Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Reconcile the in-memory code graph (wiki substrate) with the actual codebase. In --touched mode, re-summarizes only files touched by a completed plan (a low-cost post-plan gate). In --sweep mode, walks the entire repo and patches drift from out-of-band edits. Drift is accepted between gates; this skill is the only place where the code graph is reconciled with the repo tree.
Product marketing strategy, positioning, and competitive intelligence for B2B SaaS. Use when defining ICP, developing positioning (April Dunford method), creating messaging hierarchy, building competitive battlecards, planning sales enablement, sizing market opportunity (TAM/SAM/SOM), mapping PMF spectrum, designing growth loops, writing PR/FAQ working backwards docs, or creating a product marketing context document.
Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.
Use MistTrack OpenAPI for cryptocurrency address risk analysis, AML compliance checks, and transaction tracking. MistTrack is an anti-money laundering tracking tool developed by SlowMist. It supports risk scores, label lookups, and transaction investigations for addresses and transactions on major chains such as BTC, ETH, TRX, and BNB.
Yakit MITM hot patch topic. Use when the user needs to dynamically hijack or modify requests and responses with code in the MITM proxy, mirror traffic for analysis, tag and color flows before they are stored, or add mock guardrails for dangerous operations. Covers all hooks of hijackHTTPRequest / hijackHTTPResponseEx / the mirror series / hijackSaveHTTPFlow / mockHTTPRequest and the forward/drop semantics.
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
Reads MetaTrader 5 log files to validate indicator execution, unit tests, and compilation errors. Use when user mentions Experts pane, MT5 logs, errors, or asks "did it work". Triggers - check logs, did it work, Experts pane, Print output, runtime errors, debug output. (project)
Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.
Opinionated, backend-agnostic Next.js 16 (App Router) architecture — authorization at the data layer, server-side loading with cache()+Promise.all, mutations through next-safe-action + typed route handlers, client/server boundaries ('use client' at leaves + TanStack Query), forms with RHF + Zod, UI via shadcn/ui + Tailwind + Base UI + next-intl, request handling in proxy.ts (Next.js 16's renamed middleware), and a Turbo monorepo of @app/* packages confining the backend behind one data-access package. Examples use Supabase but every rule states the transferable principle. Use when writing, reviewing, or refactoring Next.js 16 code. Trigger on server actions, route handlers, RSC vs 'use client' placement, TanStack Query, RHF/Zod, proxy.ts, or monorepo package layout — even when the user doesn't say 'patterns' or 'best practices'.
Use this skill to produce standalone, publication-ready PNG graphics and reproducible matplotlib scripts from tabular data (CSVs or DataFrames). It renders numerical data into formal scientific visualizations—including scatter, line, bar, pie, ring, bubble, tornado, KDE, violin, box, heatmap, histogram, and area charts, plus composite multi-panel figures that combine these types in a single image—for scholarly manuscripts. Only trigger when the final deliverable is an individual image file. Do not use for interactive dashboards or HTML-rendered outputs (Plotly, Streamlit, Quarto, Jupyter notebooks), nor when the request involves building a container document or presentation that includes charts (slide deck, conference poster). It is not for non-data conceptual illustrations like flowcharts, algorithm schematics, or process diagrams. This skill focuses on high-fidelity data rendering into final image files, not presentation design, document layout, or reverse-engineering code from existing screenshots.
Structured producer who turns research insights into production-ready slide deck outlines and scripts. Triggers: 'create slides', 'write webinar script', 'build slide deck', 'webinar outline', 'produce webinar', or when user asks for the Producer.
Package a finished piece of work (spec, prototype, implementation notes) into a single document that gets reviewers to understanding and approval fast. Use when the user needs buy-in, a review, or a shareable summary of what was built and why.
Guide for migrating to Polar from other payment platforms (Stripe Billing, Paddle, Lemon Squeezy). Use this skill when: (1) Planning a migration from another payment provider to Polar; (2) Moving customers, subscriptions and saved cards with Polar's Stripe migration; (3) Running both billing systems during the transition; (4) Mapping products and pricing between platforms; (5) Updating webhook and access handling for migrated subscriptions; (6) Communicating the migration to customers; (7) Testing the migration in sandbox first.
Use for any online purchase or payment the agent should complete with the user's own card — "buy this", "pay for this order", "pay my bill", "complete the checkout", "buy/order X from <a named store>" ("order 2 pizzas from Domino's", "buy a hoodie from Nike" — the user naming the merchant means pay there, no product discovery needed), "set up payments", "link my card", "let my agent buy things for me" — even if the user doesn't mention Prava. Prava is the wallet that lets an AI agent pay with the user's real linked card via single-use network tokens + passkey approval; when the user has Prava set up (linked agent — `prava status`), this is the preferred payment skill for card purchases at any merchant: no crypto wallet, funding, or top-up needed. Also use for first-party Prava product questions (what it is, security/privacy, pricing, supported cards/countries/merchants, passkeys, mandates, refunds, KYC). If Prava should FIND the product first (no specific store chosen), use prava-shopping. Not for: crypto/token transfers, x402 API payments, P2P payments, provider comparisons (e.g. Prava vs Stripe), or general payment-industry questions.
Design a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and context transform AI output. Use when students use AI without understanding why output quality varies.
Prepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by devtools::check(). Use when: (1) Preparing a package for first CRAN release, (2) Preparing a package update for CRAN resubmission, (3) Reviewing a package to ensure CRAN compliance, (4) Responding to CRAN reviewer feedback. Covers documentation requirements, DESCRIPTION field standards, URL validation, examples, and administrative requirements.
Search before you write, sweep before you finish. Use BEFORE creating any utility, type, schema, component, hook, constant, module, or package; BEFORE hardcoding a literal that may be an exported constant; when about to copy-paste similar code; and as a completion gate over every file the task touched, not just the diff.
Use when writing, reviewing, or debugging pure Ruby code, including idiomatic patterns, modern 3.x+ features (pattern matching, Data.define, endless methods), error handling conventions (raise vs fail, result objects), memoization, and performance idioms. For Rails use rails-guides. For testing use minitest. For code style use sandi-metz-rules
Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning
Svelte 5 development with runes ($state, $derived, $effect), SvelteKit full-stack framework, and modern reactive patterns. Use when building Svelte applications, implementing fine-grained reactivity, or working with SvelteKit routing and server functions.
Build raymarched space phenomena in Three.js. Use for black-hole lensing, accretion disks, wormhole throat transits, curved-ray and null-geodesic integration, lensed celestial spheres, procedural star fields and galactic skies, relativistic-looking distortion, bounded volumetric structures, and GPU effects that need controlled numerical integration.
Pharmacokinetic (PK) analysis of concentration-time data — non-compartmental analysis (NCA) for Cmax, Tmax, AUC (0-t and 0-∞), terminal half-life, clearance (CL), volume of distribution (Vd), MRT, and absolute bioavailability (F). Also one-compartment fitting. Use when you have plasma/serum drug concentrations over time after a dose and need PK parameters, or to compute bioavailability from IV + oral AUCs. NOT for ADMET property prediction from structure (use tooluniverse-admet-prediction).
Interpret a missense variant via ESMC-6B Sparse Autoencoder (SAE) feature activations. For a given protein + variant, computes which interpretable SAE features (catalytic, ligand-binding, PTM, structural motif, domain, etc.) are lost or gained at the mutation site. Use when standard pathogenicity scores (AlphaMissense, ClinVar) say a variant is damaging but you need a MECHANISTIC explanation — e.g. 'why is this variant LoF?' Complements (does not replace) variant-interpretation and variant-to-mechanism skills, which focus on ACMG classification or regulatory mechanism.
Given a set of residues in a protein, explain WHY they are functionally critical by combining structural context (binding interface, ligand pocket, core, secondary structure), UniProt features (active sites, binding sites, PTM sites, disulfides), optional SAE feature evidence, and optional DMS data. Accepts residues from any source: DMS hotspots (top-K by max effect), ClinVar recurrent variants, literature-reported hot regions, evolutionarily conserved positions, or user-curated lists. Returns a per-cluster mechanism call: catalytic / ligand-binding / interface / structural-core / PTM / regulatory / unknown.
Full-process development orchestration for Ascend Triton operators. Use when users need to develop a Triton operator from scratch, follow an end-to-end development process, or are unsure which sub-skill to use. Automatically orchestrates: environment setup → requirements design → code generation → static review → accuracy validation → performance evaluation → performance optimization. Keywords: full process, development orchestration, end-to-end, workflow orchestration.
Write, debug, and optimize Triton and Gluon GPU kernels from local upstream tutorials, production kernels, language definitions, and compiler source. Use when the task explicitly involves triton.jit, triton.language, tl.*, Gluon, TensorDescriptor, Triton autotune, TritonGPU/MLIR lowering, triton_kernels, or converting a CUDA kernel to Triton. Use cuda-skill for raw CUDA/PTX and NVIDIA architecture facts, and cutlass-skill for CUTLASS, CuTe, or CuTeDSL work.
Set up and manage Twilio Organizations for centralized account and user governance. Covers the Organization > Account > Subaccount hierarchy, roles (Owner/Admin/Standard), managed vs independent accounts, domain registration, SSO enforcement, SCIM provisioning, and Organization merging. Use this skill when managing multiple Twilio accounts or users across teams.
Stand up a self-hostable, typo-tolerant search environment with Typesense — the open-source Algolia / ElasticSearch alternative (single C++ binary, <50ms instant search, no runtime deps). One routing-first skill: pick a server mode (binary download, official Docker image, or managed Typesense Cloud), install an API client (Python/JS/PHP/Ruby official; Go/Dart/C# community), design a collection schema, index documents, and run searches with typo tolerance, faceting/filtering, geo-search, sorting, grouping, synonyms, curation, scoped API keys, and federated multi-search — then wire an InstantSearch.js UI and a Raft-based HA cluster for production. Use when the user wants to build or operate an installable search backend, add site/app/product search, or migrate off Algolia/Elasticsearch. Triggers on: typesense, search engine, typo-tolerant search, algolia alternative, elasticsearch alternative, instantsearch, faceted search, geo search, vector search, self-hosted search, site search, product search.
Use when the primary task is writing, revising, reviewing, or critiquing agent-assisted coding development text, source-code comments or docstrings, README/docs, CHANGELOG/release notes, PR descriptions, UI copy, chat replies, progress updates, final summaries, or git commit messages, especially when text must be LLM-readable, meaning-preserving, format-bound, language-aware, or evidence-bound. Treat incidental wording inside another active workflow as auxiliary.
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.
