Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.
Use when reviewing or validating Frappe/ERPNext code against best practices and common pitfalls. Checks generated code before deployment, validates against all 61 frappe-* skills, catches v16 patterns (extend_doctype_class, type annotations), validates ops patterns (bench commands, deployment), and generates correction reports. Keywords: review code, check script, validate deployment, find bugs, code quality, check my code, is this correct, code review, before deploying, best practices check.
Guides writing and running Vitest tests for Fusion Framework React apps with @equinor/fusion-framework-vitest-plugin-react-app — choosing a testing layer, configuring vitest.config.ts and Browser Mode, rendering with test/render/renderAppHook/renderAppComponent/testApp fixtures, and troubleshooting or migrating a suite. USE FOR: writing a new app/component/hook test, setting up vitest.config.ts for a Fusion app, choosing between app/framework/module/HTTP test layers, composing or overriding test fixtures, diagnosing a failing Fusion app test. DO NOT USE FOR: seeding module-specific mock state (auth, context, bookmarks, feature flags, HTTP) — use fusion-framework-mocking; dev-server-time API mocking/proxying (use fusion-developer-app); non-Fusion test suites; backend/service-repo tests.
Reports bugs and feature requests against the right Infrahub-ecosystem GitHub repository. Classifies the request, routes it (with the main `opsmill/infrahub` repo as the safe fallback when in doubt), searches for existing duplicates, gathers conservative environment info for bugs, and prepares the issue for the user to review before any submission. TRIGGER when: user wants to report a bug, file an issue, request a feature, open a ticket, or escalate a problem in any opsmill/infrahub-* project (SDK, Ansible, VS Code, MCP, Helm, schema-library, sync, backup, nornir, skills). DO NOT TRIGGER when: the user wants to fix the bug themselves locally, write a test, or debug code without filing.
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app—not just that it compiles or type-checks. Combines /_next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running `next dev`.
(NS) Code quality gate: SOLID, clean code, performance, security, testability. `Approved` only at score 10; score 9 = `Rejected`. Use after code changes, before PRs, at implementation closure, or code/PR/issue review — even without naming this skill. Delivery proof is ns-judge after Code Review: Approved. GitLab `ISSUE_URL`: Issue review mode. Do NOT parse requirements.md. Do NOT write code-review-report.md. Do NOT debug root-cause (ns-investigator).
Python backend testing patterns with pytest for FastAPI applications. Use when writing Python tests: unit tests for services and repositories, integration tests for API endpoints with httpx.AsyncClient, fixture creation, factory setup with factory_boy, async testing with pytest-asyncio, mocking strategies, and parametrized tests. Covers test organization (tests/unit, tests/integration), conftest hierarchy, and coverage requirements. Does NOT cover frontend tests (use react-testing-patterns) or E2E browser tests (use e2e-testing).
Read-only cross-artifact consistency check across spec.md, plan.md, and tasks.md, ideally by an agent that did not write them. Detects coverage gaps, conflicts, FRAMEWORK.md violations, and plan claims about the code that do not hold, before implementation begins
Use this skill when reviewing or fixing SwiftUI performance issues, including unnecessary invalidation, unstable identity, broad state dependencies, expensive body work, heavy rows, scrolling hitches, layout/drawing cost, or async lifecycle work. Do not use it for general SwiftUI syntax, styling, UIKit-only performance, or generic profiling unless SwiftUI update behavior is central.
TanStack DevTools for debugging Query, Router, and Form state in React apps. Use when setting up devtools, debugging cache state, or inspecting route trees. Use for devtools, react-query-devtools, router-devtools, form-devtools, debug, inspect, cache-viewer.
Critique, audit, or score a Temporal workflow design for correctness, production readiness, and best-practice compliance. Use when asked to review a Temporal architecture, evaluate whether a design is production ready, identify anti-patterns or risks, assess Temporal fitness for a use case, or give a design a thumbs up/down. Not for writing or debugging Temporal code — use temporal-developer for that.
Multi-perspective UX review combining usability heuristics, WCAG accessibility checks, and interaction design analysis. Use when reviewing UI components before release, evaluating user flows for usability issues, conducting design critiques, or auditing accessibility compliance.
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.
Reviews adk-bot pull requests by validating technical correctness against source code, checking PR states and formatting, and following Google's developer documentation style and ADK docs conventions. Triggers on "review bot PR", "check bot changes", or "verify bot issue".
Split a completed PostHog task run into activity records — what the agent tried, whether it worked, what blocked it — and record each one through the report_activity tool. Use when a task asks to analyze a run, produce a task analysis, or review a run from an attached run log. Covers the log query protocol (bounded jq queries over the raw JSONL), both log schemas, the activity schema, and evidence verification. Records facts only; it does not suggest fixes.
Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views, and HogQL catalog metrics: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Metrics support custom SQL checks only. Use when asked to test a model, validate a view, check for nulls or duplicates, add data quality checks, find out why a number looks wrong, or judge whether a warehouse table is trustworthy before using it in an analysis. To describe what data *means* (metrics, certifications, joins), see setting-up-data-catalog instead. Trigger terms: data quality, data test, dbt test, not null check, uniqueness check, freshness check, referential integrity, row count check, validate model, is this table trustworthy.
Biome reference (Rust formatter and linter). Supports JavaScript / TypeScript / JSX / CSS / JSON / GraphQL / HTML (Vue, Svelte, Astro). Covers biome.json, biome check / lint / format / ci / migrate / upgrade, linter rules, presets and domains, GritQL plugins, assist (organizeImports), suppressions (biome-ignore), LSP / VS Code / Zed, ESLint / Prettier migration, monorepos, and CI
Work a Rust crate's recorded issue file to green — one finding at a time, disciplined and sequential: for each finding, write the failing regression test first, apply the smallest correct fix, run the full crate's `cargo test` and `cargo clippy -D warnings`, then mark the finding FIXED / Deferred / Not-a-bug in the issue file before moving on. Never marks a finding fixed without its verification pass, never batches findings, and never buries a warning under `#[allow]` or swaps a real fix for a comment — the issue file and crate state stay in sync after every fix. Use only when the user asks to fix findings from an existing crate issue file.
Review code changes for bugs, security issues, and code quality using OpenAI Codex CLI as an external adversarial reviewer. Use from any agent or provider when the user asks for a code review, wants to check code for bugs or security issues, asks to review a PR, branch, commit, or diff, or says things like "any issues with this?", "review before I push", "check my changes", "look at what I changed", or "review my PR". Tell Codex where to find the code.
Review a Confluent agent skill in this repo against the Agent Skills spec (agentskills.io), Confluent conventions in CLAUDE.md, the PR template gates, and the evals-as-contract rule. Use this skill whenever the user asks to review, audit, validate, or lint a skill; opens or inspects a PR that adds or modifies anything under `skills/`; asks about spec conformance, lazy-loading, frontmatter shape, trigger overlap, or eval coverage; or wants a pre-merge sanity check on skill changes. Do NOT trigger for general code review of application code; security review; auditing schemas, producer/consumer configs, PII tagging, or Terraform generation for Schema Registry (handled by `kafka-schema-registry`); runtime/log analysis of skill behavior (use `tools/skill_review_dashboard.py`); or any changes that don't touch the `skills/` tree.
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Author, scaffold, and run coding-agent-driven tests: Markdown case files executed by a coding agent against a live environment (browser, API, DB, logs, cloud, telemetry) with an auditable PASS/FAIL/BLOCKED report. Use when a deterministic test would be premature, brittle, too expensive, or too narrow.
Runs drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences. Use when the user asks to detect drift or check for consistency across all design documents or READMEs in a directory.
Use when drafting, rewriting, classifying, or improving code review comments as a reviewer. TRIGGER on rough review notes, requests to make comments clearer or kinder, severity labels, "how should I phrase this review comment?", "write review comments", author pushback, or turning findings into PR comments. If role is unclear, ask reviewer or author. DO NOT TRIGGER for full code review, PR descriptions, or author responses unless wording is requested.
Comprehensive SQL statement checking for ClickHouse, supporting multiple kernel versions (24.8, 23.3, 22.3) and two check modes: 1. Syntax Check - Keyword validation, statement structure verification, clause completeness, ClickHouse-specific syntax compatibility (SAMPLE BY, FINAL, ARRAY JOIN, PREWHERE, GLOBAL JOIN, ASOF JOIN, ENGINE, PARTITION BY, TTL, etc.) based on kernel source grammar 2. Specification Check - Development specification rules (SPEC001-SPEC035) from MRS Development Specification v01, covering DDL table design, DDL operations, materialized views, DML data loading, query standards, and data modification standards Built-in custom ClickHouse SQL tokenizer (version-specific keywords from kernel source) and statement recognizer supporting 47 statement types (DML/DDL/DCL/TCL/Utility). Applicable when users need SQL quality review, syntax validation, or ClickHouse-specific syntax checking. Trigger: "Clickhouse SQL check", "CK SQL check", "Clickhouse SQL 校验", "Clickhouse SQL 检查", "Clickhouse SQL specification", "Clickhouse SQL 规范检查", "Clickhouse SQL optimization", "Clickhouse SQL 优化", "检查 Clickhouse SQL"
Use this skill when choosing, running, or interpreting iOS performance profiling workflows, including Instruments traces, signposts, XCTest metrics, MetricKit, Xcode Organizer, hangs, hitches, CPU, allocations, memory graphs, disk I/O, networking, power, or production performance signals. Do not use it as the deep domain skill for launch, SwiftUI, concurrency, perceived performance, or runtime issues unless the task is specifically about measurement, tool selection, trace interpretation, or verification.
Provides comprehensive guidance for JUnit testing framework including test annotations, assertions, test lifecycle, and best practices. Use when the user asks about JUnit, needs to write Java unit tests, use JUnit annotations, or configure JUnit for Java projects.
Test quality validation through mutation testing, assessing test suite effectiveness by introducing code mutations and measuring kill rate. Use when evaluating test quality, identifying weak tests, or proving tests actually catch bugs.
Use when reviewing/judging a finished (or amended) wireframes document — an acceptance gate: can the downstream hi-fi + UI engineering build the screen structure from it. Judges a TEXTUAL markdown wireframe against a single-sourced buildability + coverage + composition bar: every flow-named screen/state covered with quality states; layout unambiguous on a grid + shared app-shell meeting an objective layout-quality bar; real + consistent components; affordances + data-display annotated; microcopy intent (no data-model leak in labels); screen-composition a11y (landmarks/focus-order/target-size) — pixel contrast/focus-appearance are the design-system's, not judged here; responsive; gaps surfaced; structural not hi-fi; an amend reviewed as a scoped versioned delta. Emits `VERDICT: approve|revise` + actionable findings; approves a doc meeting the bar (no false-revise on a thin screen), revises only on a named gap. Not for authoring, the navigation graph (user-flows), the visual tokens (design-system), or hi-fi.
Perform language- and framework-specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best-practice guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
Writes and maintains Storybook stories and interaction tests using CSF3 format. Covers component stories, play functions, visual regression testing with Chromatic, and accessibility testing. Use when creating component documentation, writing interaction tests, debugging test failures, configuring visual snapshots, or updating story structure. Use for CSF3, play functions, userEvent, Testing Library queries, Chromatic configuration, autodocs, MDX.
Diagnose root causes with a four-phase debugging protocol. Use for ANY technical issue — test failures, production bugs, unexpected behavior, performance problems, build failures, or integration issues. ESPECIALLY when under time pressure, when "one quick fix" seems obvious, or when previous fix attempts have failed. Do not use this skill for unrelated requests; route to the nearest named specialist.
Reproduce TON bugs on a local tontester network. Use only when the task involves launching tontester validators, deploying contracts to a local network, or comparing patched validator builds — not for general TON development or testnet interaction.
Gates whether a code comment should exist and forces the ones that stay to explain why, not what. Use ALWAYS before writing or editing a comment in any language (Python, TypeScript, Go, Rust, SQL), and when reviewing a diff that adds comments. Removes the comment types that clutter the codebase: narration that restates the code, change-history and chat-context notes ("previously did X", "per PR #123", "AI:"), perishable measurements and current-state stamps ("~20 min build", "currently", "today"), commented-out code, and redundant docstrings. Keeps the ones that earn their place: a non-obvious why, a warning about a non-local consequence, a pointer to context a future reader can't reconstruct. Not for user-facing copy (see `/writing-user-facing-copy`) or commit messages.
Design and build an Antithesis workload for a specific feature: analyze the feature, discover its testable properties, build a self-driving workload that runs locally and in Antithesis, and iterate until the feature's behaviors are exercised and its invariants are checked.
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.