AI Skills Hub - Browse 180,000+ Agent Skills

Валидация структурной корректности макета табличного документа (MXL)

Launch review.sh for parallel code quality review (security, quality, architecture). Creates beads tasks for findings. Runs in background with Haiku model.

Remote control Chrome/Chromium via CDP for web automation: navigate pages, take screenshots, execute JavaScript, inspect elements. Use for testing UIs, scraping dynamic content, or capturing page states.

Use when: (1) creating use cases in application layer, (2) defining DTOs (request/response), (3) wiring repositories to use cases, (4) implementing CRUD operations, (5) adding features that orchestrate domain objects.

Use when: (1) creating route handlers for pages/partials, (2) extracting form/query data, (3) connecting handlers to use cases, (4) returning HTML with HX-Trigger headers, (5) implementing middleware (auth/errors/logging).

Batch beads task operations to minimize tool calls. Use when: (1) creating ≥3 tasks, (2) bulk status updates, (3) generating reports/queries, (4) creating task hierarchies (epics with children), (5) batch closing/starting tasks, (6) processing tasks with jq filters. Creates single scripts that run multiple bd commands instead of separate tool calls.

Create or update Claude Skills that extend capabilities with specialized knowledge, workflows, or tool integrations. Use when users want to build a new skill, improve an existing skill, or package a skill for distribution.

Autonomous phase execution with Codex validation. Runs plan/execute/verify cycles in a bash loop until done or halted.

Guided training mode to calibrate your taste profile (20 images)

Generate a single image + splat from prompt

Use ACE-Step API to generate music, edit songs, and remix music. Supports text-to-music, lyrics generation, audio continuation, and audio repainting. Use this skill when users mention generating music, creating songs, music production, remix, or audio continuation.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Creates 09-consistency-audit.md by checking consistency across DocFactory outputs (00-*, 01, 02, 03, 04, 06). Report conflicts, missing details, and propose patches to source docs. Use after docfactory-backlog or when the user asks for a consistency audit, to check docs, or review documentation. No coding.

Resolve relative and natural language date expressions to concrete ISO dates. Use this skill whenever you need to compute a relative date like "next Wednesday", "3 fridays from now", "in 2 business days", or "end of month". Also use it for calendar lookups, day-of-week checks, and computing how far away a target date is (including business days). This skill handles the date *math* — the error-prone computation part. It does NOT handle knowing today's date (that should already be in your context via a hook or system prompt). Trigger on any date arithmetic: "when is", "how many days until", "what day of the week is", scheduling math, deadline computation, or any expression that needs resolving to a concrete date. Even if you think you can do the math yourself, use the script — off-by-one errors in date arithmetic are common and undermine trust.

Orchestrate and manage multiple watchers for Silver tier: Gmail, WhatsApp Web, LinkedIn, and filesystem monitoring. Monitors all sources for new emails, messages, and notifications. Creates action items in /Needs_Action/ folder. Manages watcher authentication, session persistence, health monitoring, and automatic restart on crash. Use when: (1) Setting up Silver tier watcher infrastructure, (2) Starting all watchers simultaneously, (3) Checking watcher health and status, (4) Debugging watcher issues, (5) Managing watcher sessions and credentials. Trigger phrases: "start Silver watchers", "run multi-watcher system", "monitor Gmail WhatsApp LinkedIn", "check watcher status", "setup multi-watcher infrastructure", "manage watchers 24/7".

Run, smoke-test, and debug the Bronze-tier filesystem watcher (Python) that monitors a local drop folder and creates markdown action items inside the Obsidian vault's /Needs_Action folder. This skill should be used when the user asks to "run the watcher", "start the filesystem watcher", "debug why Needs_Action is not updating", "watch a folder for new files", "test the watcher end-to-end", or when Claude needs to validate the Perception layer of Hackathon Zero without Gmail/OAuth. Trigger phrases include: "filesystem watcher", "drop folder", "watchdog", "watcher logs", "no files appearing in Needs_Action", "uv run watcher", and "watchdog observer".

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.

Validates specification completeness and quality by checking for mandatory sections, [NEEDS CLARIFICATION] markers, testable criteria, and clear scope boundaries. Use this skill when you need to check if spec is complete, validate specifications, review spec.md, or check specification quality. Ensures specifications are ready for architecture and implementation phases.

Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this skill for all Mastra development to ensure you're using current APIs from the installed version or latest documentation.

Testing patterns for smart contracts and APIs. Unit, integration, e2e tests. TDD workflows. Use when writing tests for any project.

Call `newAgent(domain, agentAddress)` with 0.005 ETH. Returns token ID via Transfer event.

Meta-skill for creating properly structured OpenClaw/Anthropic-format skills. Use when building new skills or refactoring existing ones.

Connect to external MCP servers as a client. Discover tools, invoke them, handle auth. Use when AgentHQ needs to call Circle, ENS, Chainlink, Stripe, or any MCP-compatible service.

Agent reputation system built on EAS attestations. Scoring, trust graphs, 'should I pay this agent?' decisions. Use when evaluating agent trustworthiness or building reputation features.

Guide for creating effective skills that extend AI agent capabilities with specialized knowledge, workflows, or tool integrations. Use when creating a new skill, updating an existing skill, or reviewing skill design for quality and token efficiency. Adapted from microsoft/skills.

FastAPI REST API 엔드포인트 구현 가이드.

> 실행 계획 수립 에이전트

Query, retrieve, and save Granola meeting notes and summaries locally using the Granola MCP server. Use this skill whenever the user wants to: search or find past meetings, get meeting summaries or transcripts, copy meeting notes to local markdown files, review what was discussed in a meeting, look up action items or decisions from meetings, export meeting data, or analyze meeting patterns. Triggers: "meeting notes", "meeting summary", "what was discussed", "find the meeting", "copy meeting notes", "export meeting", "meeting transcript", "action items from meeting", "last meeting", "recent meetings", "meeting with [person]", "granola".

Search, retrieve, and index local markdown knowledgebase files using the QMD CLI. Use this skill whenever the user wants to: search a local knowledgebase of markdown files, retrieve specific documents or passages from indexed collections, index or re-index a directory of .md files, check the status of the knowledge index, or perform any knowledge retrieval task against local documentation. Triggers: "search the knowledgebase", "find in docs", "index my files", "look up", "search notes", "retrieve document", "knowledge search", "what does the docs say about", "find information about", "re-index", "update the index".

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates an isolated git worktree with smart directory selection and safety verification

Create a pull request with title and body from branch context

Update PR description from current branch context

Produces pre-call research briefs and post-call follow-up messages for PGA 1:1 coaching calls. Use before any 1:1 call or after pasting a call transcript.

SvelteKit data flow guidance. Use for load functions, form actions, server/client data, and invalidation. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error(), invalidateAll().

Reinstall Jarvis plugins with optional cache clear

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

This skill should be used when user asks to generate protobuf protocol files from Java .class files or reverse engineer protobuf from compiled bytecode. Activates with phrases like class to protobuf, convert class to proto, generate protobuf from class, reverse engineer protobuf from class, class protobuf conversion, bytecode to protobuf. Provides comprehensive guidance for parsing Java @Protobuf annotations from .class files using javap and generating .proto files.

Fetch market data using CryptoKlineVisionData with Failover Control Protocol (cache → Vision API → REST API). TRIGGERS - fetch market data, use CKVD, access Binance, get klines, OHLCV data, CryptoKlineVisionData API.

Run tests for crypto-kline-vision-data with proper markers and coverage. TRIGGERS - write tests, run tests, pytest, test coverage, unit tests, integration tests, mocking patterns.

Monitor and diagnose FCP (Failover Control Protocol) behavior, cache health, and data source performance. TRIGGERS - FCP issues, cache problems, slow data, Vision API errors, REST fallback, data source debugging.

Confluence API operations via Python CLI scripts. AUTOMATICALLY TRIGGER when user mentions Confluence URLs (https://wiki.*/pages/*, https://*.atlassian.net/wiki/*), page IDs, or asks about Confluence pages/spaces. Use when Claude needs to: (1) Get page content by ID or title, (2) Search pages with CQL, (3) List spaces, (4) Get page tree/children, (5) Create or update pages. If authentication fails, offer interactive credential setup via confluence-setup.py. Supports both Confluence Cloud and Server/Data Center with automatic auth detection.

Create server actions following your project's established patterns. Use when writing mutations, form submissions, data operations, or cache invalidation. Enforces repository usage, revalidatePath, structured returns, and route colocation.

Audit all git worktrees in the current project. Use when the user asks about worktree status, which branches are merged, which have uncommitted changes, or which worktrees can be safely cleaned up.

Stop recording, transcribe, summarize, and save

Effectful library conventions and decision rules. Use when writing effectful code, designing effects, or migrating from mtl.

Optimize Ollama configuration for maximum performance on the current machine. Use when asked to "optimize Ollama", "configure Ollama", "speed up Ollama", "tune LLM performance", "setup local LLM", "fix Ollama performance", "Ollama running slow", or when users want to maximize inference speed, reduce memory usage, or select appropriate models for their hardware. Analyzes system hardware (GPU, RAM, CPU) and provides tailored recommendations.

Customize or personalize a Claude Code plugin for a specific organization's tools and workflows. Use when users want to customize a plugin, replace tool placeholders, or configure MCP servers for a plugin. This skill requires Cowork mode with mounted plugin directories and will not work in remote or standard CLI sessions.

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.

Clone any published Framer site into a local, Vercel-deployable static site with pixel-perfect fidelity. Use when the user wants to replicate, clone, mirror, or self-host a Framer website (.framer.app domain or custom domain powered by Framer). Triggers on requests like "clone my Framer site", "make a local copy of my portfolio", "self-host my Framer site", "replicate this Framer page", or "deploy my Framer site to Vercel without Framer hosting".

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

Electron desktop development guide. Use when implementing desktop features, IPC handlers, controllers, preload scripts, window management, menu configuration, or Electron-specific functionality. Triggers on desktop app development, Electron IPC, or desktop local tools implementation.

Guide for adding keyboard shortcuts. Use when implementing new hotkeys, registering shortcuts, or working with keyboard interactions. Triggers on hotkey implementation or keyboard shortcut tasks.

Drizzle ORM schema and database guide. Use when working with database schemas (src/database/schemas/*), defining tables, creating migrations, or database model code. Triggers on Drizzle schema definition, database migrations, or ORM usage questions.

Zustand state management guide. Use when working with store code (src/store/**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management questions, or action implementation.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

High-quality web search with AI-optimized results. Use when user needs to search the internet for current information, news, or research topics.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

Fetch unresolved PR review comments using GitHub GraphQL API, filtering out resolved and outdated feedback.

Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control

Best practices and comprehensive guide for Remotion - programmatic video creation in React with animations, compositions, and media handling

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Query, stage, and apply configuration changes for Railway environments. Use for ANY variable or env var operations, service configuration (source, build settings, deploy settings), lifecycle (delete service), and applying changes. Prefer over railway-status skill for any configuration or variable queries.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

Laboratory automation toolkit for controlling liquid handlers, plate readers, pumps, heater shakers, incubators, centrifuges, and analytical equipment. Use this skill when automating laboratory workflows, programming liquid handling robots (Hamilton STAR, Opentrons OT-2, Tecan EVO), integrating lab equipment, managing deck layouts and resources (plates, tips, containers), reading plates, or creating reproducible laboratory protocols. Applicable for both simulated protocols and physical hardware control.

This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling large-scale biological datasets. Use when tasks involve AnnData objects, h5ad files, single-cell RNA-seq data, or integration with scanpy/scverse tools.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

Python interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS proteomics and metabolomics workflows including file handling (mzML, mzXML, mzTab, FASTA, pepXML, protXML, mzIdentML), signal processing, feature detection, peptide identification, and quantitative analysis. Apply when working with mass spectrometry data, analyzing proteomics experiments, or processing metabolomics datasets.

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.

Quantum computing framework for building, simulating, optimizing, and executing quantum circuits. Use this skill when working with quantum algorithms, quantum circuit design, quantum simulation (noiseless or noisy), running on quantum hardware (Google, IonQ, AQT, Pasqal), circuit optimization and compilation, noise modeling and characterization, or quantum experiments and benchmarking (VQE, QAOA, QPE, randomized benchmarking).

Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.