencies for known CVEs and generates actionable security reports.
Perform a thorough quality review of a pull request or feature branch before merging. Use this skill whenever the user asks to review a PR, check if code is production-ready, assess quality, verify docs are updated, or asks "is this ready to merge?", "review this PR", "check quality", "is this production ready?", or similar. Also use when reviewing your own work before submitting.
Review code for any Frappe application — a checklist distilled from years of engineering practice on correctness, security, performance, concurrency, readability, API design, and testing. Use this when reviewing a diff, a PR, or a piece of code for quality and security, or when you want a reviewer's checklist grounded in hard-won Frappe/ERPNext lessons.
Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural language, code, and design. Use when reviewing or improving content quality, preventing generic AI patterns, cleaning up existing content, or enforcing quality standards in writing, code, or design work.
Design and implement integration tests that verify component interactions, API endpoints, database operations, and external service communication. Use for integration test, API test, end-to-end component testing, and service layer validation.
Production-ready scripts for Android app testing, building, and automation. Provides semantic UI navigation, build automation, log monitoring, and emulator lifecycle management. Optimized for AI agents with minimal token output.
Finish the GitHub pull request attached to the current branch; resolve merge conflicts, diagnose and fix failed CI checks, action review feedback from every source without duplicating replies that are awaiting a reviewer response, push focused commits, and continue until current-head CI and any running PR Agent review succeed and all actionable feedback is addressed. Use whenever the user asks to finish, complete, ready, resolve, fix, or address feedback/CI/conflicts on the current PR.
Use when Ane types /improve-system, asks to "mine recent sessions", "what is the system getting wrong", "improvement loop", "trend the rejection rate" — or asks "where are my tokens going", "token audit", "why was that session expensive" (spend-audit mode) — or when the SessionStart maintenance nudge reports improve-system due (14-day cadence). Mines the QA logs and session history for recurring correction patterns, proposes system edits, and audits where token spend goes. Not for one-off bug fixes (/system-audit finds those), not for wiki integrity (/li lint), not for quality-posture grading (/grade-system).
End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a "continue" checkpoint between each. Pure orchestration over the agent-observability sub-skills (`agent-observability-session-classify`, `agent-observability-trace-rca`, `agent-observability-eval-bootstrap`, `agent-observability-experiment-bootstrap`, `agent-observability-experiment-analyzer`). Use when user says "run the eval pipeline", "go from traces to evals", "bootstrap evals end to end", "classify then RCA then bootstrap", "build an eval set from scratch", "onboard me to datasets and experiments", "walk me through experiments", "I have an ml_app, now what", "Agent Observability onboarding", "guided experiment setup", "from traces to experiments", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with `--stop-after <phase>` to short-circuit at evaluators or dataset, or resume mid-flow with `--start-at <phase>`.
End-to-end functional testing framework for Huawei Cloud skills — three-tier pipeline covering single-skill unit testing, multi-skill orchestration, and end-to-end full flow testing. Each phase produces structured JSON output with chain verification. Supports skill installation validation, functional analysis, CLI→SDK→API feasibility research, test case generation, real-environment execution with resource lifecycle, resource cleanup, multi-skill scenario orchestration, trigger-conflict detection, and consolidated reporting. Triggers include: 测试技能, 执行技能测试, 跑测试流程, 技能回归测试, skill test, run skill tests, test huawei cloud skill, verify skill, 测试华为云skill, 全流程测试, 编排测试, 技能完整性检查, skill-tester, 跑测试, 回归测试, 组合测试, 多skill编排, verification, e2e.
You MUST use this when findings from a code review, pull request comments, CI or static-analysis output, or reviewer suggestions need a decision before any fix - a cr-request result, a spec or plan review, or a reviewer's message - in any programming language. Verifies each finding against the current tree, decides accept, reject, partial, defer, or escalate with evidence, fixes only what holds up, records the decisions in the plan's execution record, and routes back to verify. Replaces devflow review-resolution.
Testing Roblox code - testable modules with dependency injection, Jest Lua (runCLI, .spec files), legacy TestEZ, running tests in Studio, via Studio MCP, run-in-roblox, or CI with Open Cloud Luau Execution, Lune for pure Luau, multi-client playtests, QA checklist. Use when adding tests, setting up a test runner or CI, or verifying a gameplay change works.
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.