Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Case studies of American screenwriting (美国电影剧作案例) — Mei Feng's readings of the Hollywood Western (value pairs, four oppositions), screwball comedy (strong heroine, buddy vs adversary two-hander), Billy Wilder (disguise, Lubitsch touch, meet-cute), Hitchcock and his writers, Adaptation, Mildred Pierce (eight drafts, woman's film + noir), Thelma & Louise ("but" method, mirror pair), Fargo (Coen method), Good Will Hunting (five-part structure), American Beauty (POV strategy, genre mix), Eternal Sunshine (1:5:1, image motifs); Walter's American Graffiti; the Hollywood masterclass films (Bourne, Guardians, Zootopia, Thor); Hoxter's Winter's Bone and Jojo Rabbit; Snyder's Miss Congeniality; Field's Chinatown. Use when you want a worked example of how a specific American film's script is built, when analysing a film for structure, character or theme, or when looking for a model to imitate for a Western, screwball, noir, buddy, coming-of-age, black comedy or non-linear romance.
The screenwriting business and career (编剧行业与生意经) — merged from Diamond & Weissman's Bulletproof (buyer's-eye workflow, three Cs, one-page nine-step, set pieces, submission, notes, resilience), Eric Bork's The Idea (PROBLEM seven-element idea test, 60/30/10, television differences), Neill Hicks (market four entities, six criteria, WGA, agents, option, credit arbitration, gross vs net, step deals), Richard Walter (query letter, agents, package, option, spec, release, copyright, guild, gatekeepers, professionalism, 66 principles), Wendy Henson (breaking in), Blake Snyder (logline pitch, genre, agents), Julian Hoxter (industry terms), Mei Feng's Oscar analyses, and the Hollywood masterclass (pitching, notes, credits, TV vs film). Use when evaluating whether an idea is sellable, writing a logline/query/pitch, preparing a submission, handling notes and rewrites, understanding options/credits/WGA/agents/net profit, choosing between film and TV, or building a career strategy.
Tauri v2+ cross-platform app development with Rust backend. Use when configuring tauri.conf.json, implementing Rust commands (#[tauri::command]), setting up IPC patterns (invoke, emit, channels), configuring permissions/capabilities, troubleshooting build issues, or deploying desktop/mobile apps. Triggers on Tauri, src-tauri, invoke, emit, capabilities.json.
Retrofit an automated test suite onto a working codebase that has none: rank the untested surface, crown a slice, stand up a runner, and write tests that were each watched to fail before they were kept. Use when the user says "this project has no tests", "add test coverage" to code that already runs, or "what should I test first". Tests for code still being built belong to implementkit.
Run an extremely strict maintainability review focused on abstraction quality, oversized files, and growth of spaghetti conditions. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Guidance for threat modelling using STRIDE and the Microsoft Security Development Lifecycle (SDL). Covers data-flow diagrams, trust boundaries, the STRIDE categories, mitigation mapping, and tooling (Microsoft Threat Modeling Tool). WHEN: threat modeling, STRIDE, data flow diagram, trust boundary, identify threats, SDL threat modeling, security design review, threat model a system, mitigation mapping, Microsoft Threat Modeling Tool, secure design review, design-time security. DO NOT USE for org-wide security architecture (use security-architecture) or for runtime detection (use sentinel / defender-xdr).
Monad tooling and infrastructure provider support directory. Use this skill whenever a developer asks which tools, services, or infrastructure providers support Monad (mainnet or testnet), or needs to find an RPC provider, block explorer, oracle, bridge, indexer, wallet, onramp, custody solution, analytics tool, toolkit, or wallet infrastructure provider for Monad. Also use when a developer asks "does X support Monad?" or "what providers are available for Y on Monad?". Covers all categories from the official Monad docs tooling page.
KEGG-based disease-drug-variant network research. Connects diseases to causal genes, drugs to molecular targets, and variants to pathways using KEGG's editorially curated databases (KEGG Disease, Drug, Network, Variant, Pathway). Use for drug repurposing via shared pathways, mechanistic disease-gene-drug networks, and pathway-based target discovery. Distinguishes direct (binding) vs indirect (pathway co-membership) drug-target relationships.
Cross-species genetic analysis using model organism databases (MGI mouse, IMPC systematic knockout phenotyping, ZFIN zebrafish, FlyBase fruit fly, WormBase worm, SGD budding yeast plus protein-domain/PTM/literature detail, PomBase fission yeast, RGD rat, GeneNetwork systems-genetics/eQTL panels, HumanMine/MouseMine cross-species data-warehouse search, GBIF taxonomy) plus VEuPathDB for eukaryotic pathogens (Plasmodium, Toxoplasma, fungi, vectors). Maps human genes to orthologs, retrieves phenotype/expression/functional data, assesses gene function conservation, and identifies the best animal model for studying a human gene or disease.
Population genetics using the 1000 Genomes Project (IGSR) — superpopulation/population search, sample metadata, variant frequencies across AFR/AMR/EAS/EUR/SAS, ancestry-specific analyses. Use for ancestry comparison, population-aware allele frequency lookups, and 1000-Genomes-cohort-specific analyses (distinct from gnomAD, which has a different sample composition).
Use Osterwalder's Value Proposition Canvas to systematically achieve product-market fit by matching your products and services to customer jobs, pains, and gains. Use when: **Launching a new product or service** and need to validate the value proposition; **Struggling with product-market fit** and need to diagnose why customers aren't buying; **Repositioning an existing offering** to better meet customer needs; **Entering a new market segment** with different customer requirements; **Developin...
Create GitHub-source Webflow Cloud apps and monitor, troubleshoot, or manage existing apps through Webflow MCP. Use when creating a standalone or site-attached app from GitHub; identifying apps or environments; checking public URLs, domains, configuration keys, or deployed versions; diagnosing failures; changing a GitHub source, branch, or mount; provisioning environments; or previewing a deployment, retry, or rollback. Do not use for Designer/CSS variables, CLI/local-source app creation or deployment, or passing environment-variable values through MCP.
Wire Alchemy into application code without an API key, using the x402 or MPP gateway with wallet-based auth (SIWE/SIWS) and per-request payments (USDC via x402, or USDC/credit-card via MPP). Specialized app-integration path. Use when the user is building application code AND no API key is available, or they're an autonomous agent that needs to pay for itself, or they explicitly want x402/MPP. For normal app code with an Alchemy API key, use `alchemy-api`.
Wire Alchemy into application code (server, backend, dApp, script) using a standard API key. Preferred app-integration path for normal server/backend usage. Covers EVM JSON-RPC, WebSocket subscriptions, Simulation, Webhooks/Notify, Solana RPC, Solana DAS, Solana Yellowstone gRPC, Sui gRPC, Wallets/Account Kit, Account Abstraction, and operational topics. Requires `$ALCHEMY_API_KEY`. For app code without an API key (autonomous agent paying per-request, or explicit x402/MPP), use `alchemy-agentic-gateway` instead.
Audit a website or web codebase for SEO and AI-search (GEO/AEO) — produces two independent 0-100 scores (Search SEO + AI Visibility) plus a prioritized, evidence-backed report persisted on disk. Read-only; never writes to the project. Use when the user asks to audit, analyze, check, or score a site's SEO, structured data/schema, meta tags, Core Web Vitals, robots.txt, sitemaps, or AI discovery files, or how it ranks in Google and is cited by AI engines (ChatGPT, Perplexity, Google AI Overviews, Gemini, Claude).
Use when writing any client-facing content, marketing copy, or communications. Use when AI output sounds generic, corporate, or lacks personality. Triggers on "sounds like AI", "lacks voice", "too generic", or when content could apply to any competitor.
Build durable competitive advantage using Hamilton Helmer's "7 Powers" framework—the complete, mutually exclusive enumeration of all possible sources of sustainable business moats. Use when: **Evaluate your competitive position** and identify if you have true Power; **Choose strategic direction** for building durable advantage; **Analyze competitors** to understand their moats and vulnerabilities; **Advise on M&A** whether an acquisition target has defensible value; **Assess startup investmen...
Run a Karpathy-style LLM council (3-stage multi-agent evaluation) on top of the existing orca orchestration: N seats independently answer a question, the answers are BLIND peer-ranked (identities stripped so a model can't favour its own), and a chairman synthesizes the final answer. The orchestration makes the model calls; harness/scripts/council.py does the deterministic protocol math (anonymization, mean-rank aggregation, dissent, anchor guard, transcript). Use when the user says "run a council", "llm-council", "panel of models", "blind peer-rank these answers", "ensemble + chairman", or invokes /council. Stage-4 is a MANDATORY HTML report, rendered inside council.py itself (offline, no CDN, no external skill): every `rank` writes a NEW versioned self-contained report (llmwiki/html/council/council-report-NNN-seed<seed>.html) — opinion cards (persona name + lens), a blind-vote table, and a dashboard. Isolated in try/except so a render bug never kills the core transcript.
A consumer-oriented dating and matchmaking dashboard: left-side navigation, community-signal ticker, headline KPIs, a 30-day mutual-matches bar chart, and a match-rate trend block. Editorial typography with restrained accents. Use when the brief asks for a “dating site,” “matchmaking,” “community dashboard,” “social network dashboard,” or any consumer product where the data tells the story.
Integrate the Didit AML Screening standalone API to screen people or companies against sanctions, PEP, warning and adverse-media watchlists. Use when the user wants to run AML or KYC/AML compliance checks, screen against OFAC/UN/EU sanctions lists, check PEP status, search adverse media, tune match and risk scoring, review AML hits (Confirmed Match, False Positive, Inconclusive), or turn on ongoing AML monitoring using Didit. Covers POST /v3/aml/ (1,300+ watchlists, fuzzy name matching, configurable weights and thresholds, idempotent retries) and the AML hit review endpoints.
Framework-independent decision process for instrumenting a GenAI/LLM app (Python or TypeScript, any provider/agent SDK) so it emits OTel GenAI semantic-convention (gen_ai.*) spans queryable in Dynatrace. Four steps: detect, instrument, enrich, validate. Decides which approach a given SDK needs; does not replace the concrete per-framework recipes in dynatrace-oss/dynatrace-ai-agent-instrumentation-examples. Trigger: "instrument this GenAI app", "add tracing to this LLM app", "how do I get gen_ai spans into Dynatrace", "onboard this agent app to AI Observability". Do NOT use for analyzing telemetry from an already-instrumented app (use dt-obs-genai) or for languages other than Python/TypeScript
Front-door on-demand cho phát triển framework HOẶC distill/author một skill — SELF-CONTAINED, chạy được ở BẤT KỲ project nào (không phụ thuộc file repo-local). Gọi khi đang sửa chính framework, hoặc đang viết/chưng cất một skill trong phiên của dự án khác. KHÔNG dùng cho dev tính năng dự án thường (đó là phần lớn phiên — ADR-004).
A provider-independent FFmpeg finishing workflow for AI agents preparing generated or edited media deliverables. Use when finalizing images, image sequences, video, audio, captions, overlays, social/export variants, checksums, manifests, delivery specs, and QA with ffmpeg/ffprobe. Covers transcode versus stream-copy decisions, scaling, frame-rate handling, color metadata cautions, loudness normalization, subtitle burn-in or sidecars, concat/trim, GIFs, batch variants, and reproducible command reporting.
Use when creating, editing or debugging Ghostty terminal configuration - config.ghostty files, config option names and their valid values, keybinds and key sequences, themes, fonts, shell integration, or `ghostty +` CLI actions. Covers macOS and Linux/GTK differences
Create rich HTML documents for project specs, implementation plans, design exploration, RFCs, and proposals. Use whenever the user asks for a spec, plan, RFC, design doc, or proposal, or wants to explore approaches, options, or alternatives—even when they don’t explicitly say “HTML.” Strongly prefer HTML over markdown for any planning artifact longer than a screen, especially when it will be shared with reviewers or fed back to the agent for implementation.
Automate batch creation and management of Huawei Cloud CES alarm rules for ECS instances using hcloud CLI v7.2.2+. Use this skill to: (1) batch create alarms with templates (web/database), (2) update SMN notifications, (3) query ECS metrics and alarm lists
Use this skill when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, token authentication, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads, including data processing, inference, experiments, batch jobs, and any Python-based tasks. Invoke for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
Handle Hotwire form workflows: form submission lifecycle, inline editing, validation errors, typeahead/autocomplete, modal forms, and external form controls. Prefer this skill when the core problem is correctness and UX of form interaction. Use hwc-navigation-content for pagination/tabs/filter navigation, hwc-realtime-streaming for WebSocket/Turbo Stream broadcasting, hwc-media-content for image/video/audio behavior, hwc-ux-feedback for generic loading/transition polish, and hwc-stimulus-fundamentals for framework-level Stimulus APIs not tied to forms.
Guide for creating and managing Infisical App Connections — the reusable authenticated links between Infisical and third-party services that Secret Syncs, Secret Rotations, PKI certificate authorities, PKI Syncs, and Secret Scanning data sources all depend on. Covers all 83 connection types and their exact auth methods (AWS assume-role vs access-key, GitHub OAuth vs GitHub App vs PAT, Azure OAuth vs client-secret vs certificate, GCP service account impersonation, and more), platform-managed credentials, Gateway-routed connections for private networks, and connection-level credential rotation. Use this skill when someone asks about: App Connections, connecting Infisical to AWS/GCP/Azure/GitHub, 'connection not found' when creating a sync, which auth method a connection needs, reusing a connection across syncs, or 'how do I authenticate Infisical to a third-party service'. This is Infisical authenticating OUTWARD to a third party. Not for machine identities, which are workloads authenticating INTO Infisical (infisical-setup).
Analyzes and correlates live Infrahub data via the MCP server — answers operational questions, detects drift, and investigates impact. TRIGGER when: querying infrastructure data, checking compliance, investigating change impact, producing ad-hoc reports. DO NOT TRIGGER when: writing automated checks, building transforms, designing schemas, populating data files, planning an Infrahub version upgrade (use infrahub-planning-upgrades). ALWAYS pass the user's question verbatim as args — this skill runs in a forked context and cannot see the parent conversation. Invoking without args will fail.
Optimize landing pages for maximum conversions using proven frameworks from Unbounce and Oli Gardner—apply the "one goal, one message, one action" principle with data-driven design, copy, and CTA best practices. Use when: **Create a new landing page** for a campaign; **Optimize an existing landing page** that isn't converting; **Review landing page design** before launch; **Improve form conversion rates** on lead gen pages; **A/B test landing page elements** systematically
Discover popular new products in 16 TikTok Shop regional markets using EchoTik new product ranking data. Trigger this skill when users mention TikTok new product rankings, TikTok best-selling products, TikTok Shop hits, short-video e-commerce product selection, TikTok new product discovery, cross-border TikTok product selection, TikTok new product rankings, TikTok bestsellers, short-video product selection, TikTok viral products, new product ranking, or TikTok product trends. Trigger it even if the user does not explicitly mention “EchoTik” or “new product rankings”, as long as their request involves finding hot new products or emerging product trends on TikTok Shop.
Detect potential design patent infringement using Ruiguan, with image-based patent searches across 25+ countries and regions. Trigger for design patent detection, patent infringement checks, patent risk analysis, TRO case lookups, design patent searches or similarity checks, product patent screening, or related requests. Also trigger when users want to check whether a product image may infringe an existing design patent, or mention infringement, patents, TRO, or design patents, even if “design patent” is not explicitly stated.
Retrieve translated patent claims from the 智慧芽 patent database. Trigger this skill when the user asks about patent claims or claim translations, wants to view claims in a specific language (Chinese, English, or Japanese), looks up patent claims by patent ID or publication number, analyzes claim text, or mentions claim translation, patent claim translation, PatSnap, or patent translation. Trigger it even if the user does not explicitly mention “patent claim translation,” as long as they need patent claims in a specific language.
Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare experiments", "analyze against baseline", or provides one or two experiment IDs for analysis.
Deterministic guardrailed agent-loop driver — wrap any step with propose → deterministic-verify → (critique → revise) and enforce hard termination guards (max_iter, wall-clock budget, no-progress via state-hash, escalate-to-human). The control loop + guards + progress detection are deterministic; the LLM critique/revise step is the one quarantined adapter. Trigger when an agent fix-loop must not spin forever and must not be able to argue its way around a failing test.
Meeting notes page: title bar with attendees, agenda checklist, decisions block, action-items table with owners and dates, and a “next meeting” footer. Use when the brief mentions “meeting notes,” “minutes,” “1:1 notes,” “all-hands recap,” or “会议纪要.”
Participate in moltbook.com — the social network for AI agents. Read feeds, post, comment, upvote, search semantically, send DMs, and manage submolts. Use when asked about Moltbook, checking agent social feeds, posting updates, messaging other agents, or engaging with the molty community. Triggers: "moltbook", "molty", "submolt", "check moltbook", "post to moltbook".
Design ObjectStack AI skills, tools, knowledge sources, and the open-edition MCP server surface. Use when the user is adding `*.skill.ts` / `*.tool.ts`, configuring an LLM provider, wiring the tools a skill grants, or indexing ObjectStack data as a knowledge source for RAG. Agents themselves are platform-internal (`ask` / `build`) — third parties extend them via skills, not by authoring `*.agent.ts`. Do not use for general LLM prompting questions unrelated to ObjectStack metadata.
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.