Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Follow-up Signals scout for the inbox itself. Attaches a check to each newly resolved report, spot-checks a couple of settled fixes with fresh probes, answers the checks it is dispatched for, and reports when a fix didn't hold, plus a gated escalation check on dismissed reports.
Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools—pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on “engineering analytics,” “is CI getting slower,” “slow workflow,” “flaky CI,” “time to merge,” “cycle time,” “PR throughput,” “failing checks,” “where is PR <n> stuck,” “CI long pole,” “what's holding up this PR.” For a verdict on one specific CI failure (whose fault, which commit) use investigating-ci-failures; to save these numbers as insights use turning-engineering-analytics-into-insights.
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterating up to 3 times per phase (10 total). Use when: the main agent delegates a code task with 'MODE: MORE_EFFORT', the user selects 'More Effort' code generation mode, or the task explicitly requests iterative refinement for higher code quality. Do NOT use for single-pass code generation (Lite mode), experiment pipeline orchestration (use experiment-pipeline), or diagnosing a specific experiment failure (use experiment-craft).
Xcode setup and tooling guidance for iOS 26 / Swift 6.2 clinic modular MVVM-C projects covering project configuration, SwiftData container wiring, testing, debugging, profiling, and distribution workflows. Use when configuring App-target infrastructure or day-to-day tooling around clinic architecture modules.
Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, and INP with guided debugging that automatically determines follow-up analysis based on results. Includes workflows for an LCP deep dive (5 phases), CLS investigation (loading vs. interaction), INP debugging (latency breakdown + attribution), and cross-skill integration with loading, interaction, and media skills. Use when the user asks about Core Web Vitals, LCP optimization, layout shifts, or interaction responsiveness. Compatible with Chrome DevTools MCP.
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Multi-agent adversarial code review. Spawns three reviewer subagents (Auditor, Adversary, Pragmatist) on a single model, runs a cross-examination round, then deterministically synthesizes a single ranked report. Use this for non-trivial PRs, security-sensitive changes, refactors that touch many files, or any change where one perspective has obvious blind spots. Trigger phrases include "adverse review", "adversarial review", "multi-perspective review", "review my changes from multiple angles", "panel review". NOT suitable for trivial diffs (typos, dependency bumps, formatting).
Audit NFR evidence for performance, security, reliability, and maintainability. Use when implementation evidence exists and the user says "audit NFR evidence", "audit NFRs", or "evaluate non-functional requirements"
Review, refactor, and debug code with verification before claiming done. Use when responding to review feedback, requesting a review, refactoring or reducing technical debt, root-causing a bug or failing test, or checking work before a merge, commit, or completion claim
Use when diagnosing an unexplained failure in a Meteor 3 application before the failing layer or fix is known. Triggers on server crashes, client-only errors, stuck subscriptions, DDP or WebSocket disconnects, Minimongo/server data mismatches, hanging or flaky tests, slow builds, --inspect, console.log, .only, Playwright traces, Instrumentation lifecycle events, or requests to debug a Meteor app. Use this skill when evidence must distinguish Meteor tool, server, client, data, test, browser, mobile, or production boundaries. For test setup and authoring use meteor-testing; after confirming a domain cause, hand the repair to the owning skill.
Practice-cognition loop. Test a hypothesis or plan in practice, learn from the result, and iterate in a rising spiral with an explicit stop condition. Trigger when a plan needs validation, an attempt failed and must be retried, or you notice thinking without doing (or doing without thinking); skip for one-shot outputs, lookup questions, or before any hypothesis exists
Use when verifying the codebase against the UX scenario base (batched, evidence-backed, report in docs/ux/audits/). Triggers: “ux audit” / “UX-аудит,” “run the scenarios” / “прогони по сценариям.” Not for a whole-project audit (project-audit) or editing scenarios (ux-scenarios)
Expert in Langfuse, the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
Use when you need to add or review fuzz testing for Java APIs with CATS — including contract-driven negative testing, malformed payload validation, boundary input exploration, CI integration, reproducible failures, and local execution guidance. This should trigger for requests such as Add fuzz testing to a Java project; Use CATS for API negative testing; Review CI quality gates for API contract robustness; Improve boundary and malformed input test coverage; Run CATS fuzz tests against an OpenAPI contract. Part of Plinth Toolkit
Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Use when user says \"integrity forensics\", \"forensic audit this paper\", \"投稿前自查诚信\", \"审这篇论文的诚信\", or says \"anti-autoresearch\" when the upstream repo's own skills are not installed. Also invoked by /paper-writing (submission self-forensics, default ON), /peer-review (forensic appendix), /resubmit-pipeline.
Crawl and validate all internal and external links across an AEM Edge Delivery Services site. Uses the query index or sitemap to discover pages, extracts links from .plain.html renditions, checks HTTP status codes, and produces a prioritized report of broken, redirecting, and insecure links. Use when auditing link health before launch, after a migration, or as a periodic maintenance check.
Configures monitoring systems, implements structured logging pipelines, creates Prometheus/Grafana dashboards, defines alerting rules and instruments distributed tracing. Implements Prometheus/Grafana stacks, conducts load testing, performs application profiling and plans infrastructure capacity. Use when setting up application monitoring, adding observability to services, debugging production issues with logs/metrics/traces, running load tests with k6 or Artillery, profiling CPU/memory bottlenecks or forecasting capacity needs.
Generate a QA plan for a feature just implemented, grounded in the actual code changes: the agent runs every check with an observable result, in a headless browser when one is available, and leaves a short manual list of what needs human judgment, saved to docs/qa. Use when a coding session wraps and you want to hand-test the result, or the user says "write a QA plan", "make a manual test plan", "how do I test this", "generate a testing plan for this feature", "try to break this component", or runs /qakit.
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.