AI Skills Hub - Browse 180,000+ Agent Skills

WHAT: OpenTelemetry tracing with useTracer hook for spans and distributed traces. WHEN: tracking user actions, monitoring async operations, debugging production issues. KEYWORDS: tracing, OpenTelemetry, OTEL, spans, useTracer, createEventSpan, withSpan, startSpan, SPAN_KEYS, attributes.

WHAT: Download screen screenshots from Figma files via bash script. WHEN: extracting visual assets, creating screenshot references, archiving designs. KEYWORDS: figma, download, screenshot, images, frames, png, export, design.

WHAT: Safe HTML rendering with RenderSanitizedHTML and XSS prevention. WHEN: rendering CMS content, translated HTML, user-generated rich text. KEYWORDS: html, render, sanitize, xss, RenderSanitizedHTML, sanitize-html, truncation, content.

WHAT: ImageCloudinary component with Cloudinary CDN for automatic optimization, quality, and responsive sizing. WHEN: displaying product images, optimizing quality/format, supporting Retina displays, implementing fallbacks. KEYWORDS: ImageCloudinary, Cloudinary, CDN, quality, auto:eco, DPR, crop, gravity, fallbackSource, alt.

WHAT: Access native iOS/Android repository data with TanStack Query. WHEN: fetching auth tokens, app config, plan data from native container. KEYWORDS: native, repository, fetchRepository, iOS, android, container, observables, DataAccess, nativeRepositories.

Inspect GitHub PR for CI failures, merge conflicts, change requests, and unresolved review threads. Create fix plans and implement after user approval. Resolve review threads and notify reviewers after fixes.

Expert guidance for building MCP (Model Context Protocol) servers using the TypeScript SDK. Use when developing MCP servers, implementing tools/resources/prompts, or working with the @modelcontextprotocol/sdk package. Covers server initialization, request handlers, Zod schemas, error handling, and JSON-RPC patterns.

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).

理性、數據驅動的台股投資顧問，提供全方位個股健檢與市場掃描。

AI时代自媒体创作者的个性化任务管理系统，基于本地 Markdown 文件。 围绕内容创作生命周期：灵感 → 选题 → 创作 → 发布 → 复盘

有了实施计划后使用 - 批量执行任务，在检查点验证，更新进度

创建新 skill、编辑现有 skill 或在部署前验证 skill 时使用

面对 2 个以上独立任务时使用 - 无共享状态、无顺序依赖的任务可以并行处理

在声称任务完成之前使用 - 必须先验证结果，有证据才能声称完成

Claude Code MCP (Model Context Protocol) server configuration reference. Use when adding MCP servers, configuring external tools, or integrating third-party services.

Claude Code plugins configuration reference. Use when creating plugins, bundling commands/agents/hooks/skills/MCP servers, setting up marketplaces, or distributing extensions.

Scans Cosmos SDK blockchains for 9 consensus-critical vulnerabilities including non-determinism, incorrect signers, ABCI panics, and rounding errors. Use when auditing Cosmos chains or CosmWasm contracts. (project, gitignored)

Use when working in mm-ibkr-gateway to access market data, account summary, positions, PnL, or orders via the REST API (FastAPI). Covers starting the API server, required env and safety settings, authentication with X-API-Key, and market/account/order endpoints for quote, historical bars, preview, place, status, cancel, and open orders.

Expert system for interacting, scraping, and debugging TradingView Advanced Charts and SuperCharts.

Use for UI/UX design and accessibility work. Covers design principles, color theory with WCAG contrast requirements, typography scales, 8pt spacing grid, responsive breakpoints, WCAG 2.1 accessibility compliance, motion design, and design system governance. Activate when working on user interfaces, design tokens, or accessibility audits.

Use for database design and optimization. Covers schema design, primary key selection (UUID/ULID/serial), safe migrations, query optimization with EXPLAIN ANALYZE, indexing strategies (B-tree, partial, composite), and normalization tradeoffs. Activate when working with SQL files, migrations, or database schema decisions.

Debug Kubernetes deployment failures including CrashLoopBackOff, image pull errors, and resource limits. Use when pods are failing to start or deployments are stuck.

Write Chinese prose/essay in a Lu Xun-like style (syntax, rhetoric, rhythm) from user-provided material, without copying any original sentences/plots and without imitating ideological stance. Use when the user asks for 鲁迅式/鲁迅风格/鲁迅文笔 的散文、随笔、回忆性短文、议论短文，或提到“鲁迅-散文/鲁迅-随笔”。

Write Chinese satire/essay in a Lu Xun-like prose style (syntax, rhetoric, rhythm) from user-provided material, without copying any original sentences/plots and without imitating ideological stance. Use when the user asks for 鲁迅式/鲁迅风格/鲁迅文笔 的杂文、讽刺短文、评论短文，或提到“鲁迅-杂文”。

系统化调试技能，在遇到任何 Bug、测试失败或意外行为时使用。在提出修复方案之前，必须先进行根因分析。

Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests

Show full session token usage, costs, TLDR savings, and hook activity

Azure SWA + Container Apps deployment workflows

Analyze Claude Code sessions via Braintrust

Meta-skill for creating and managing Claude Code skills

Reference guide for Agentica multi-agent infrastructure APIs

Query and store learnings in the persistent memory system

Environment Triage

Query the memory system for relevant learnings from past sessions

Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.

Detect silent sections in audio/video files using FFmpeg and optionally SRT transcripts. Use when user wants to find silence, remove gaps, or analyze audio for editing. Supports multiple detection modes: FFmpeg only, SRT gaps only, AND (both agree), OR (either), DIFF (disagreements).

Push configuration changes to GitHub

Pull latest configuration from GitHub

Generate WPL (Warp Parse Language) parsing rules and OML (Object Mapping Language) transformations from raw log samples. Use this skill when converting raw logs to structured JSON, creating WPL rules for log formats (Apache/Nginx/syslog/JSON/KV/custom), creating OML transformations, debugging or optimizing existing WPL/OML code, or understanding Warp Parse syntax.

Lattice-based cryptography in Isabelle/HOL including LWE, SIS, RLWE, and security reductions

Algebraic structures in Isabelle/HOL including groups, rings, fields, polynomial rings, and quotient rings

Design data analysis from purpose clarification to visualization. Use when analyzing data, exploring BigQuery schemas, building queries, or creating Looker Studio reports.

Archive a completed change and update main specifications. Use when the user has finished implementing and wants to integrate the change into the main codebase.

Comprehensive web scraping, crawling, and data extraction toolkit powered by Firecrawl API. Provides scripts for single-page scraping (scrape.py), web search (search.py), URL discovery (map.py), multi-page crawling (crawl.py), structured data extraction (extract.py), and autonomous data gathering (agent.py). Use when you need to: (1) extract content from web pages, (2) search and scrape the web, (3) discover URLs on websites, (4) crawl multiple pages, (5) extract structured data with JSON schemas, or (6) autonomously gather data from anywhere on the web. Requires FIRECRAWL_API_KEY environment variable.

Generate production-ready animation code from specifications. Use when transforming animation specs into CSS, GSAP, Framer Motion, or Remotion implementations with token references, reduced motion support, and performance optimizations.

Testing strategies for animations and motion. Use for visual regression testing, timing verification, reduced motion compliance, and performance profiling to ensure animations work correctly.

Easing curves and cubic-bezier values from industry standards. Use when selecting animation easing, understanding curve differences across design systems, or implementing easing in code. References W3C DTCG, M3, Fluent, Carbon, and CSS standards.

Scroll-triggered and scroll-linked animations for web interfaces. Use when implementing scroll-based reveals, parallax effects, progress indicators, scrubbing animations to scroll position, or viewport-aware stagger patterns. References GSAP ScrollTrigger, Intersection Observer API, and M3 motion tokens.

Remotion video rendering with motion design tokens. Use when creating programmatic videos, implementing motion token animations in Remotion, or building video templates. References Remotion documentation and M3 token integration.

CLI testing guidance and patterns. Loaded by /ops/test/cli command or subagents for comprehensive testing.

This skill should be used when the user asks about "wm command", "waymark cli", "wm find", "wm add", "wm edit", "wm rm", "wm fmt", "wm lint", or needs to use waymark tooling. Requires `using-waymarks` skill for syntax fundamentals. Provides comprehensive CLI command reference and workflows.

Write deep-dive analytical technical articles for marvinzhang.dev following 4-stage workflow (Research → Outline → Writing → Refine). Use for technical deep-dives, technology comparisons, industry analysis, and theoretical concepts with practical implications. Produces data-driven, Economist-inspired bilingual content. Requires blog-common skill.

Write step-by-step tutorial articles for marvinzhang.dev following 3-stage workflow (Outline → Writing → Refine). Use for how-to guides, implementation tutorials, and practical walkthroughs. Produces clear, actionable bilingual content with minimal code. Requires blog-common skill.

Common formatting, localization, quality standards, and writing principles for all marvinzhang.dev blog articles. Provides MDX syntax rules, EN/ZH bilingual translation guidelines (形不同而意同), Economist-inspired style principles, and quality validation. Always load this skill when creating or editing blog articles.

Expert system for preventing and fixing TypeScript errors (excessive deep type instantiation) and setting up good types in Convex projects. Analyzes schemas and functions against 12 core principles, identifies violations, and provides concrete refactoring solutions. Triggers on TS2589 errors, type safety queries, schema audits, or complexity reviews.

Assists with writing and maintaining Morphir Rust technical documentation. Use when creating, reviewing, or updating documentation including API docs, user guides, tutorials, and content for the Jekyll-based GitHub Pages site. Also helps ensure documentation quality through link checking, structure validation, and code review for documentation coverage.

What this skill does and when to use it (3-5 sentences)

Implements comprehensive tests using Jest and test vectors

Lightweight ad-hoc task with minimal ceremony

Maestroを使用したiOSアプリのUIテストとスクリーンショット撮影を支援します。テストフロー作成、画面撮影、UI自動化について質問された場合に使用してください。

Chat with any YouTube video using AI. Use this skill when users share YouTube URLs and want summaries, answers, or information extracted from video content. Triggers on YouTube links, video summarization requests, or questions about video tutorials.

shadcn/ui 元件庫使用指南與最佳實踐。使用此 skill 當： (1) 需要新增或修改 shadcn/ui 元件時 (2) 建立表單並需要了解 Field 系統 vs Form 系統的選擇 (3) 需要了解 react-hook-form + zod 整合模式 (4) 需要自訂元件樣式或主題配置 (5) 需要確保無障礙 (accessibility) 支援 觸發詞：shadcn, form, field, 表單驗證, ui component

Boundary error-handling handbook (exception translation, failure paths, null/None). Use when designing or reviewing error paths. Always open references/error-handling.md and cite headings.

FeatherCMSに記事を投稿・更新するためのAIスキル

Agentic PR committer with deterministic commits, enforced branch/PR workflow, and explicit paths (no git add .).

Release Node.js CLI packages to npm (Trusted Publishing/OIDC) and Homebrew (tap auto-update). Use when setting up release automation, publishing a CLI to npm/Homebrew, configuring GitHub Actions for package releases, or when the user asks about npm Trusted Publishing or Homebrew formula generation.

Generate and validate YAML frontmatter for docs folder documents. Triggers: "add frontmatter", "update frontmatter", "generate frontmatter", "validate frontmatter", "document metadata"

Develop zgrok tunnel service following project conventions, issue specs, and Rust best practices. Use when implementing features, fixing bugs, or reviewing code in this repository.

Analyzes legacy COBOL programs and JCL jobs to assist with migration to modern Java applications. Extracts business logic, identifies dependencies, generates migration reports, and creates Java implementation strategies. Use when working with mainframe migration, COBOL analysis, legacy system modernization, JCL workflows, or when users mention COBOL to Java conversion, analyzing .cbl/.CBL/.cob files, working with copybooks, or planning Java service implementations from COBOL programs.

Guides comprehensive requirements gathering and analysis including stakeholder interviews, user story creation, use case documentation, acceptance criteria, requirements prioritization, and traceability. Produces requirements documents, user stories, use cases, and development roadmaps. Use when gathering requirements, writing user stories, creating acceptance criteria, analyzing stakeholder needs, prioritizing features, or when users mention requirements analysis, business analysis, user stories, use cases, or requirements documentation.

Analyzes legacy JCL (Job Control Language) scripts to assist with migration to modern workflow orchestration and batch processing systems. Extracts job flows, step sequences, data dependencies, conditional logic, and program invocations. Generates migration reports and creates implementation strategies for Spring Batch, Apache Airflow, or shell scripts. Use when working with mainframe job migration, JCL analysis, batch workflow modernization, or when users mention JCL conversion, analyzing .jcl/.JCL files, working with job steps, procedures, or planning workflow orchestration from JCL jobs.

YouTube 视频中文配音自动化工具 (v3.0 弹性时间轴版)。 核心特性：语义合并字幕、弹性时间轴配音、智能防重叠。 解决语速忽快忽慢和声音截断问题，提供纪录片级的自然配音体验。 关键词：视频配音、YouTube、中文解说、弹性时间轴、自动对齐

Mattermost mm-importer plugin development workflow (SemVer bump, Docker multi-stage build, bundle output, deploy/enable via backend API). Use when changing plugin endpoints, attachment streaming, channel creation, or plugin packaging.

Deterministic mini Slack backup regression workflow (docker compose, plugin ensure, upload, early success counters, log scan). Use when changing importer/exporter logic or verifying end-to-end behavior.

FastAPI backend dev workflow for Slack-MM2 Sync (Python 3.14+, venv, Alembic migrations, black, pytest). Use when changing API endpoints, importer/exporter code, or debugging backend behavior.

Solana wallet operations - create wallets, check balances, send SOL/tokens, swap via Jupiter

Manages Monarch Money transactions, categories, accounts, and receipt splits. Use when the user needs Monarch Money budgeting or transaction operations.

Manage Kubeasy Kubernetes learning challenges - create new challenges, review existing ones, or generate ideas from K8s documentation. Use when working with Kubeasy challenges in any capacity.

Keep local and server versions of dotfiles aligned while preserving intentional machine-specific differences. PROACTIVELY use when: (1) user says "sync dotfiles", "align dotfiles", "check dotfiles", (2) after editing a .local or .server file, (3) when dotsync is run, (4) periodically after dotfile edits. Analyzes paired files, identifies sync candidates vs intentional differences.

TypeScript library and CLI for Monarch Money budget management. Search transactions by date/merchant/amount, update categories, list accounts and budgets, manage authentication. Use when user asks about Monarch Money transactions, wants to categorize spending, needs to find specific transactions, or wants to automate budget tasks.

GoDaddy DNS management skill for managing domain DNS records via GoDaddy API v1. Use when the user wants to list domains, view DNS records, add/create DNS records, update/edit DNS records, or delete DNS records for domains hosted on GoDaddy. Supports A, AAAA, CNAME, MX, TXT, NS, SRV, and CAA record types.

Access Google Secret Manager to securely retrieve, list, create, update, and delete secrets. Use this when you need to fetch API keys, database credentials, or other sensitive configuration values stored in Google Cloud Secret Manager. Requires gcloud authentication and Secret Manager permissions.

Analyze a markdown file for prime numbers using a dedicated script.

Create and manage PostgreSQL database migrations. Use when adding tables, columns, indexes, or modifying the database schema.

Remove events from the Ursine CalDAV calendar. Use for deleting calendar events by UID or summary matching.

Read and display events from the Ursine CalDAV calendar. Shows upcoming events, schedules, and plans. Automatically uses default calendar - no arguments needed.

Capture website screenshots using Site-Shot API. Use for taking screenshots of web pages, capturing full-page screenshots, creating website thumbnails, or generating visual content from URLs. Triggers on: screenshot website, capture webpage, screenshot URL, full page screenshot, website thumbnail.

Fetch company logos using Logo.dev API. Use when needing company/brand logos for slideshows, presentations, thumbnails, or visual content. Supports lookup by domain, stock ticker, or crypto symbol. Triggers on: get logo, company logo, brand logo, fetch logo, logo for [company], create slideshow with logos.

Use the Greptile MCP integration to inspect PRs, reviews, and comments, trigger Greptile reviews, and manage custom context. Use when requests mention Greptile, Greptile MCP, Greptile review comments, or setting the GREPTILE_API_KEY.

Reliable self-hosted ZITADEL administration and day-2 operations with configuration-only changes: initial setup (`zitadel init/setup/start`), hardening (TLS, HTTP/2, masterkey, SMTP), upgrades/scaling, backups, observability, and common troubleshooting. Use when working with ZITADEL deployment config (Helm, Docker Compose, Linux service), ZITADEL config/steps YAML, or diagnosing self-hosted ZITADEL runtime issues.

Authoritative guidance for Codex CLI using OpenAI developer docs via MCP. Use when questions involve Codex CLI installation, upgrades, usage, commands/flags, slash commands, configuration (config.toml, profiles, providers, sandbox), MCP setup, skills, AGENTS.md, non-interactive/CI workflows, or troubleshooting.

Build and refactor Rust command-line tools: Cargo scaffolding, `clap` argument parsing, stdin/stdout IO, error handling and exit codes, logging/config, integration tests (`assert_cmd`), and packaging/distribution. Use when requests mention Rust CLI apps, `clap`, `assert_cmd`, shell completions, man pages, `cargo install`, or releasing Rust binaries.

팀 Private GitHub 저장소에서 스킬을 동기화합니다. 전체 또는 특정 스킬만 선택하여 가져올 수 있습니다. "스킬 동기화", "팀 스킬 가져와", "skill sync", "팀 저장소 동기화" 등의 요청 시 사용하세요.

Intelligent token optimization through Qdrant-powered semantic caching and long-term memory. Use for (1) Semantic Cache - avoid LLM calls entirely for semantically similar queries with 100% token savings, (2) Long-Term Memory - retrieve only relevant context chunks instead of full conversation history with 80-95% context reduction, (3) Hybrid Search - combine vector similarity with keyword filtering for technical queries, (4) Memory Management - store and retrieve conversation memories, decisions, and code patterns with metadata filtering. Triggers when needing to cache responses, remember past interactions, optimize context windows, or implement RAG patterns.

Use when the current repo has many unrelated changes or the user explicitly requests isolation before starting work

Configure Unicode text input support for Android automation. Install and setup DeviceKit (for MCP) and ADBKeyboard (for Python) to enable Chinese, Japanese, Korean, and other non-ASCII text input. Use when text input fails or before tasks requiring Unicode.

Perform common app operations including launching apps, searching within apps, navigating UI, and executing typical user workflows. Use when user wants to open an app, search for something, or perform a multi-step task on the device.

Show PULSE project status - progress, config, errors. Reads from CONFIG.json, PULSE_FEATURES.json, PULSE_PROGRESS.json.

Unblock PULSE execution when stuck on needs_human or max retries. Mark feature as complete, skip, or retry.

Helps with Prowler repository CI and PR gates (GitHub Actions workflows). Trigger: When investigating CI checks failing on a PR, PR title validation, changelog gate/no-changelog label, conflict marker checks, secret scanning, CODEOWNERS/labeler automation, or anything under .github/workflows.