Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use when the user asks for a Markdown-only code review artifact, a review file without HTML, or a review report in `.reviews/` with no browser output. Trigger on phrases like "review my changes and save as markdown", "마크다운 리뷰 보고서만", "리뷰 결과 마크다운 파일로 저장", "markdown-only review", "/code-review-md", or "$code-review-md". For the default markdown + HTML review use the `code-review` skill.
CodeRabbit PR loop: audit findings, fix, wait for CI, merge. Pass `cli` to put `@coderabbitai ignore` in the PR description (disables the GitHub bot) and review with the CodeRabbit CLI instead. Use when: resolving CodeRabbit comments, merging a reviewed PR, or reviewing via CLI to skip the PR-side bot. Keywords: CodeRabbit, PR review, merge, CLI, @coderabbitai ignore, --bulk
Check and configure memory profiling with pytest-memray for Python projects. Use when setting up memory profiling from scratch, adding pytest-memray for CI memory regression detection, configuring memory leak detection in test suites, setting memory thresholds and allocation benchmarks, or when the user asks to profile Python memory usage.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs
Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.
Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling into individual recordings, and turning real, corroborated issues into PostHog tasks, insights, or an investigating-replay hand-off.\nTRIGGER when: user wants to pull/read/triage Replay Vision observations, asks \"what has my scanner found\", wants to act on or summarize scanner findings, turn observations into tasks/work, or points at a /replay-vision/<scanner-id> URL.\nDO NOT TRIGGER when: creating or sizing a scanner (use creating-replay-vision-scanners), running a one-off scan you don't then analyse, or authoring a signals scout.
Pre-submission checklist for iOS App Store and Google Play Store. Use this skill whenever the user mentions: app store submission, app store rejection, pre-submission checklist, app review, store guidelines, privacy manifest, data safety section, app permissions, usage descriptions, privacy policy, LGPD, GDPR, data protection, mobile app security check, or any mention of preparing an app for publication in iOS or Android stores. Also trigger when the user asks about app permissions, data collection, or privacy requirements for mobile apps.
Use alongside the `hardhat` skill when the project depends on `@nomicfoundation/hardhat-toolbox-viem`. Covers the viem clients exposed on `network.create()`, contract interaction (`viem.deployContract`, `read`, `write`, `getContractAt`), and `viem.assertions` (revert / event / balance assertions).
Create or migrate to a justfile (casey/just command runner) for any project. Use this skill when the user asks to add a justfile, replace a Makefile, set up project commands, create task runners, or mentions "just" in the context of build/dev workflows. Also trigger when you see a project with a Makefile that would benefit from just's simpler syntax, or when setting up a new project that needs common dev commands (build, test, lint, fmt). Covers Rust, Python, TypeScript/JavaScript, Go, and Ruby ecosystems. Do NOT use for CI pipeline configuration, Dockerfiles, or actual build system setup (cargo, webpack, etc.).
Review code following Kent Beck's refactoring philosophy and simple design principles. Detects code smells, guides refactoring techniques, and promotes incremental improvement (YAGNI, KISS). Use when reviewing code quality, refactoring, or improving code readability.
Light cross-material consistency resident machine-readable gate: check in the background whether terminology / metrics (name+value) / innovation-statement wording / method names are consistent across papers, PPTs, software copyright filings, code and project docs after any material is produced; when a definition changes, rescan all produced materials. Turns "make the wording match everywhere" from verbal advice into a machine-checkable, blocking, run_checkpoint-aggregatable gate (produces light.findings.v1; hard conflicts in terminology/metrics/innovations → Critical fail → exit 1). When to use: after any material is produced or modified, cross-material rescan before submission/defense/handoff, after a controlled definition (terminology/metric/innovation) changes. Trigger words: consistency / terminology unification / metrics don't match / F1 vs accuracy / value conflict / paper and PPT inconsistent / innovation wording / method name / rename / software copyright and system / glossary / rescan. Core discipline: the source of truth is the project's `.light/` controlled glossary (not local knowledge bases); scripts only locate and suggest, never rewrite automatically; visual consistency relies on human sign-off, scripts only check text; when no authoritative value is found, write "unregistered/to be verified", never fabricate; missing registry / provenance must be reported as partial coverage, and zero findings must not masquerade as a full check.
Check Module Federation build configuration: verify correct MF plugin for the bundler, async entry configuration, exposes key format, and exposes path existence. Use when modules cannot be correctly exposed, expected modules are missing from the build output, or runtime initialization errors occur.
Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got fixed, the per-metric deltas, worst rows, and whether the two runs are comparable — with the Opik compare-view link. Runs via the SDK; reads results via the MCP when connected. Does not issue a ship/no-ship verdict. Use for "did my fix work", "compare against the baseline", "run the regression suite", "why did quality drop", "which cases regressed", "compare these two experiments". Not for the ship/hold decision itself (use verify), live production triage (use diagnose), building an evaluation from scratch (use evaluate), or capturing a single case (use test).
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion. Use for "turn this into a test", "add a regression case for this trace", "make sure this doesn't happen again", "capture this failure", "add this to the test suite". Not for running the suite (use compare), building an evaluation from scratch (use evaluate), or explaining why the trace failed (use explain)
Use this skill for Pest PHP testing in Laravel projects only. Trigger whenever any test is being written, edited, fixed, or refactored — including fixing tests that broke after a code change, adding assertions, converting PHPUnit to Pest, adding datasets, and TDD workflows. Always activate when the user asks how to write something in Pest, mentions test files or directories (tests/Feature, tests/Unit, tests/Browser), or needs browser testing, smoke testing multiple pages for JS errors, or architecture tests. Covers: test()/it()/expect() syntax, datasets, mocking, browser testing (visit/click/fill), smoke testing, arch(), Livewire component tests, RefreshDatabase, and all Pest 4 features. Do not use for factories, seeders, migrations, controllers, models, or non-test PHP code.
Official PGYER (蒲公英) skill for app beta distribution. Use whenever the user mentions PGYER / 蒲公英 / pgyer.com, or asks to upload an ipa/apk/hap for beta testing, fetch install links or QR codes, query a beta app's version history or install counts, manage tester groups, or wire up CI/CD that publishes to PGYER. Covers iOS, Android, and HarmonyOS app distribution. Reads credentials from $PGYER_API_KEY or ~/.pgyer/config.
Executes workflow markdown files interactively via Playwright CLI, stepping through each workflow action in a real browser. Use when the user says "run workflows", "run playwright", "test workflows", "execute workflows", or wants to interactively test their app against workflow documentation. Supports desktop, mobile, and multi-user workflows with authentication.
Prove it for debugging, performance investigation, bottleneck analysis, profiling, and optimization work. When reading code does not prove the cause, run a minimal reproduction, add temporary traces, measure bottlenecks, and verify the fix or improvement.
Browser automation for QE agents using Vibium (WebDriver BiDi) with assertions, batch execution, visual diff, prompt-injection scanning, and semantic intents. Use when any QE skill needs to drive a real browser — visual testing, accessibility audits, E2E flow verification, pentest validation, or exploratory testing.
Comprehensive codebase quality audit with parallel agent orchestration, GitHub issue creation, automated PR generation per issue, and PM-prioritized recommendations. Use for code review, refactoring audits, technical debt analysis, module quality assessment, or codebase health checks.
Quiz the user on code changes, a spec, or an implementation plan to verify genuine understanding before committing, building, or approving. Especially valuable when working with AI-generated code or spec-driven development. Use when the user says "quiz me", "/quiz-me", "test my understanding", "quiz me before I commit", "quiz me on this spec", "quiz me on the plan", "make sure I understand this", or anything suggesting they want to verify comprehension of a diff, design doc, or architectural plan.
Triage PR review comments by confidence score and act — fix the high-scoring ones, push back on the low-scoring ones, and ask about the borderline. Handles both inline review threads (anchored to diff lines) and PR-level review body comments (summaries submitted with reviews, like Age tables or Copilot overviews). First checks the PR's build and merge state and fixes those before processing comments. Use when the user says "respond to PR comments", "handle review feedback", "address PR reviews", "fix the build", "fix CI", "fix merge conflicts", or invokes /respond with a PR number. Also trigger when the user mentions a specific PR and wants to deal with reviewer suggestions — Copilot, human, or bot. Every reply this skill posts ends with an "agent on behalf of;" attribution line so reviewers can tell the comment came from an agent on behalf of the human, not the human directly. Do NOT use to generate a new review — that is /copilot-review's job.
Audit a Scala file or codebase for refactoring opportunities — Scala 3 modernization, idiom adoption, anti-pattern removal, performance hygiene, tail-recursion safety, and migration cleanup. Produces educational, documentation-backed findings as suggestions only, never editing the file in place. Use this skill whenever the user asks to refactor Scala code, modernize Scala 2 to Scala 3, find Scala anti-patterns, optimize Scala performance, review Scala idioms, apply opaque types, replace value classes, convert sealed traits to enums, migrate implicits to given/using, audit a `.scala` file, or do anything involving cleaning up or improving Scala code — even if they don't explicitly say "audit" or "refactor". Trigger on phrases like "review my Scala", "modernize this Scala", "make this idiomatic Scala 3", "find issues in this Scala file", "check for Scala anti-patterns", or any pasted Scala code accompanied by a request to improve, clean, optimize, or modernize it.
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.