AI Skills Hub - Browse 180,000+ Agent Skills

Audit and refactor CLAUDE.md files to eliminate bloat, enforce context engineering best practices, and create folder-level CLAUDE.md files for complex domain-specific instructions.

Detect and handle session boundaries for multi-context autopilot workflows.

Configure Scarb.toml, dojo profiles, world settings, and dependencies. Use when setting up project configuration, managing dependencies, or configuring deployment environments.

OpenLark Rust SDK 的 feature-crate 参数校验规范（必填校验）。当需要统一/评审 `validate()` 写法，或用户询问 `openlark_core::validate_required`（函数）与 `openlark_core::validate_required!`（宏）的区别、是否需要宏、空白字符串处理等问题时使用。

Decompile Android APK, XAPK, JAR, and AAR files using jadx and Fernflower/Vineflower, trace call flows through application code and libraries, and produce structured documentation of extracted APIs. Two decompiler engines are supported — jadx for broad Android coverage and Fernflower for higher-quality output on complex Java code — and can be used together for comparison.

Comprehensive testing workflow for cargo-autodd.

Watch an Azure DevOps UAT PR for maintainer feedback or approval by polling threads and reviewer votes until approved/passed.

Watch a GitHub UAT PR for maintainer feedback or approval by polling comments until approved/passed.

Generate the comprehensive demo markdown artifacts from the current codebase. Use before UAT to ensure test artifacts reflect the latest code.

Regenerate test snapshot files after intentional markdown output changes. Use after modifying templates or rendering logic.

Create an Azure DevOps pull request using az devops tooling; include the repo’s linear-history merge preference and ask the Maintainer if merge options differ.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Writes production-quality Pine Script v6 code following TradingView guidelines and best practices. Use when implementing indicators, strategies, or any Pine Script code. Triggers on requests to create, write, implement, or code Pine Script functionality.

Entry point for ezorm repo skills. Use to pick the right skill based on task (write YAML vs generate code, and mongo vs mysql/mysqlr).

Write ezorm YAML schema files for this repo (mongo only). Use when asked to define or update ezorm YAML for mongo collections, fields, indexes, flags, embeds, or relations; output YAML only (no Go code).

Write ezorm YAML schema files for this repo (mysql/mysqlr). Prefer mysqlr unless the user explicitly asks for mysql. Output YAML only (no Go code).

Toolkit for comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Connect Letta Code to Google Calendar via OAuth 2.0 and perform calendar operations. Use when a user wants to search events, check availability, or create/schedule meetings. Triggers on queries about calendar, schedule, meetings, availability, or booking time.

Send and read iMessages/SMS from macOS. Use for texting contacts, scheduling services, or automating message-based workflows. Triggers on queries about texting, messaging, SMS, iMessage, or contacting someone via text.

SDK/API patterns for configuring LLM models on Letta agents. Use when setting model handles, adjusting temperature/tokens, configuring provider-specific settings (reasoning, extended thinking), or setting up custom endpoints.

Comprehensive guide for developing Letta agents, including architecture selection, memory design, model selection, and tool configuration. Use when building or troubleshooting Letta agents.

This skill provides guidance for generating self-signed SSL/TLS certificates using OpenSSL. Use this skill when tasks involve creating private keys, self-signed certificates, certificate signing requests (CSRs), or combined PEM files. It covers verification strategies and common pitfalls in certificate generation workflows.

Guidance for implementing CLI tools that perform inference using PyTorch models in native languages (C/C++/Rust). This skill should be used when tasks involve extracting weights from PyTorch .pth files, implementing neural network forward passes in C/C++, or creating standalone inference tools without Python dependencies.

Guidance for sanitizing git repositories by identifying and removing sensitive credentials, API keys, tokens, and other secrets. This skill should be used when tasks involve cleaning repositories of secrets, preparing code for public release, auditing for credential exposure, or removing sensitive data from version control history.

This skill provides guidance for recovering secrets or sensitive data that have been removed from Git history through operations like reset or rebase, and then properly cleaning up the repository to ensure the data is completely removed. Use this skill when tasks involve finding lost commits, recovering data from Git reflog, or securely removing sensitive information from Git repositories.

This skill provides guidance for starting QEMU virtual machines with proper serial console access, process management, and boot verification. It should be used when tasks involve launching QEMU VMs, configuring serial/telnet console access, or managing VM lifecycle. Covers common pitfalls around KVM availability, port conflicts, process hierarchy, and boot readiness detection.

This skill provides guidance for translating RStan (R-based Stan interface) code to PyStan (Python-based Stan interface). It should be used when converting Stan models from R to Python, migrating Bayesian inference workflows between languages, or adapting R data preparation logic to Python equivalents.

Guidance for setting up Git-based multi-branch deployment systems with web servers. This skill applies when configuring Git repositories with post-receive hooks that deploy different branches to different directories, typically served by Nginx or Apache. Use for tasks involving SSH-accessible Git servers, branch-specific deployments, and web server configuration.

This skill provides guidance for translating COBOL programs to modern languages (Python, Java, etc.) while preserving exact behavior. It should be used when tasks involve COBOL-to-modern-language migration, legacy code translation, fixed-width file format handling, or ensuring byte-level compatibility between source and target implementations.

Guidance for configuring Nginx web servers with custom logging, rate limiting, and static content serving. This skill should be used when tasks involve setting up Nginx server blocks, configuring custom log formats, implementing rate limiting, or serving static files on specific ports.

Guidance for writing and verifying SPARQL queries against RDF datasets, particularly university/academic ontologies. This skill should be used when tasks involve querying RDF data with SPARQL, working with academic datasets (students, professors, departments, courses), or performing complex graph pattern matching with filters and aggregations.

Guidance for installing and running Windows 3.11 in QEMU with VNC access and web-based noVNC interface. This skill should be used when tasks involve setting up legacy Windows 3.11 environments, configuring QEMU for DOS/Windows 3.x, or creating virtualized retro computing setups with remote access capabilities.

This skill provides guidance for tasks involving merging git branches that contain different implementations of ARC-AGI pattern recognition algorithms, and then implementing a working solution that generalizes across examples. Use this skill when the task involves (1) merging git branches with conflicting code, (2) analyzing ARC-AGI style input/output grid transformations, or (3) implementing pattern recognition algorithms that must generalize to unseen test cases.

This skill provides guidance for compiling software (particularly SQLite) with gcov code coverage instrumentation, installing to custom prefixes, and making binaries available system-wide. Use when tasks involve compiling C/C++ projects with coverage flags, installing software to non-standard locations, or ensuring PATH availability for installed binaries.

This skill provides guidance for recovering lost Git commits, resolving detached HEAD states, and fixing common Git repository issues. Use this skill when encountering lost commits, accidental checkouts, orphaned branches, merge conflicts during recovery, or needing to restore repository state from reflog history.

This skill provides guidance for semantic similarity retrieval tasks using embedding models (e.g., MTEB benchmarks, document ranking). It should be used when computing embeddings for documents/queries, ranking documents by similarity, or identifying top-k similar items. Covers data preprocessing, model selection, similarity computation, and result verification.

Guidance for implementing asyncio task cancellation with proper cleanup, especially for handling keyboard interrupts (Ctrl+C). This skill should be used when tasks involve asyncio cancellation, signal handling, or graceful shutdown of concurrent Python tasks.

Manage tasks in Obsidian via TaskNotes plugin API. Use when user wants to create tasks, list tasks, query by status or project, update task status, delete tasks, or check what they need to do.

Utility skill to detect Magento development environment and determine command wrapper. This skill should be used by other skills that need to execute shell commands in the Magento environment. It detects Warden, docker-magento, and local environments and provides the appropriate command wrapper.

Expert guidance on building and deploying apps to WendyOS edge devices. Use when developers mention: (1) Wendy or WendyOS, (2) wendy CLI commands, (3) wendy.json or entitlements, (4) deploying apps to edge devices, (5) remote debugging Swift on ARM64, (6) NVIDIA Jetson or Raspberry Pi apps, (7) cross-compiling Swift for ARM64.

High-precision bug detection. Every report is a proof, not a suspicion. Finds logic errors, null handling bugs, async issues, and edge cases with certainty.

SRE agent for incident response and debugging. Uses Axiom, Grafana, and Pyroscope. Mandatory initialization protocol.

Rust testing patterns and best practices. Use this skill when writing, reviewing, or modifying Rust tests. Covers test organization, assertions with pretty_assertions, parameterized tests, and testing multiple input formats.

Use when implementing features or fixing bugs - enforces RED-GREEN-REFACTOR cycle requiring tests to fail before writing code

Use when creating Claude Code hooks - covers hook patterns, composition, testing, progressive enhancement from simple to advanced

Dynamic application security testing (DAST) using OWASP ZAP (Zed Attack Proxy) with passive and active scanning, API testing, and OWASP Top 10 vulnerability detection. Use when: (1) Performing runtime security testing of web applications and APIs, (2) Detecting vulnerabilities like XSS, SQL injection, and authentication flaws in deployed applications, (3) Automating security scans in CI/CD pipelines with Docker containers, (4) Conducting authenticated testing with session management, (5) Generating security reports with OWASP and CWE mappings for compliance.

Software Composition Analysis (SCA) using Synopsys Black Duck for identifying open source vulnerabilities, license compliance risks, and supply chain security threats with CVE, CWE, and OWASP framework mapping. Use when: (1) Scanning dependencies for known vulnerabilities and security risks, (2) Analyzing open source license compliance and legal risks, (3) Identifying outdated or unmaintained dependencies, (4) Integrating SCA into CI/CD pipelines for continuous dependency monitoring, (5) Providing remediation guidance for vulnerable dependencies with CVE and CWE mappings, (6) Assessing supply chain security risks and third-party component threats.

Policy-as-code enforcement and compliance validation using Open Policy Agent (OPA). Use when: (1) Enforcing security and compliance policies across infrastructure and applications, (2) Validating Kubernetes admission control policies, (3) Implementing policy-as-code for compliance frameworks (SOC2, PCI-DSS, GDPR, HIPAA), (4) Testing and evaluating OPA Rego policies, (5) Integrating policy checks into CI/CD pipelines, (6) Auditing configuration drift against organizational security standards, (7) Implementing least-privilege access controls.

SQL-powered forensic investigation and system interrogation using osquery to query operating systems as relational databases. Enables rapid evidence collection, threat hunting, and incident response across Linux, macOS, and Windows endpoints. Use when: (1) Investigating security incidents and collecting forensic artifacts, (2) Threat hunting across endpoints for suspicious activity, (3) Analyzing running processes, network connections, and persistence mechanisms, (4) Collecting system state during incident response, (5) Querying file hashes, user activity, and system configuration for compromise indicators, (6) Building detection queries for continuous monitoring with osqueryd.

Generic detection rule creation and management using Sigma, the universal SIEM rule format. Sigma provides vendor-agnostic detection logic for log analysis across multiple SIEM platforms. Use when: (1) Creating detection rules for security monitoring, (2) Converting rules between SIEM platforms (Splunk, Elastic, QRadar, Sentinel), (3) Threat hunting with standardized detection patterns, (4) Building detection-as-code pipelines, (5) Mapping detections to MITRE ATT&CK tactics, (6) Implementing compliance-based monitoring rules.

Search your conversation history using ripgrep. Use when you need to find previous messages, file edits, tool calls, or decisions from earlier in the session.

Fetch Twitter/X likes and bookmarks. Use when asked to download liked tweets, get Twitter bookmarks, or fetch saved tweets from X.

Create conference talk outlines and iA Presenter markdown slides using the Story Circle narrative framework. Use when the user wants to structure a tech talk, create presentation slides, or needs help organizing talk ideas into a story-driven format.

Use when note files exceed 1000 lines or need better organization. Splits large note files into smaller, focused files with index files for navigation, following progressive grouping principles with clear hierarchy.

Write minimal, concise testthat 3e unit tests for R package code

Expert on EAS Build cloud service for building iOS and Android apps. Covers build configuration, credentials management, custom builds, CI/CD integration, and troubleshooting. Invoke when user mentions EAS Build, cloud builds, app compilation, build workflows, or iOS/Android binary creation.

Expert on Plaid accounts and account management. Covers account data retrieval, balance checking, account types, multi-account handling, and account webhooks. Invoke when user mentions Plaid accounts, account balance, account types, or account management.

Expert on Plaid Auth product for bank account authentication and verification. Covers account and routing number retrieval, account ownership verification, balance checks, and integration patterns. Invoke when user mentions Plaid Auth, ACH verification, bank account verification, or routing numbers.

Migrates attack implementations from the old approach (using AttackId) to use new approach (Mechanic enum)

Implement code quality ratchets to prevent proliferation of deprecated patterns. Use when (1) migrating away from legacy code patterns, (2) enforcing gradual codebase improvements, (3) preventing copy-paste proliferation of deprecated practices, or (4) setting up pre-commit hooks to count and limit specific code patterns. A ratchet fails if pattern count exceeds OR falls below expected—ensuring patterns never increase and prompting updates when they decrease.

Expert knowledge of Electron Inter-Process Communication patterns for SEPilot Desktop. Use this when adding IPC handlers, creating frontend-backend communication, implementing streaming responses, or debugging IPC issues. Ensures secure and efficient communication between renderer and main processes.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Algebra-Driven Design (ADD): model domains via minimal algebra + laws; encode in types; test laws.

Create micro-commits (minimal incision) with at least one validation signal per commit.

Xit (xit) CLI for version control in repositories with a .xit directory. Prefer xit whenever `.xit/` is present; never run the TUI; translate git-like intents to xit CLI and avoid git unless explicitly requested.

Manage AI notes in ~/Compost/AI-Notes - read existing notes, list recent documents, and write new implementation plans (仕様書, 計画書, 設計書). Auto-triggers when reading from or writing to notes, specifications, or plans.

Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.

Use when user asks "why didn't X work", "not working", "debug", "check logs", mentions something "stopped working", or needs to diagnose Home Assistant issues.

Use when user wants device presets, mentions "scene", "mood", "setting", or describes setting multiple devices to specific states like "movie mode" or "goodnight".

Entity resolution and capability snapshot procedures for Home Assistant

Fetch raw file content from GitHub URLs. Trigger when user shares a GitHub file link (https://github.com/user/repo/blob/main/file.go) and wants to view the source code. Avoids HTML/JS clutter from WebFetch.

Security & Authentication Specialist - Expert in JWT, cookie-based auth, MFA, and generic security patterns

Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.

Design and implement visionOS SwiftUI scenes that integrate RealityKit content. Use when building spatial UI with RealityView, Model3D, attachments, volumetric windows, ImmersiveSpace, or spatial gestures, or when choosing SwiftUI vs RealityKit APIs for 3D presentation.

Build, integrate, and troubleshoot SharePlay GroupActivities features, including GroupActivity definitions, activation flows, GroupSession lifecycle, messaging and journals, ShareLink and SharePlay UI surfaces, and visionOS spatial coordination. Use when implementing or debugging SharePlay experiences across Apple platforms, especially visionOS.

Read, write, and update Google Sheets data via CLI. Use when the user asks to read spreadsheet data, update cells, append rows, or work with Google Sheets. Triggers on mentions of spreadsheets, sheets, Google Sheets, tabular data in the cloud, or specific sheet names like "Projects" or "Tasks".

Use when implementing Phoenix LiveView features - TDD with html_snapshot for state inspection and Pa11y for accessibility. Sprinkle snapshots to see what's rendered, delete when done.

Add Instagram accounts or web aggregators to sources.yaml configuration

Fill DOCX template forms programmatically while preserving 100% of original structure - logos, footers, styles, metadata. Zero-artifact insertion for forms, applications, and standardized documents. Output indistinguishable from manual filling.

Access GitHub API using gh CLI in sandboxed environment - install binary, authenticate with tokens, query repos, PRs, issues, workflow runs, and download artifacts

Dual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), finally integrate both conclusions.

Portfolio system knowledge base. Covers position queries, routing strategies, {PRIMARY_PROVIDER} integration, cache design.

Explain complex code logic using Codex MCP. Supports brief/normal/deep depth levels.

Implement feature code using Codex MCP. Decomposes specs into items, implements one at a time, with review loop.

Project initialization inventory and cache generation (one-time intake). Use when first onboarding a project or after major structural changes.

Document review knowledge base. Covers tech spec review, document audit, document refactoring. Codex MCP integration for .md reviews.

Code investigation knowledge base. Covers code history tracking, issue introduction analysis, root cause diagnosis.

Verify plan consistency, generate summaries, maintain plan health. Use for review, verification, summaries, or plan maintenance. Mostly read-only with maintenance operations.

Preview and verify imported content in local AEM Edge Delivery Services dev server. Validates rendering, compares with original page, and troubleshoots common issues.

Get skills.sh trending rankings with AI summaries, trend analysis, and category insights. Use when asking about skill rankings, trends, or skill details.

MateCode - Claude Code Telegram Bridge 管理工具。用于启动、停止、监控 Telegram 远程控制服务

Comprehensive knowledge base for go-zero microservices framework. **Use this skill when:** - Building REST APIs with go-zero (Handler → Logic → Model architecture) - Creating RPC services with service discovery and load balancing - Implementing database operations with sqlx, MongoDB, or Redis caching - Adding resilience patterns (circuit breaker, rate limiting, load shedding) - Troubleshooting go-zero issues or understanding framework conventions - Generating production-ready microservices code **Features:** - Complete pattern guides with ✅ correct and ❌ incorrect examples - Three-layer architecture enforcement - Production best practices - Common pitfall solutions

Oura Ring data integration and analytics. Fetch sleep scores, readiness, activity, HRV, and trends from the Oura Cloud API. Generate automated reports, correlations with productivity, and trigger-based alerts for low recovery days. Requires OURA_API_TOKEN (get at cloud.ouraring.com).

Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.

Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.

Detect and reject indirect prompt injection attacks when reading external content (social media posts, comments, documents, emails, web pages, user uploads). Use this skill BEFORE processing any untrusted external content to identify manipulation attempts that hijack goals, exfiltrate data, override instructions, or social engineer compliance. Includes 20+ detection patterns, homoglyph detection, and sanitization scripts.

Manage printers via CUPS on macOS (discover, add, print, queue, status, wake).

For headless/automated operation, set these environment variables: - MS365_MCP_CLIENT_ID - Azure AD app client ID - MS365_MCP_CLIENT_SECRET - Azure AD app secret - MS365_MCP_TENANT_ID - Tenant ID (use "consumers" for personal accounts)