Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Senior-engineer coding standard for Bun/TypeScript, Next.js, and Java (Quarkus) repos. Enforces strict TDD (primary-port SUT, hand-written fakes, no mocks), Clean Architecture (`src/{domain,use-cases,infra,presenter,composition}`), `Result<T, E>` at IO boundaries, branded types at trust boundaries, Bun-only or Maven toolchains (no `class`/`function` declaration/`interface`/`console.*` in TS), Atomic Design, a logic-free design system (no Tailwind in app code), and production disciplines covering privacy (no PII in logs/URLs), tenant isolation, IO deadlines, soft-delete, expand-contract migrations, optimistic locking, observability, AI ports with evals, delivery, accessibility. Use for ANY code task in a Bun, Next.js, or Java repo, covering writing, scaffolding, testing, refactoring, review, React components, APIs, persistence, debugging, security. Consult even when conventions are not mentioned; rules are non-negotiable; violations are rewritten.
Specifies best practices, including following RESTful API design principles, implementing responsive design, using Zod for data validation, and regularly updating dependencies. This skill promotes modern coding standards and helps developers write consistent, maintainable code.
Generates a runnable lead-generation or enrichment script against the official Blitz SDK (blitz-api-py or blitz-api-js), installs it with the best available package manager (uv or pip for Python, bun or npm for JS/TS), and adds API-key safety, baseline error handling, and correct pagination including partition-for-scale. Use when the user wants to turn a GTM brief into working code, scaffold a Blitz People/Company/Employee search or email/phone enrichment job, or says "write the script", "build the integration", or "generate code for this ICP". Consumes a gtm-brief.yaml from blitz-gtm-brainstorm or works standalone.
Reviews a Blitz API integration against the live Blitz docs before you run it. Confirms the Blitz MCP is installed (and pushes to add it), checks the blitz-api SDK and the Blitz skills are on the latest version, scans your project for wrong SDK methods, malformed request bodies, and case-sensitive enum typos by validating each call against the MCP's OpenAPI specs and normalization pages, and reads your API key's per-endpoint rate limits and credits to flag throughput left on the table. Reports a pass/warn/fail checklist and applies each fix only after you confirm. Use when the user says "review my Blitz integration", "audit my Blitz code", "check my Blitz setup", "is my Blitz usage correct", "preflight my Blitz job", or before running a Blitz job at scale.
Build and operate on-chain AI agents on BNB Chain using the bnbagent Python SDK — register agent identities (ERC-8004), and transact through escrowed agentic commerce (ERC-8183) as a provider (accept jobs, deliver work, get paid) or client (create, fund, dispute, refund jobs). Also covers x402 micropayment signing. Use for anything involving BNB Chain agent identity, agent-to-agent paid jobs, BSC escrow jobs, or ERC-8004/ERC-8183/x402.
The worker's router in a repository run by the Boring Factory. Use at the start of every task from a work packet (a task issue, its acceptance lines and their proof): it picks the playbook, the principles and the proof the pull request must carry. Adapted from pstack's poteto-mode.
Author a PostHog canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and focused experiments where React components add no useful structure. Use after building-canvases has routed a canvas request to a plain-HTML/browser-API implementation. Covers the thin component wrapper the current runtime requires, styling and theming without Quill, drawing surfaces, and animation/cleanup patterns.
Build UIs using IBM's Carbon Design System. Use when the user requests Carbon-styled interfaces, IBM-style dashboards, enterprise UIs following Carbon conventions, or explicitly mentions Carbon, IBM design, or @carbon/react. Covers component usage, design tokens (color, typography, spacing, motion), theming (White, Gray 10, Gray 90, Gray 100), grid layout, and accessibility. Supports both artifact/HTML output (CDN-based) and full React project output (@carbon/react). Triggers include "Carbon", "IBM design system", "enterprise dashboard", "@carbon/react", "carbon components", or requests for IBM-style professional interfaces.
This skill should be used when the user asks to "record a terminal demo", "generate a CLI demo GIF", "make a vhs recording", "create a terminal GIF for the README", or "capture a CLI walkthrough as a GIF". Generates CLI demo GIFs using vhs (Charmbracelet) for README files and documentation.
Use when the user asks to improve, add, or clean up code comments, focusing on WHY over WHAT. Reads specified files (or recently modified ones), adds strategic inline comments for non-obvious logic, removes redundant ones, and converts WHAT-comments to WHY-comments. Accepts optional $ARGUMENTS for target files.
Use when running a systematic open-source prior art survey for a software idea — deriving a keyword map (typed search vocabulary) or executing one search angle of repository discovery across code hosts, package registries, curated catalogs, code search, alternative directories, and community channels. Produces schema-validated artifacts: a keyword-map file or a per-angle search-output file with reproducible coverage records and candidate repositories — or deep-reading one candidate into an EXTRACTION (a 10-section analysis + a machine-readable verdict/score/license/deps block). Keywords: prior art, open source search, repository discovery, keyword map, code extraction, competitor alternatives. Covers the survey's SEARCH wave (keyword-map derivation + angle execution), the EXTRACT wave, and the SYNTHESIS wave (aggregating extractions into a report + a borrow-index).
Engineering-discipline toolkit for non-technical users working with AI coders. Wields KISS, DRY, YAGNI, fail-fast, and idempotency as commands. Use when the user asks to audit, simplify, clean up, dedupe, or harden code; or says "make this simpler", "any duplicates?", "is this safe to run twice", "explain this app", "find dead code", "simplify the plan", or "find silent failures".
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
Use when starting a new Spring Boot 4 project — scaffolding a service, REST API, or modular backend; picking an architecture (layered, package-by-module, modular-monolith, tomato, DDD-hexagonal); selecting Spring Boot 4 features; or applying the bundled templates and references in this skill. Not for migrating existing projects or for isolated JPA/repository work without broader project-creation context.
Reference skill for building production-ready crw integrations. Covers verb selection, call surfaces (CLI/MCP/REST), post-filtering strategies, context-window hygiene, Hybrid RAG patterns, common pitfalls, and crw-specific operational considerations (search backend limits, renderer pool, proxy rotation). Load this when writing application code that embeds crw, designing a multi-step agent workflow, or debugging an integration that isn't behaving as expected.
Coming from Firecrawl? Switch to fastCRW in one line. Use when the user has existing Firecrawl SDK code (firecrawl-py, firecrawl-js, REST calls, or an MCP config) and wants to point it at fastCRW — managed or self-hosted. Covers the exact base_url swap, which endpoints are drop-in, which have gaps, and how to verify the switch worked.
Unified upstream repo operations: audit commit drift, detect repo overlap with local project, and perform sync maintenance. Use when: reviewing upstream updates, evaluating a new repo for integration, updating last-sync.yaml after sync. Applies to requests written in English or Chinese.
Generate diagrams from declarative text using D2 - modern text-to-diagram language with automatic layouts, themes, and advanced styling. Use when creating architecture diagrams, flowcharts, decision trees, workflow diagrams, sequence flows, or ERDs from text definitions.
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship instead.
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to disk, run /ork:design-import instead.
Establish the mechanism behind a hard, intermittent, recurring, or performance failure from a faithful reproduction or distinguishing runtime evidence. Use when the user asks to diagnose or debug, or when an authorized repair remains causally uncertain after direct inspection; do not use for simple factual questions, obvious local failures, proactive audits, or routine test fixes.
Move Django performance-sensitive Python loops into database-side computation with annotations, aggregates, filtered aggregates, F expressions, functions, Subquery, OuterRef, Exists, Window expressions, db_default, and GeneratedField. Use when Django code counts, sums, filters, flags, ranks, or derives values in Python after fetching rows.
Model, migrate, refresh, and verify PostgreSQL materialized views in Django for expensive report or dashboard queries that can tolerate stale data. Use when ORM/index/query rewrites are not enough, the result is read often, freshness can be bounded, and a Django app needs unmanaged models, RunSQL migrations, refresh commands, or concurrent refresh.
Improve Django and Django REST Framework pagination for large querysets using bounded page sizes, stable ordering, indexed ordering, offset limits, keyset pagination, DRF CursorPagination, and count-query tradeoffs. Use when list pages, admin views, APIs, exports, or infinite scroll become slow, inconsistent, or memory-heavy as result sets grow.
Read and compare Django/PostgreSQL query execution plans using QuerySet.explain(), EXPLAIN, EXPLAIN ANALYZE, scan types, joins, estimates, actual timing, buffers, and row counts. Use when one SQL query dominates Django latency or when an index, ORM rewrite, pagination change, or materialized view needs proof from a query plan.
Find the Django ORM code and request path responsible for slow SQL by using APM traces, slow query logs, Django Debug Toolbar, query logging, and local reproduction. Use when a Django database performance issue is suspected but the exact queryset, view, serializer, template, or job causing it is not yet proven.
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST URLs, IAM policies, and S3 mocking for tests. Trigger terms: django-storages, S3, boto3, S3Boto3Storage, STORAGES, presigned URL, CloudFront, media files, collectstatic, AWS_STORAGE_BUCKET_NAME.
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.