Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image
Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image
Universal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, GitHub Releases, annotated tags, historical release backfill, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送", "release notes", "GitHub Release", or "回填 Release".
This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", "refined translation", "精细翻译", "proofread translation", "快速翻译", "快翻", "这篇文章翻译一下", or provides a URL/file with translation intent. Supports three modes (quick/normal/refined) with custom glossary support.
MANDATORY recipe for every Caffeine build that sends email through the user's own Gmail account. The ONLY supported path is the `googlemail-client` mops package (Gmail REST API) combined with the `google-oauth` mops package (token exchange + refresh + PKCE). Hand-rolling `ic.http_request` calls to `oauth2.googleapis.com` or `gmail.googleapis.com` is a FORBIDDEN anti-pattern — it bypasses bearer auth, replication-cost safeguards, and the `google-oauth` library's percent-encoding and JSON parsing. Load this skill whenever the user, spec, or any prior task mentions sending email, Gmail, "notify via email", "forward results by email", or any equivalent phrasing — and BEFORE writing any code that touches a Google endpoint.
Quick reference for the Caffeine Data Intelligence agent to query an OQL-exposing canister (schema() + execute()) through the `icp` CLI against the project's `backend` canister: read the schema, form JSON queries (filter / order / paginate / aggregate / dotted-path edges), and parse the Candid result rows.
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice design, voice replication, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. Covers SDK usage and best practices for Gemini models and agents in Python and TypeScript.
Extracts existing constraints and asks only about information that affects execution or acceptance, turning vague wishes into actionable, verifiable delivery goals. Use when the user wants to clarify what to produce, its boundaries and acceptance criteria. Does not replace concept breakdown or reframing research questions.
Create, record, edit, replay, or repair reusable Argent flow YAML files. Use when the user asks to record or replay a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-flows. Also use before repeating three or more interactions. For one-off UI checks, acceptance-driven regression tests, or screen video, use argent-test-ui-flow, argent-qa-flows, or argent-screen-recording respectively.
Audit project rule files, identify the source of truth, standardize naming, and generate bridges to migrate a project into a consistent cross-platform Agent workspace. Use when users ask to migrate Claude Code, Codex, Grok, or general Agents, or organize AGENTS.md.
Interactively guide a user through PR review comments one at a time, collect a decision for each comment, then post agent-authored replies on GitHub and resolve review threads after the user approves a preview. Use only when the user wants to reply to or resolve review threads on GitHub. Skip when the user only wants comments fetched or displayed (use `pr-comments`), or only wants code changes made without posting anything back to GitHub.
Validate that a branch or pull request implementation matches introduced product, technical, security, and related specs. Use when reviewing or finishing a spec-driven change and resolving mismatches between checked-in specs and implementation.
WeCom online doc document skill. Create new docs, import local .doc/.docx/.txt files as docs, read doc content, and append to or overwrite docs. Use this skill only when the user explicitly mentions strong type-specific terms such as “doc,” “docx,” “word,” “online document,” or “office document,” or provides a https://doc.weixin.qq.com/doc/xxx link. For generic requests such as “document,” “create a document,” “write a document,” “organize this into a document,” or “output to a document” without specifying a type, always use wecomcli-smartpage.
Use when the user wants to plan, run, sponsor, speak at, or get pipeline from events — webinars, conferences, trade shows, meetups, dinners, workshops, virtual summits, or user conferences. Also use when the user mentions 'event marketing,' 'field marketing,' 'run a webinar,' 'webinar funnel,' 'show-up rate,' 'should we sponsor,' 'sponsor a conference,' 'trade show booth,' 'booth strategy,' 'event ROI,' 'badge scans,' 'event follow-up,' 'speaking slot,' 'CFP,' 'conference talk,' 'host a dinner,' 'user conference,' or 'virtual summit.' Covers all four roles: hosting, sponsoring/exhibiting, speaking, and attending. For product launch moments, see launch. For the partnership side of joint webinars, see co-marketing. For ongoing community programs, see community-marketing. For podcast appearances, see public-relations. For the email sequences themselves, see emails.
Find the papers that answer a research query in Firecrawl's research paper index — a corpus of paper abstracts whose largest share is biomedical and life-science literature (PubMed, bioRxiv, medRxiv), alongside arXiv preprints in CS, physics, and math — using semantic search, semantic and structural expansion, and in-body verification. Use this skill for literature-finding and paper-retrieval tasks of any kind, including clinical, biomedical, drug, gene, disease, and other life-science questions, whether the answer is a single paper or a full multi-paper set. The index is reached only through the `firecrawl_research_*` MCP tools or the `firecrawl research` CLI subcommands. Calling `firecrawl_search` with its `categories` option set to `["research"]` is a different feature — it filters ordinary web search to research-affiliated websites (the list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites) and returns page results from them, without querying the paper records in this index.
Use wecom-cli to search the WeCom address book by name, pinyin, English name, or alias, and retrieve matching users’ userid, department, and job title. Use to find contacts, distinguish people with the same name, retrieve a user’s userid, and list all people with the same name.
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or when debugging dependency cycles between application layers.
WeCom meeting management. This skill handles “online meetings”—meetings with an online meeting link (including a meeting ID or join link, with remote or video attendance)—including creation, lookup, search, details (meeting information, minutes, to-dos), full meeting transcript (verbatim speech record), updates, and cancellation. If the user wants a “calendar event” without an online meeting link (including an in-person meeting), use the wecomcli-calendar skill instead. If the user only says “meet,” “schedule a meeting,” or “that meeting” without specifying whether they mean a calendar event or online meeting, first read this skill and follow its disambiguation process to ask the user; do not assume and create one directly.
Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet of drawers, a plotter, a lock), with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint and live readout, and calm eased motion. Use this whenever someone wants an isometric illustration, an explanatory diagram or figure for docs, a blog post, a landing page or an article, a "Linear-style" or "premium" technical drawing, an interactive explainer, or an SVG that shows how a system, algorithm or component works, even if they never say "isometric". Works framework-free (TypeScript/JS that writes SVG and HTML) and in React/Next.js, and can add realistic WebGL shaders (fire, exhaust, water, caustics, lamp light) that live inside the drawing in the same isometric perspective. Also prints a figure as an A4 PDF (poster, drawing or handout) and publishes it to the Anatomy community gallery when asked.
ACCESS-GATED beta. Deepline Monitors are provider event feeds (job posts, email replies, funding, intent) that stream into your warehouse and trigger plays. Only use if you have monitor access: run `deepline monitors status` first; if it reports no access, do NOT use this recipe — tell the user to contact the Deepline team.
Break a topic into a series of learning articles, then adjust the depth, angle, and pace of later articles based on user feedback. Use when the user wants to study a topic systematically, continue with the next article, or adjust the course based on feedback.
Build and submit iOS and Android apps with EAS to TestFlight, the App Store, or Google Play. Supports Expo and other React Native projects, plus existing native apps. Use for eas.json setup, release pipelines, signing, app versions and build numbers, store submissions, and listing metadata. For Expo websites and API routes, use eas-hosting; for adding React Native screens to a native app, use expo-brownfield
Work with the @upstash/redis TypeScript/JavaScript SDK, a serverless HTTP-based Redis client for Next.js, Vercel, Cloudflare Workers, edge runtimes, and Node.js. Use when adding a cache (cache-aside, write-through, TTL and expiration strategies), session storage and user sessions, a key-value store, leaderboards and rankings with sorted sets, counters, distributed locks, queues with lists, streams and consumer groups, sparse index-addressed arrays and ring buffers (ARSET, ARINSERT, ARRING, ARGREP, AROP), embeddings and nearest-neighbour vector search stored inside Redis (VECTOR commands via redis.vector, separate from @upstash/vector), JSON documents, pipelines and MULTI/EXEC transactions, Lua scripting, read replicas, or full-text search, typo-tolerant search, facets, aggregations, and search over Redis stream entries with Upstash Redis Search (different from regular FT.SEARCH; also available for TCP clients via @upstash/search-redis and @upstash/search-ioredis). Also use when migrating from ioredis or node-redis, when a Redis connection is needed from a serverless function without connection pooling, when integrating @upstash/ratelimit, or when the user says Redis cache, KV store, session store, serverless Redis, or Upstash Redis. Also use when building AI agents on Redis with Upstash AgentKit (agent memory, chat history, RAG tools, tool caching, chat persistence, resumable streams, distributed locks) for the Vercel AI SDK, TanStack AI, or Vercel Eve. Supports automatic serialization/deserialization of JavaScript types.
Rewrite vague questions as problem briefs that an Agent can reason about, critique, and verify, and assess how amenable they are to automation. Use when the user wants to improve question phrasing, research a question, or assess whether an Agent can solve it; do not re-clarify goals when the task’s deliverable is already clear.
Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects. Use when the task involves organizing project structure with FSD layers, deciding where code belongs, placing static assets (images, icons, fonts, PDFs), grouping closely related slices, defining public APIs and import boundaries, resolving cross-imports or evaluating the @x pattern, deciding whether to create or remove an entity, evaluating whether the entities layer is needed at all, deciding where page layouts belong or whether to use the widgets layer (discouraged), deciding whether logic should remain local or be extracted, migrating from FSD v2.0 or a non-FSD codebase, integrating FSD with frameworks (Next.js App Router and Pages Router, React Router, Nuxt, Vite, Astro), or implementing common patterns such as authentication, API handling, Redux, and TanStack Query (React Query) within FSD.
Design the org-wide revenue KPI framework at the macro level - which metrics matter at each org level from board to IC, how they roll up through a reconciling metric tree with explicit math, who owns each branch, which guardrail counter-metrics ride alongside each owned number, and how the set is gated by company stage and business model. Use whenever the user mentions a revenue KPI framework, a metric hierarchy, a KPI tree, a North Star metric, driver metrics, guardrail counter-metrics, NRR, or which revenue metrics each org level should track - even if they never say "framework". Covers B2B and B2C. Do NOT use for writing the board report itself - use mbfinotti/revops-skills@revenue-reporting instead.
Use when working with the Resend email API: sending transactional emails (single or batch), receiving inbound emails via webhooks, managing email templates, tracking delivery events, managing domains, contacts, broadcasts, webhooks, API keys, inboxes (threads, labels, drafts, replies), automations, events, viewing API request logs, checking account usage and quotas, or setting up the Resend SDK. Always use this skill when the user mentions Resend, even for simple tasks like “send an email with Resend”—it contains critical gotchas (idempotency keys, webhook verification, template variable syntax) that prevent common production issues.
Before starting any RevOps or Sales Ops task, and at the start of every session on an ongoing RevOps project, run this first - it routes the task to exactly one skill of the revops-skills collection or says plainly that none fits, and bootstraps or resumes the project's shared, versioned context artifact so the next session starts warm instead of cold, ending in a short-list plus an ordered skill chain. Run it even when the collection's other skills are already used daily - a new project is a new context. Also use whenever the user mentions a revops kickoff, a new RevOps project, a revops project start, revops or crm skill routing, a periodic RevOps check-in, a recurring RevOps review, "which revops skill do I need", or "where do I start with RevOps" - even if they never name a skill, and even if the request looks like it already belongs to one specific skill. Do NOT use for routing quota-carrying sales tasks - use mbfinotti/sales-skills@sales-kickoff instead.
Run a periodic, checklist-based hygiene audit over an active pipeline snapshot — stale deals (no stage, close date, or amount change, no logged touches) flagged against segment-specific stage medians, close-date push-count anomalies, and missing forecast-critical fields — producing an exception list with a disposition per flagged deal, a remediation plan, and a pass threshold. Use whenever the user mentions pipeline hygiene, a stale deal audit, pipeline cleanup before a QBR, deals that keep pushing, a close date that keeps slipping, missing fields on deals, or "our pipeline is full of junk" — even if they never say "hygiene". Covers B2B and B2C/high-velocity/PLG. Do NOT use for rewriting stage definitions — use mbfinotti/revops-skills@pipeline-stage-definition-audit instead.
Design a company's revenue funnel model from scratch, at the macro level - the stage set, the unit of analysis (lead, buying group, account), the model purpose (process vs planning vs forecast), the cohort-based conversion assumptions behind the plan, and the ownership handoffs between marketing, sales, and CS. Use whenever the user mentions funnel design, funnel stages, a funnel model, conversion rate assumptions, a bowtie model, a demand waterfall, MQL to SQL to opportunity definitions, or marketing-sales handoff design - even if they never say "funnel". Covers B2B and high-consideration B2C. Do NOT use for auditing an existing pipeline's stage definitions - use mbfinotti/revops-skills@pipeline-stage-definition-audit instead.
Audit existing sales pipeline stage definitions against buyer-verifiable milestones and flag the ones built on rep activity instead. Core test - does each stage exit criterion name something the buyer did, said, or agreed to, checkable by two managers independently? Adds stage aging, conversion decay, stage-skip rate, and close-date push diagnostics. Use whenever the user mentions stage definitions, stage exit criteria, stage inflation, stages named after rep activity ("demo scheduled", "proposal sent"), "our stages don't mean anything", or "why is everything stuck in one stage" - even if they never say "audit". Covers enterprise and high-velocity pipelines, B2B and B2C. Do NOT use for designing a funnel stage set from scratch - use mbfinotti/revops-skills@revenue-funnel instead.
Trace where deals and revenue silently exit one specific funnel and size the loss in recoverable (never gross) dollars - untracked steps, unworked leads, manual handoffs, mid-funnel stalls, paper-process drops, billing and renewal misses - separating real leaks from healthy disqualification and data-capture gaps. Use whenever the user mentions revenue leakage, funnel drop-off, a leaky funnel, deals disappearing, unworked leads, handoff gaps, "where are we losing deals", or "why did pipeline vanished" - even if they never say "leakage". Covers B2B sales-led and B2C/self-serve/PLG, one funnel instance at a time. Takes stage definitions as given - to audit those, use mbfinotti/revops-skills@pipeline-stage-definition-audit instead.
Build a personalised, time-budgeted watch list of RevOps / Sales Ops information sources - revops podcasts, revops newsletters, revops communities, industry events, and revops people to follow - every source verified still active, with a periodic refresh routine that keeps the list fresh. Use whenever the user mentions a revops radar, staying current in revenue operations, which revops newsletters or podcasts to subscribe to, which revops communities or conferences deserve their time, or who to follow in the field - even if they never say "radar". Tool-agnostic; B2B-SaaS-centric with explicit B2C guidance. Do NOT use for sales-specific sources - use mbfinotti/sales-skills@sales-radar instead.
This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot prompting", or wants to apply advanced prompt engineering patterns for production LLM applications.
Diagnose why an existing sales forecast is unreliable and recommend fixes — stage inflation and happy ears, sandbagging, deals without verifiable buyer evidence, stale or mass-pushed close dates, wrong forecast-category assignment, zombie and duplicate opportunities, late-created deals, manager roll-up overrides, and comp incentives that reward bias — separating data-quality from behavioral from genuine demand problems. Use whenever the user mentions forecast accuracy, a forecast miss, reps sandbagging, deals that keep slipping, "why did we miss the number", or "our commit is never right" — even if they never say "forecast". Covers B2B deal-based and B2C/high-volume. Do NOT use for pipeline coverage modeling — use mbfinotti/sales-skills@sales-pipeline-coverage-modeling instead.
Build and advance a RevOps or Sales Ops career from the candidate's side - place the candidate on the ladder by scope rather than title, close competency gaps, build defensible evidence of structurally invisible work, and prepare the four exercises RevOps interview loops actually run. Produces a career plan with a gap roadmap, an evidence ledger, interview readiness, and a compensation ask. Use whenever the user mentions a RevOps career, a sales ops career path, RevOps interview prep, RevOps certifications, "how do I break into RevOps", "am I ready for a RevOps manager role", or proving impact when nobody notices ops working - even if they never say "career". Candidate side only - for the hiring manager's side, use mbfinotti/revops-skills@revops-hiring instead.
Build and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL. Use for streaming data into R2 Iceberg tables, managing catalogs, or querying those tables; also use for requests using the former Data Platform, Pipelines, R2 Data Catalog, or R2 SQL names.
Build the complete hiring packet for a RevOps or Sales Ops role: archetype and level decision, outcome scorecard, interview stage map with a competency question bank and anchored rating scales, a work-sample exercise with rubric and debrief, and a 30-60-90 ramp plan branched on seniority and archetype. For the hiring manager or founder recruiting the hire. Use whenever the user mentions hiring a RevOps manager, sales ops interview questions, a RevOps take-home exercise, a scorecard for a first ops hire, or a 30-60-90 for a new ops hire—even if they never say "hiring packet". Does not source candidates or post jobs. Do NOT use for a candidate's own interview prep—use mbfinotti/revops-skills@revops-career instead.
Rate limiting for serverless and edge apps with the @upstash/ratelimit TypeScript/JavaScript SDK backed by Upstash Redis. Use when adding a rate limiter or throttling to an API route, Next.js middleware, Vercel Edge, Cloudflare Workers, or any HTTP endpoint; returning 429 Too Many Requests; choosing between fixed window, sliding window, and token bucket algorithms; limiting per user, IP, API key, or tenant with prefixes and custom keys; protecting login, signup, form, or AI endpoints from abuse, bots, and brute force; using deny lists, ephemeral caching, analytics, timeouts, and multi-region rate limits; or estimating the Redis command cost of rate limiting. Also use when the user says rate limit, rate-limiting, throttle, quota, request limits, or traffic protection
Design and operate CRM field-level governance: who owns each CRM field, which system is authoritative for it, how often it must be refreshed, and how the rules are enforced. Produces a field dictionary, per-field ownership, a system-of-record map with write-precedence and conflict rules, freshness SLAs, an enforcement plan, a field lifecycle, and a governance cadence. Use whenever the user mentions field ownership, single source of truth, system of record per field, data dictionary, stale CRM data, custom field sprawl, "which system wins", or "our CRM fields contradict each other"—even if they never say "governance". Covers B2B and B2C. Do NOT use for org-wide, object-level source-of-truth policy—use mbfinotti/revops-skills@revenue-data-governance-strategy instead.
Set org-wide revenue data governance policy: which system is source of truth per object class (account, contact, opportunity, subscription, usage event, revenue metrics), how cross-team data contracts bind producers to consumers, where revenue metric definitions live, and who arbitrates disputes. Produces a per-object SOR/SOT designation table, an identity-resolution spine, a data-contract register, and a federated ownership model. Use whenever the user mentions source of truth, "two ARR numbers", GTM data contracts, revenue data governance, metric definition ownership, or "finance and sales report different numbers"—even if they never say "governance". Covers B2B, PLG/B2C, hybrid. Do NOT use for CRM field-level rules—use mbfinotti/revops-skills@crm-data-governance instead.
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Propose multiple visual design variants for on-screen elements and let the human pick in the Argent Lens window. Use when the user asks for design alternatives, options, or A/B choices for a screen or component, or whenever you have produced more than one candidate look for an element and want a human decision before committing.
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.