Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules. Load when handling untrusted tool results, guarding a write tool, or scoping what an agent remembers.
The reference presentation-tool contract, covering server-side enrichment, suggestion chips, the event stream, progressive rendering, both roles' built-in components, and adding a vertical component. Load when building or reviewing how a commerce agent's output reaches a frontend.
Commit the current work — runs the quality, consistency and passport gates, branches off main if needed, stages specific files, and writes a commit whose subject states what is now true. Pushes and opens a pull request only with --pr or when the user asks; never merges — a merge happens only when the user explicitly says to merge. Use ONLY on explicit commit intent — user says "commit", "let's commit this", "open a PR", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Never force-pushes or skips hooks.
Use when designing or auditing onboarding, activation flows, habit loops, pledges, public commitments, progressive profiling, retention programs, behavior-change plans, pricing flows, or lowball-risk funnels where consistency pressure may shape user decisions.
Build and deploy the Goldsky Compose compliance-oracle example under the user's own account — a compliance-gated payment system where a smart contract holds funds in escrow, Compose screens the sender wallet via a compliance API (Webacy recommended, or bring-your-own / mock), then calls back to approve or reject. Supports two payment models: single-payee (payment gateway — funds go to a configurable recipient) and multi-payee (P2P — sender specifies recipient per transfer). Ships a second cron task that reconciles stuck transfers. Triggers on: 'build a compliance oracle', 'compliance-gated payments', 'AML screening onchain', 'KYC payment gateway', 'escrow with compliance check', 'wallet screening oracle', 'gated transfers', 'Webacy oracle', 'P2P compliance', 'payment gateway with screening'. The escrow contract's approve/reject are oracle-permissioned, so there is no shared no-deploy contract — each user deploys their own instance bound to their oracle wallet (recommended path: Base Sepolia + a MockUSDC). The oracle is a named Compose smart wallet (`compliance-oracle-wallet`, gas-sponsored) with no private key to manage on the default path. For a custom/novel Compose app, use /compose. For debugging a deployed app, use /compose-doctor. For manifest/CLI/API field lookups, use /compose-reference.
Generate a graded exercise set — easy to advanced — that lets a learner verify whether they actually understand a topic, concept, method, derivation, or paper, with solutions kept in a separate file for honest self-testing. Use whenever the user says "give me exercises", "quiz me on X", "test whether I actually get this", "problems from easy to hard", "practice questions with solutions", "how do I check if I understood this", or wants a self-check after learning something. Produces two artifacts: an `exercises.md` (problems only, tagged by difficulty tier and concept) and a `solutions.md` (worked answers plus a self-check rubric and a pointer to what to revisit on a miss). This skill builds the verification material; it does not teach the concept (use professor-mentor-technical-teaching for that) and it does not sequence a learning path (use flow-learn-new-topic for that). It is one of the assessment steps those flows hand off to at an exit gate (the other being a discussion round).
Integrate or upgrade the Contentsquare React Native SDK -- Session Replay, screen tracking, transactions, analytics, masking, privacy opt-in/out. Always starts with a mandatory Contentsquare project healthcheck (ask for the data source IDs or resolve the Android and iOS bundle ids, call the healthcheck endpoint, report project health) before any other work. Use when working with Contentsquare, CSQ, StartConfig, AnalyticsOptions, CSQMask, CSQWebView, @contentsquare/react-native-bridge, or migrating from the legacy `Contentsquare` API to `CSQ`.
A topic router for the AI Engineering from Scratch course. Give it a topic, question, or bug you're working on, and it will point you to the exact lesson that teaches it and the next right command. Trigger phrases: “where to learn,” “which lesson covers,” “course navigation,” “I'm stuck on,” “what should I do next,” “teach me MCP,” “teach me Agent Skills,” “where to prepare for Claude certification,” or "where do I learn", "which lesson covers", "course guide", "I'm stuck on", "what should I do next", "teach me MCP", "teach me Agent Skills", "where do I prepare for a Claude certification"
Fetches structured public web data through Crawlora's hosted REST API, including broad search, bounded web crawls, and durable cross-corpus research jobs. Calls require a user-provided API key and successful requests may consume credits. Use for public prices, listings, reviews, transcripts, SERPs, trends, financials, and places.
INVOKE THIS SKILL IMMEDIATELY when user asks to: write/create/build a Nextflow pipeline or workflow, create any bioinformatics pipeline (RNA-seq, DNA-seq, variant calling, ChIP-seq, etc.), or compose/chain Nextflow modules (process or workflow modules) from the Nextflow Registry. This skill handles all Nextflow workflow creation tasks.
Use when building a catalog backend module that ingests entities from an external source (e.g. Azure DevOps, internal API, JSON file). Covers both the normal EntityProvider and the IncrementalEntityProvider for large-volume sources, plus module wiring via catalogProcessingExtensionPoint or incrementalIngestionProvidersExtensionPoint. Triggers on phrases like "catalog provider", "ingest entities from X", "import entities from <source>", or "incremental ingestion".
Route mixed, ambiguous, cross-modal, or workspace-management requests through Creative Claw. Use when the user asks to use Creative Claw generally, needs several media types, or asks about account balance and past charges, saved assets, brand themes, the curated examples catalog, or onboarding; prefer a focused skill for one clear outcome.
Design and audit creator, listing, plugin, skill, app, marketplace, content, or community ranking quality across relevance, quality signals, freshness, fairness, fraud resistance, diversity, monetization, review abuse, creator trust, and user outcomes. Use when marketplaces need discovery/ranking systems that reward quality without becoming pay-to-win or spam-prone.
Cross-platform Agent task coordination hub. This skill should be used when Agents on multiple different platforms need to distribute tasks around a project task source, mark ownership, route by capability, and hand off context. Do not use for local parallel execution within a single platform, or for Git branch, commit, PR and merge safety rules.
Methodology for cross-domain attack chains between web and AI. Use when the target system contains both traditional web applications and AI/LLM components, and you need to assess the impact of web vulnerabilities on the AI system or the impact of AI vulnerabilities on the web system. Covers bidirectional attack chains: Web→AI (XSS to steal conversations/SSRF to call model APIs/SQLi to poison RAG/RAG poisoning via file upload) and AI→Web (injection generating stored XSS/agent executing SQL commands/tools reading sensitive files/sandbox escape RCE).
Design or sharpen a commercial offer from customer evidence, the actual product boundary and, when useful, competitor ad research. Use for front-end offers, paid discovery products, webinars, price ladders, order bumps, upsells, high-ticket pathways, positioning and offer-message decisions.
Research a product idea before committing it to a CodeSpring build plan. Finds direct competitors, open-source projects, substitutes, and relevant platform capabilities; separates commodity features from a defensible wedge; then records an evidence-backed recommendation and creates only the scoped feature and tasks worth building. Use when the user asks whether an idea already exists, requests market or competitor research, asks what would make a product unique, or wants to validate an idea before creating a PRD or tasks.
Anime character skill distiller. Give a character name and work title: it retrieves core material locally → cross-validates → distills behavior → generates a runnable, traceable, updatable character Skill. Trigger words: "generate XX's skill", "distill XX", "make an XX character", "turn XX into a skill", "create an XX", "/csp". Vague requests also trigger: "I want to chat with a tsundere character", "any yandere recommendations", "help me make a character from XX". Requires Python; core sites use local scripts first, while web search skill / MCP / WebFetch only supplement and serve as a fallback on failure.
Review documents, proposals, and plans through the lens of a CTO. Simulates feedback from a technical leader who has built and scaled multiple companies and values platform thinking, mobile-first craft, and iterative execution. Use when you need engineering leadership review: platform strategy, architecture decisions, team structure proposals, or anything that needs a 'will this scale and can we ship fast?' lens.
Second step of the content creation pipeline: turn fragmented judgments into one closed chain of question relay. Input: fragment draft + why; output: closed chain (nodes marked by status, keyhole markers, density ledger). The AI leans proactive: propose chain candidates, point out breakpoints, compute the density ledger. The judgments themselves can only come from the user. Triggers: /cuihuo-logic-chain, "碎片有了帮我理链", "梳理逻辑链", "理一下结构"
Find out why clients actually hire a B2B service company, using evidence the company already owns: won-deal call notes, client interviews, case studies, named testimonials, Clutch or GoodFirms reviews, LinkedIn recommendations. Produces hire reasons ranked by how many clients name them, the events that started each search, what clients tried before, quotable proof numbers, a bank of the clients' own phrases, honest weak spots and the alternatives they weighed. Use when asked "why do clients pick us", "what do our clients say about us", "analyze our customers", "find customer pain points", "client language for messaging", "our positioning from reviews", or before writing ICP, personas, site copy or outbound sequences. Vendor-side research across your own client base. For ONE company you want to sell to, use `account-dossier`
Research-backed customer persona creation with market data and avatar generation. Covers demographics, psychographics, jobs-to-be-done, journey mapping, and anti-personas. Use for: marketing strategy, product development, UX research, sales enablement, content strategy. Triggers: customer persona, buyer persona, user persona, target audience, ideal customer, customer profile, audience research, user research, icp, ideal customer profile, target market, customer avatar, audience persona
Debug Flutter applications systematically with this comprehensive troubleshooting skill. Covers RenderFlex overflow errors, setState() after dispose() issues, null check operator failures, platform channel problems, build context errors, and hot reload failures. Provides structured four-phase debugging methodology with Flutter DevTools, widget inspector, performance profiling, and platform-specific debugging for Android, iOS, and web targets.
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.