Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Write tests, mock functions, assert values, and configure test suites for Roblox/Luau code using Jest Roblox — a Luau port whose API diverges from JS Jest in subtle, non-obvious ways that LLM training data does not cover. Use whenever encountering Jest in Roblox/Luau code: editing .spec test files, calling jest.fn/jest.mock/spyOn, using describe/it/expect, or debugging Jest tests.
Get an independent verdict on an AI-proposed plan, fix, architecture, or claim by verifying its premises against the real artifact, then dispatching a panel of fresh models from different providers that answer independently. Use for "double check", "proof this", "are you sure", "second opinion", "am I right or is he right", "this still isn't working", or "not sure this is the right approach".
Write OpenTofu modules and tests for homelab infrastructure (infrastructure/modules/). Use when: creating new modules, writing or modifying .tftest.hcl test files, adding variables/outputs/resources, debugging test failures, or questions about tftest syntax. Triggers: "opentofu module", "terraform module", "tofu module", "create module", ".tftest.hcl", "tftest", "test my module", "module test", "infrastructure test", "variables.tf", "outputs.tf", "module testing", "assertion", "task tg:test", "test-config"
End-to-end testing patterns for Blazor applications using Playwright, including component testing and page navigation. Use when writing E2E tests for Blazor applications, testing Blazor component interactions with Playwright, or setting up Playwright testing infrastructure for Blazor apps.
Tracking and metrics design generator. Starting from product requirements or the core user journey, output a complete tracking plan document (events, fields, trigger timing, metric definitions, QA validation checklist). Trigger conditions: the user mentions keywords such as "tracking", "event design", "data collection", "reporting plan", "tracking plan", "event spec", "field design", "metric definitions", "data acceptance", or "QA validation". Also applies when: the user provides a product PRD or requirements document and asks for a tracking plan; the user provides a core user journey and asks to break down events; the user asks to standardize event naming or field definitions; the user asks to design a data acceptance plan. Typical input: event naming spec + field dictionary + core journey description/flowchart. Not applicable to: pure data analysis (use pm-analytics), pure BI dashboard building, or pure SQL query writing.
Focused pull request review practices with severity-ranked, file-and-line-cited findings across four angles: security, performance, tests, and architecture. Use when asked to review a pull request, review a diff or set of changes, review "this PR," or provide a code review before merge.
Execute, inspect, and rerun an existing Promptfoo redteam scan. Use for generated YAML, result exports, attack success rates, grader/target errors, filtered reruns, and CI gates. Use promptfoo-provider-setup for connections and promptfoo-redteam-setup for new scan plans.
Facilitate methodical review of proposals (technical designs, product specs, feature requests). Use when asked to "review this proposal", "give feedback on this doc", "help me review this RFC", or when presented with a document that needs structured feedback. Handles markdown files, GitHub gists/issues/PRs, and other text formats. Chunks proposals intelligently, predicts reviewer reactions, and produces feedback adapted to the proposal's format.
Complete Python gotchas reference. PROACTIVELY activate for: (1) Mutable default arguments, (2) Mutating lists while iterating, (3) is vs == comparison, (4) Late binding in closures, (5) Variable scope (LEGB), (6) Floating point precision, (7) Exception handling pitfalls, (8) Dict mutation during iteration, (9) Circular imports, (10) Class vs instance attributes. Provides: Problem explanations, code examples, fixes for each gotcha. Ensures bug-free Python code.
Complete Python testing system. PROACTIVELY activate for: (1) pytest fundamentals, (2) Fixtures and scopes, (3) Parameterized tests, (4) Mocking with pytest-mock, (5) Async testing with pytest-asyncio, (6) Coverage configuration, (7) FastAPI testing with httpx, (8) Property-based testing with hypothesis, (9) Snapshot testing. Provides: pytest patterns, fixture examples, mock setup, coverage config. Ensures comprehensive test coverage with best practices.
Design, exercise, and evidence graceful degradation, disaster recovery, and restoration behavior across systems and dependencies. Covers failure-mode analysis, RTO/RPO decision records, restore testing, game days, failover drills, data integrity verification, and recovery communication. Do not use for live incident command or incident response; route to site-reliability-engineering for those. Do not use for infrastructure implementation details; route to platform-engineering.
Use when the user wants to anticipate reviewer questions, select the strongest ablations to present, prepare rebuttals, or identify paper weaknesses before submission. Triggers on phrases like "reviewer questions", "anticipate reviewers", "rebuttal", "paper weaknesses", "defend the paper", or "strengthen the paper".
**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.
Set up CI so every pull request gets a Testomat.io run scoped to the code it changes. One job runs after the deploy — it creates the run and launches the affected tests into it. Use when the user wants to integrate Testomat.io runs into a CI pipeline, create test runs per pull request, or set up change-aware testing that triggers affected tests from CI events.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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
Use this skill to structure a Jetpack Compose UI test class the way androidx itself writes them — `@MediumTest` + `@RunWith(AndroidJUnit4::class)`, a single `createComposeRule(StandardTestDispatcher())` rule, hoisted `mutableStateOf` declared above `setContent { }`, and the Test → Find → Assert → Act → Re-assert flow. Covers when to use `createAndroidComposeRule<MyActivity>()` for custom Activities, how to drive state from outside the composition via `runOnIdle { }`, why state must NOT be hoisted inside `setContent`, and why `@get:Rule createComposeRule()` and `runComposeUiTest { }` MUST NOT both appear in the same test. Use when the developer asks "how do I write a Compose test", "where do I declare state", "how do I name the test class", "MediumTest vs LargeTest", "rule.setContent inside @Before", or shows a test class that won't compile or doesn't drive state from outside.
Expert SystemVerilog guidance for RTL, interfaces, and verification-adjacent code with EDA-friendly design patterns. Use when designing, reviewing, or refactoring hardware-oriented SystemVerilog and when spotting HDL antipatterns that cause timing, lint, CDC, or tool-flow pain.
Use this skill to gate DDD and ubiquitous-language quality with a pass/fail adversarial review — a single blind reviewer subagent judges a diff, a module/bounded context, or a DSL/semantic-model surface against 20 decidable rules across glossary lifecycle (a recorded ubiquitous language is required once domain concepts exist — absence is FAIL; code must conform; entries stay live and carry business meaning), language consistency (one name per concept, one meaning per name, no Manager/Helper/Data names on domain rules, transitions named as operations, one vocabulary across code, tests, docs, UI copy), domain model integrity (anemic models, valid-on-construction, value types over primitives, named states over flag piles), context boundaries (foreign-model reach, vendor-type absorption, infrastructure in the domain, multiple writers), and DSL surfaces. Language-agnostic; repeated runs converge code, team, and stakeholders on one recorded vocabulary. Verdicts only.
Code-quality gate and coding guardrail for AI coding agents. Always invoke when you finish editing and prepare to hand control back, even if the user did not explicitly ask. Trigger on commit, push, PR, or phrases like any slop, remove slop, review my code, run aislop, or score my code. Scans with aislop, fixes what is mechanical, addresses the rest in-session in the project style, then reports what changed
Conducts comprehensive architecture design reviews including system design validation, architecture pattern assessment, quality attributes evaluation, technology stack review, and scalability analysis. Produces detailed review reports with findings, recommendations, and risk assessments. Use when reviewing software architecture designs, validating architecture decisions, assessing system scalability, evaluating technology choices, or when users mention architecture review, design assessment, technical review, or architecture validation.
Backend security review and hardening for authentication, authorization, tokens, sessions, secrets, validation, injection, payments, uploads, webhooks, data exposure, rate limits, and deployment configuration. Use when asked to audit, security-review, harden, threat-check, or inspect backend code for vulnerabilities across Express, NestJS, Django, Rails, Go, and other stacks.
Render a production-readiness GO/NO-GO grid for a database — runs a read-only audit, then maps the findings onto a fixed launch checklist (PITR/backups, RLS on tenant tables, FK indexes, money-as-numeric, timestamptz/UTC, connection pooling sized, migration reversibility, secrets-not-in-schema, charset/utf8mb4). Each row is PASS/WARN/FAIL/NEEDS-LIVE with the finding id, topped by a plain-language verdict. Read-only. Use when the user asks if a database is production-ready, ready to launch/ship, a go/no-go, a pre-launch or readiness checklist, or what to fix before going live.
Orchestrator drives, Codex codes. Execute an approved plan one task at a time: your agent (Claude Code, etc.) sequences the work, briefs OpenAI Codex to write ALL product code, reviews every diff, runs the test gate BEFORE each commit, commits one task per commit, and opens exactly ONE PR at the end. Use when the user says 'codex-build', 'have codex code it', 'you orchestrate, codex codes', or hands over a plan for step-by-step implementation.
Validate that claims in documentation match codebase reality. Extracts verifiable assertions (file paths, commands, function references, behavioral claims, dependencies) from markdown docs and checks them against the actual project. Use after code changes, before releases, or when docs feel untrustworthy.
Validate the SDD corpus - cross-document references, orphans, cumulative-tag gaps, duplicate IDs, and full bidirectional traceability (with optional repair), plus a prose/terminology pass. Use before releases, after batch generation, or to validate and repair the corpus.
Periodically audit a repository's docs for staleness against the implementation: run a cheap mechanical scan (dead source-path references, dead links, leftover DEPRECATED/TBD banners, doc-vs-code freshness gap, git-invisible ignored leftovers, completed-but-undeleted plan files), then dispatch parallel read-only agents to verify only the suspicious docs against source, and finally propose update / delete / migrate-to-ADR dispositions for user approval. Use on a monthly or quarterly docs review, after large refactors or renames, or when asked whether docs are stale.
Entry point for the CodeStable skill engineering loop. Triggers: writing or modifying a cs skill, evaluating skill effectiveness, quantifying across models/agents, optimizing skill prompts, or consolidating conclusions back into a skill. Internally drives author, eval, optimize, release.
Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the spec', 'evaluate the run'. Runs mechanical checks, a semantic review per criterion, and multi-model consensus when uncertain. With execution.auto_evolve on (the default), a rejected result with a Seed continues into a Ralph fix loop; pass auto_evolve: false to verify only.
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.