AI Skills Hub - Browse 180,000+ Agent Skills

Edicus 플랫폼(모션원) 연동을 위한 API 및 SDK 가이드. 온라인 편집기 기반 맞춤형 인쇄물(포토북, 명함, 스티커 등) 주문 시스템 연동. 🔹 Server API: "에디쿠스 API", "주문 조회", "프로젝트 생성", "토큰 발급", "렌더링 상태" 🔹 JS SDK: "편집기 연동", "에디쿠스 SDK", "create_project", "open_project" 🔹 주문 처리: "주문 확정", "주문 취소", "tentative order", "definitive order" 🔹 리소스 API: "템플릿 등록", "상품 정보", "폰트 정보" 🔹 MES 연동: "주문 상태 동기화", "배송 정보", "품목 매핑" 지원 기능: 프로젝트 CRUD, 주문 워크플로우, 템플릿 관리, 썸네일/미리보기, VDP(가변데이터인쇄)

Cafe24 API 전체 레퍼런스. Admin API(165개 리소스), Front API(20개 리소스) 완전 문서화. 특화 스킬(주문연동, 상품연동, 정산 등)의 기반 스킬. 🔹 전체: "Cafe24 API", "카페24 API", "Cafe24 개발" 🔹 인증: "OAuth", "토큰 발급", "인증 흐름", "Access Token" 🔹 Admin: "Admin API", "관리자 API", "쇼핑몰 관리" 🔹 Front: "Front API", "프론트 API", "고객용 API" 🔹 에러: "에러 코드", "Rate Limit", "429", "401"

Use Convex Components to add isolated backend features and compose component APIs. Use for installing components, calling component APIs, authoring components, and handling component-specific constraints (Id types, env vars, pagination, auth). Use proactively when users mention components, workpool, workflow, agent component, or reusable backend modules. Examples: - user: "Install the Agent component" → add convex.config.ts + use() + components API - user: "Call component functions" → ctx.runQuery(components.foo.bar, args) - user: "Build a component" → defineComponent, schema, _generated, packaging - user: "Expose component API to clients" → re-export functions with auth

Use the `mem` CLI (mem-cli) to manage agent memory stored as Markdown + a local SQLite index. Use when Codex needs to initialize a public/private memory workspace, add daily/long-term memories, run hybrid semantic+keyword search (default Qwen3 embeddings), reindex after settings changes, or troubleshoot search/embedding behavior via the global config at `~/.mem-cli/settings.json`.

Export the current conversation to Markdown and HTML files for sharing or archiving

Download source code from CodeSandbox public projects into local .context/csb/ folder. Use when user shares a CodeSandbox URL (e.g., codesandbox.io/s/abc123) and wants to analyze, run, or work with the code locally.

Use when you need to understand context limits, loading order, compaction behavior, or optimize what is in the context window.

Restructure and optimize CLAUDE.md documentation in repositories following best practices for larger codebases. Use when user asks to: (1) audit/review CLAUDE.md structure, (2) optimize/restructure project documentation, (3) reduce CLAUDE.md size or context bloat, (4) implement hierarchical CLAUDE.md structure, (5) organize scattered .md files, or mentions "CLAUDE.md best practices", "documentation restructure", or "context optimization". Applies lazy loading patterns and progressive disclosure principles.

Trading strategy implementations for BrokeDancer. Use when: (1) Creating a new trading strategy (arbitrage, market making, momentum) (2) Modifying existing strategy logic (3) Understanding the BaseStrategy interface and execution modes (4) Debugging strategy execution or opportunity detection (5) Working with multi-strategy orchestration Strategies are provider-agnostic and implement trading logic using the BaseProvider interface.

Exchange/platform provider integrations for BrokeDancer trading bot. Use when: (1) Adding a new exchange provider (Binance, Coinbase, etc.) (2) Modifying existing provider implementations (3) Debugging provider connection or API issues (4) Understanding the BaseProvider interface contract (5) Working with provider-specific configurations Providers abstract exchange APIs into a unified interface for strategies.

UI/UX 设计情报与可搜索设计数据库（样式/配色/排版/落地页结构/UX 规范/图表/技术栈指南）。当需要做界面设计方案、生成设计系统、挑选配色与字体、审查与改进 UI/UX、给出可落地的前端实现建议时使用；通过 Python CLI 查询并输出推荐。

Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.

Define contact and interactions in Abaqus - contact pairs, tie constraints, connectors, cohesive behavior. Use for multi-body contact problems.

Define analysis steps in Abaqus - static, dynamic, frequency, thermal, coupled. Use for configuring analysis procedures.

Define time-varying amplitudes in Abaqus for loads, BCs, and other time-dependent quantities.

Configure topology and shape optimization in Abaqus using Tosca - design responses, objectives, constraints, and manufacturing restrictions.

Define initial conditions and predefined fields in Abaqus - initial temperature, stress, velocity, and imported fields.

Create and manage Abaqus jobs - job creation, submission, monitoring, and input file generation.

Configure output requests in Abaqus - field outputs, history outputs, and output database settings.

Extract and analyze results from Abaqus ODB files - field outputs, history outputs, and post-processing operations.

Export Abaqus geometry and results to external formats - STL, STEP, INP, images, and data files.

即席分析与对比归因报表，面向 FO/BO Leader。支持按服务/系统/客户/团队/时间/优先级组合钻取，环比同比对比，输出"结论+证据样本清单"。采用预计算分析 + LLM 描述生成模式，确保分析结果可靠。支持 DOCX 和 HTML 输出，中英文双语。

Brief description

Convert floor plan images to 3D building geometry for Sitea. Use this skill when analyzing floor plan images to extract walls, doors, windows, and rooms for 3D visualization. Handles CAD drawings, simplified floor plans, and architectural layouts. Outputs structured JSON compatible with React Three Fiber wall rendering.

Submit Python functions to Modal with job tracking using the ModalJob decorator. Use when user wants to run GPU workloads, training jobs, or long-running tasks on Modal.

Create and manage annotated bibliographies for research projects. Use when building literature reviews, gathering sources on a topic, or organizing research with citations and key findings. Handles web search → URL collection → content fetching → structured annotation workflow. Ideal for research synthesis that spans multiple sessions or hits context limits.

创建 IM 项目的业务服务层。当用户要求创建新服务、添加业务逻辑、实现 CRUD 服务时使用此技能。

Genera (scaffold) nuevas Skills para Windsurf (.windsurf/skills) con buenas prácticas: metadatos claros, progressive disclosure, ejemplos y guardrails.

Define el flujo para sincronizar cambios entre repositorios Git locales y GitHub, incluyendo validaciones de tamaño, .gitignore y push seguro.

Multi-repository workflow using gitgrip (gr). Use this when working with multiple repos, creating branches across repos, syncing repos, creating linked pull requests, or any cross-repo operations.

Use when PowerDNS Recursor dnstap framestream produces 0 events or a rec_control reloader sidecar keeps restarting under Docker Compose. Trigger symptoms: (1) dnstap collector shows recv_total=0 while the unix socket exists, (2) recursor has no obvious dnstap error logs, (3) a sidecar meant to run `rec_control reload-*` restarts with “Fatal: non-options (sh, while true; do ...)” or shell syntax errors. Fixes unix socket permissions (chmod 0666) and correct Compose entrypoint scripting.

Use when `docker compose` fails reading `.env` with errors like "unexpected character '\\' in variable name" due to accidental backslashes inserted by env-generation scripts (e.g., perl replacements). Fix by ensuring `.env` contains plain KEY=VALUE lines with no escaping and generate values using safe character sets.

Use when adding dnsdist in front of PowerDNS Recursor to get true client IP attribution and dnstap-based “Pi-hole-like” logging. Covers common docker/dnsdist gotchas: (1) dnsdist container entrypoint/command pitfalls, (2) dnsdist newServer() not accepting hostnames like recursor:5300, (3) dnstap CLIENT_* field mapping where QueryAddress is the downstream client and ResponseAddress is dnsdist itself, and (4) ingesting CLIENT_RESPONSE only to avoid query/response duplicates.

Use when running PowerDNS dnsdist in docker-compose and wiring dnstap to a local UNIX framestream socket. Covers: (1) dnsdist-19 Docker image entrypoint gotcha causing "Unable to convert presentation address 'dnsdist'" when you pass a command, (2) dnsdist newServer() requiring an IP literal (hostnames like recursor:5300 fail), (3) dnstap CLIENT_RESPONSE address fields: QueryAddress is the downstream client; ResponseAddress is the local bind (dnsdist).

Use when LSP diagnostics fail with "basedpyright-langserver: command not found" and installing via pip hits PEP 668 "externally-managed-environment". Installs basedpyright safely via pipx so the LSP server is globally available without breaking system Python.

Understand and work with Spitakolus shared tracking infrastructure. GTM containers, GA4 properties, BigQuery datasets, consent mode, and event naming.

A skill that enables web browsing and interaction using the Vercel Agent Browser CLI. Use this to navigate to websites, take snapshots of the page structure (accessibility tree), and interact with elements using short references (@e1, @e2, etc.) rather than complex CSS selectors.

Draft investment memos from dataroom documents

Guidance for Qt/QML chat attachment rows and message bubbles: Flow wrapping, image/file chip alignment, right/left alignment, and width/height sizing quirks. Use when fixing attachment layouts that stack vertically, wrap incorrectly, or appear full-width in Qt Quick/QML.

Guidance for integrating Claude Code CLI in agent/headless mode: required stream-json flags, NDJSON protocol, control_request/control_response tool approvals, and process management. Use when building a host that drives Claude CLI or troubleshooting permission prompts and tool approvals.

Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

Run a single GitHub issue end-to-end through the orchestration graph using scripts/run_issue_harness.py (manual validation/debugging).

Analyze stock tickers by return and volatility using K-means clustering. Use when exploring investment opportunities, identifying risk profiles, comparing market segments, finding high-performers, or analyzing portfolio positioning.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Use this skill when implementing database storage using Supabase PostgREST client (not Drizzle ORM). This requires manual snake_case ↔ camelCase conversion. ONLY use this if you need Row Level Security or browser compatibility. Otherwise, prefer the drizzle-orm-setup skill.

Merge files from golden branch (forensics-migration-refactor) into jake/leo-cleanup. Use this skill when syncing prompt/skill/pattern updates from the golden branch.

Show Monimen documentation status. Use to verify if AI agents properly documented their changes.

Create Monimen documentation. Analyzes context to suggest document type or accepts explicit type parameter. Always confirms before creating.

Analyze aviation agent planner behavioral test results and apply improvement workflow. Use when: running planner tests, adding test cases to planner_test_cases.json, analyzing test failures, improving planner prompts, validating planner improvements, or working with tests/aviation_agent/ test infrastructure.

Database schema management using idempotent sync script instead of Alembic migrations. Use when (1) Adding new database tables, (2) Adding new columns to existing tables, (3) Modifying database schema, (4) Deploying to production, (5) Syncing schema across environments. REQUIRED APPROACH - ALWAYS use scripts/sync-production-schema.py with --dry-run first, NEVER run Alembic migrations directly in production.

Enforces ZERO TOLERANCE file placement rules for documentation and scripts. Use when (1) Creating any .md file, (2) Creating any .sh script, (3) Organizing documentation, (4) Writing guides or reports, (5) Adding utility scripts. CRITICAL RULES - NEVER create .md files in root directories (except README.md, CLAUDE.md), NEVER create .sh scripts in backend (except start.sh), ALL documentation goes in docs/ subfolders, ALL scripts go in scripts/ folder.

Verifies the equivalence of two logic functions or circuits by comparing their truth tables.

Provides Oracle CLI integration for GPT-5.2 Pro review loops. Use when running external model reviews, multi-model consensus, or structured issue extraction from Oracle outputs.

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.

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 Kimibot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

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

查看 QM（查询模型）的 schema 信息。当用户需要了解某个模型有哪些字段、字段类型、是否可筛选/排序等信息时使用。

Senior Frontend Engineer (資深前端工程師) - The Frontend Builder. A pragmatic, code-first developer focused on pixel-perfect UI, reusable components, and defensive coding. Use this skill when: (1) Building UI components (React, Vue, or vanilla), (2) Implementing responsive layouts, (3) Creating reusable component libraries, (4) Frontend state management, (5) API integration with error handling, (6) User says "build a component", "implement this UI", "create a form", or any frontend development request.

QA Engineer (自動化測試工程師) - The Quality Guardian. A suspicious, nitpicking engineer who finds joy in breaking systems. Responsible for black-box testing, E2E automation, and verifying documentation accuracy. Use this skill when: (1) Writing test cases or test plans, (2) Creating automated test scripts (Playwright, Pytest), (3) Verifying API contracts, (4) Checking documentation matches implementation, (5) User says "test this", "verify the API", "write E2E tests", or any QA/testing request.

Use when you need to start a local development server, view the site locally, provide a localhost URL, or when the user wants to preview their work. Handles port conflicts automatically.

[unit description]

Build Base miniapps and Farcaster frames. Use when user wants to create a wallet-connected web app, crypto frontend, NFT minting page, tip jar, token-gated content, or Farcaster frame. Generates Next.js 14 projects with RainbowKit, wagmi, OnchainKit, and Tailwind CSS.

Best practices and tools for processing images for worksheets (trimming, transparency, resizing).

Deploys HTML presentations to Cloudflare Pages using direct API deployment. Use when the user wants to publish, host, or deploy a slideshow.

Deploys slideshows to GitHub Pages and synchronizes the live URL back to the lesson plan. Handles building, committing, and post-deployment linking.

Comprehensive chezmoi dotfile management skill for creating, modifying, and maintaining dotfile templates, configuration files, scripts, and external resources. Use when working with chezmoi for creating new dotfile templates (.tmpl files) with Go template syntax, managing .chezmoi.toml.tmpl configuration and .chezmoidata, configuring .chezmoiexternal files for external resources, writing run_once/run_onchange/run_before/run_after scripts, integrating password managers for secrets, managing cross-platform configurations, and handling conditional logic based on OS/architecture/hostname. This skill includes comprehensive reference documentation for all chezmoi features and can consult the latest chezmoi documentation via Context7.

Retrieve current weather conditions for a specific city. Use when the user asks for weather updates, temperature, or current conditions.

FastAPI web framework patterns. Triggers on: fastapi, api endpoint, dependency injection, pydantic model, openapi, swagger, starlette, async api, rest api, uvicorn.

Extract readable transcripts from Claude Code and Codex CLI session JSONL files

Use when working with CurrentAttributes for request-scoped state like current user or account. Covers thread-local state and context access patterns.

Use when creating or modifying Rails models in app/models. Covers business logic, clean interfaces, message passing, and organization patterns.

Use when creating or modifying Rails controllers in app/controllers. Covers thin controllers, authorization, message passing, and RESTful patterns.

Use when creating or modifying Pundit policies in app/policies. Covers permission-only checks, role hierarchy, and authorization patterns.

Use when modeling state changes as RESTful resources (open/close, pin/unpin). Covers CRUD-based state transitions.

Use when creating or modifying RSpec tests in spec/. Covers no-mock policy, spec types, factory patterns, and test organization.

Use when implementing URL path-based multi-tenancy. Covers tenant middleware, scoping, and request isolation patterns.

Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.

Domain registration information and ownership investigation

当无法在工作目录查到某个类的实现时，用 class-finder 从本地 Maven 仓库的 jar 中查询并输出该类源码。需要定位 jar 类实现时调用。

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.

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

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

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 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 Bot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

파일 생성 또는 수정 전, 경로가 사용자의 보안 지침(Absolute path, Workspace inside)을 준수하는지 결정론적으로 검사합니다.

마크다운 파일이 지정된 템플릿(Logseq, Astro Post 등) 서식과 일치하는지 결정론적으로 검증합니다.

动漫分镜视频生成。基于分镜列表和定妆图，调用Veo API生成每个镜头的视频片段。需要先执行 /anime-character 生成定妆图。

Write, rewrite, and optimize prompts for GPT-5.2 with a focus on fast, reliable behavior using non-reasoning / reasoning_effort: none (low deliberation) settings. Use when asked to draft system/developer prompts, refactor bloated prompts, tighten constraints (verbosity/output schema/scope), reduce overthinking/tool spam, migrate prompts to GPT-5.2, or create eval-ready prompt variants for production agents.

SwiftUI(iOS 17+) 프로젝트에서 Repository + Cache(actor) 계층을 표준화한다. DTO↔Domain 매핑 위치, 캐시 정책(TTL/만료/강제갱신), 동시성 안전 규칙을 강제하며, Store/View에서 데이터 접근이 섞이지 않게 한다.

Quick-start command to run SWE-bench Lite evaluation with sensible defaults.

Run an MCP evaluation using mcpbr on SWE-bench or other datasets.

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.

Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS data processing. For simple spectral comparison and metabolite ID use matchms.

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

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.

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.

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