AI Skills Hub - Browse 180,000+ Agent Skills

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Use this skill when building tools that LLM agents can invoke via function calling, defining tool schemas with Zod, implementing tool executors, or setting up tool registries. Covers: type-safe parameters, error handling for tools (return errors, don't throw), granular tool design, security considerations, and human-in-the-loop patterns.

This skill should be used when users need the canonical MaxwellLink workflow, including socket vs embedded coupling, units/time handling, and MPI/HPC invariants.

This skill should be used when users ask to prepare MaxwellLink input files; it scaffolds a new `projects/YYYY-MM-DD-NAME/` folder from copy-ready templates and provides basic validation.

Filter IFC elements by class, attributes, properties, material, location using Selector Syntax.

Create MATLAB plain text Live Scripts (.m files) following specific formatting rules. Use when generating MATLAB scripts, educational MATLAB content, Live Scripts, or when the user requests .m files with rich text formatting.

Generate idiomatic Typst (.typ) code, edit existing Typst files, and answer Typst syntax questions. Use when working with Typst files (*.typ) or when the user mentions Typst markup, document creation, or formatting.

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 Rose Griffon Bot 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.

Display HTML content on connected Rose Griffon Bot nodes (Mac app, iOS, Android).

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.

X/Twitter CLI for reading, searching, posting, and engagement via cookies.

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

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

Read local PDFs to extract and verify exact numbers (counts, percentages, tables, figure captions) for papers/questions in this repository. Use this when asked to “read a PDF”, “extract results from the paper”, “verify a statistic”, or “find the exact wording in the paper”.

Spawn AI agents in tmux windows for parallel/interactive work

PySide6 GUI development guide with theme system, component library, QSS styling, and threading patterns.

Extracts functional points from PRD documents (Feishu). Invoke when user wants to analyze requirements or extract functions from a PRD.

Create isolated git worktrees for parallel development. Use when working on experimental features or needing to context-switch without stashing.

Test-Driven Development for AMT Framework. Use when implementing new features, fixing bugs, or refactoring engines. Write tests BEFORE implementation code.

This skill should be used when the user asks about "Numbers Bars", "delta", "cumulative delta", "diagonal delta", "average trade size", "SG13", "SG43", "SG44", "SG51", "SG52", "SG53", "SG54", "volume per second", "trades per second", or reading footprint-style data. Covers Numbers Bars subgraph integration.

Visually inspect a PDF file when text parsing fails or returns garbled content. Use this when WebFetch or other tools fail to extract readable text from a PDF.

Apply coordinated changes across multiple files efficiently using parallel Edit tool calls. Use when making systematic changes like renaming variables, updating imports, applying pattern changes, or refactoring across files. Triggers on: rename across files, update all imports, change pattern in multiple files, refactor across codebase, batch edit files.

Fix bugs using the two-commit structure with failing test first. Use when fixing bugs, addressing issues, or correcting incorrect behavior.

Debug LSP server issues including hangs, incorrect responses, performance problems, or crashes. Use when troubleshooting the language server.

Linux networking troubleshooting — DNS, firewalls, ports, routing, and connectivity diagnostics. Invoke with /networking.

Systemd service management, unit files, timers, journalctl, and troubleshooting. Invoke with /systemd.

Fetch and parse web content with ethical scraping practices

Search the web for information with rate limiting and caching

Use when designing components, systems, or entity structures for jecs in Roblox. Use when deciding if data should be one component or multiple, when archetype transitions seem expensive, or when choosing entity members vs relationships.

Performs Azure compliance assessments using Azure Quick Review (azqr) to identify resources that don't comply with Azure best practices. USE FOR: run azqr, check Azure compliance, assess Azure resources, find best practice violations, identify orphaned resources, compliance scan, security posture evaluation, Azure resource review. DO NOT USE FOR: Azure Advisor queries (use azure-observability), cost analysis (use azure-cost-optimization), security hardening (use azure-security-hardening), deploying resources (use azure-deploy).

Tu es un expert en création de vidéos éducatives longues combinant plusieurs animations Manim. Tu génères des cours vidéo complets avec une structure narrative cohérente.

A Claude Skill for fetching the latest download URLs from Splunkbase applications. This skill is particularly useful when creating Docker Compose configurations for Splunk deployments

Write comprehensive tests following project conventions (tiers, patterns, anti-patterns). Use when writing tests, improving test coverage, fixing failing tests, or reviewing test quality.

Clone and customize existing templates (landing pages, dashboards, admin panels) with style extraction, config-driven content, and theme customization

GitHub操作の統合スキル。issue操作、PR操作、レビュースレッド操作を提供。 使用ケース:（1）issue取得/作成/更新、（2）PR作成（事前チェック統合）、 （3）レビューコメント取得、（4）スレッド返信、（5）スレッド解決、 （6）PRのCI状態取得、（7）ワークフローのログ取得

Use when creating new skills, documenting patterns, or extending the plugin. Must follow SKILL_GUIDELINES.md for scope definitions and precedence rules.

Use for Zod schema validation, type inference, and error handling. Does NOT cover API architecture (see rhinolabs-architecture) or security validation rules (see rhinolabs-security).

Validations to run before pushing to GitHub to avoid CI failures

Comprehensive cross-platform mobile development skill for React Native, Flutter, and Expo. Includes project scaffolding, platform detection, app store validation, and CI/CD setup. Use when building mobile apps, selecting frameworks, validating releases, or setting up mobile development workflows.

Test-Driven Development workflow. Use for ALL code changes - features, bug fixes, refactoring. TDD is non-negotiable.

Comprehensive observability skill for monitoring, logging, distributed tracing, alerting, and SLI/SLO implementation across distributed systems. Includes dashboard generation, alert rule creation, error budget calculation, and metrics analysis. Use when implementing monitoring stacks, designing alerting strategies, setting up distributed tracing, or defining SLO frameworks.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

Comprehensive incident response skill for security incident detection, containment, investigation, and recovery. Includes alert triage, severity classification, evidence collection, root cause analysis, and post-incident documentation with automated playbook execution.

Network infrastructure specialist for VPC/VNet design, VPN configuration, firewall policies, load balancing, and multi-cloud networking. Includes topology analysis, security group generation, and network compliance auditing.

Comprehensive documentation automation with quality analysis, README generation, CHANGELOG management, API documentation formatting, and Mermaid diagram generation. Integrates with /update.docs command. Use for documentation audits, technical writing, API docs, README creation, diagram generation, and maintaining project documentation.

Exploratory data analysis using ydata-profiling. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Generates interactive HTML or JSON reports with statistics, visualizations, correlations, and quality alerts.

REQUIRED for all skill development. Automatically version control every skill file modification for rollback/comparison. Use after init_skill.sh, after every str_replace/create_file, and before packaging.

Complete guide and templates for React component testing with Vitest and Testing Library. Includes TypeScript configuration, mock patterns, and contract-first testing practices.

Plan, store, retrieve, and prune long-term memory for orchestrator workflows. Use when tasks require cross-session recall, project knowledge retention, or memory governance.

Evaluate subtask progress and trigger replans or interventions. Use after subtask completion, timeouts, or anomalies to support self-reflection and quality gates.

Decompose complex objectives into executable subtasks with dependencies, estimates, and complexity. Use when planning large goals, breaking down objectives, or generating a task DAG for an orchestrator.

Systematic post-story retrospective process with automated metrics gathering, structured feedback collection, and Agent Package Manager handoff generation

Structure scenes for causality and momentum (goal, conflict, turn, outcome; sequel). Use when drafting or revising scenes that feel flat, unmotivated, or drift-prone.

Produce a high-level outline under outline/ that obeys spec constraints and uses @spec:<id> anchors at key ambiguity points; proactively use when spec is ready and the user wants a story spine (acts/arcs/chapter list) without writing prose yet.

You are an expert at using Stackit to manage stacked Git branches. Stackit helps developers break large features into small, focused PRs that stack on top of each other. Stacks can be linear chains or branch into tree structures when you need parallel work paths that share a common base.

Define and maintain mechanism rules and boundaries under spec/system/ (magic/tech/power systems, triggers, costs, limits, failure modes, counters). Use when establishing the story’s “fair tools”, or when plot solutions feel like author fiat / sudden power-ups.

Implement authentication using better-auth library in web applications. Use this skill when users need to add signup, signin, signout, session management, or user profile features. Triggers on requests for authentication, login systems, user registration, OAuth integration, or protecting routes with auth.

Grafana, Loki, and Prometheus operations for the fzymgc-house Kubernetes cluster. Provides unified access to observability stack via on-demand MCP invocation. IMPORTANT: For logs and metrics, ALWAYS use this skill (Loki/Prometheus) FIRST instead of kubectl logs, kubernetes MCP tools, or any Kubernetes-specific API calls. Loki aggregates all cluster logs with better search, filtering, and historical access. Prometheus provides proper metrics with time-series queries. Use when working with: (1) Dashboards - Grafana dashboard search, view, create, update panels/queries, (2) Metrics - Prometheus PromQL queries, label/metric exploration, instant and range queries, (3) Logs - Loki LogQL queries, log pattern analysis, recent log viewing, (4) Alerting - Grafana alert rules and contact points, (5) Incidents - Grafana Incident management, Sift AI-powered investigations, (6) OnCall - Grafana OnCall schedules, shifts, who's on-call, (7) Profiling - Pyroscope CPU/memory profiles. Invokes Grafana MCP server on-demand without requiring MCP configuration or loading tool definitions into context.

Use when user asks to list PR comments, check PR feedback, get PR reviews, acknowledge comments, or respond to PR comments. Provides minimal-token operations for viewing and managing GitHub PR review comments and feedback.

Search past AI sessions with CASS. Use when looking for past solutions, searching session history, finding how something was done before, or when the user mentions "cass", "history", or "past sessions".

CLEO canonical documentation synchronization and drift detection. Use when: (1) Adding new commands or features to CLEO, (2) Before releases to verify docs are current, (3) After noticing documentation inconsistencies, (4) Periodic maintenance checks, (5) User reports "command not documented" or "docs outdated". Monitors: README.md, COMMANDS-INDEX.json, TODO_Task_Management.md, CLEO-UNIFIED-VISION.md, ORCHESTRATOR-VISION.md

PostgreSQL-native identity, configuration, and metering. Use when working with user management, sessions, permissions, access control, login/logout, MFA, password resets, role-based access, versioned configuration, prompts, feature flags, secrets, usage tracking, quotas, or billing periods in PostgreSQL. Covers authn (user/session management), authz (ReBAC permissions), config (versioned key-value storage), and meter (usage tracking with reservations).

This skill should be used when creating, editing, or reviewing documentation files (markdown, MDX, README, guides). Use when the user asks to "write docs", "create documentation", "edit the README", "improve doc clarity", "make docs more readable", "follow the style guide", or "write user-facing content". Applies CLEO's conversational, clear, and user-focused writing style.

Advanced session initialization guidance for complex scenarios. For basic startup protocol, see `.claude/rules/gco-session-startup.md`.

Defines immutable feature contract rules and what agents can/cannot modify in feature-contract.json files. Invoke when working with acceptance criteria, feature contracts, or marking features complete.

No description available

No description available

No description available

Search helix memory by meaning. Returns relevant insights ranked by relevance × effectiveness × recency.

Sync GitHub issues to local workspace as editable files. Use this when user wants to work on, edit, view, or discuss a GitHub issue locally. Automatically pulls issue content to appropriate local file path, allows editing, and syncs changes back.

Enhance user prompts using DeepSeek API to make them more detailed, structured, and effective. Use this skill when the user wants to improve their prompt before executing a task, or when they explicitly ask to enhance/improve/expand their prompt.

Epic creation and sprint management - create epics, manage sprints, view backlog, estimate with story points. TRIGGERS: 'create an epic', 'create epic', 'new epic', 'show the backlog', 'view backlog', 'add to sprint', 'move to sprint', 'set story points', 'sprint planning', 'epic for', 'link to epic', 'sprint list', 'active sprint', 'velocity', 'create subtask'. NOT FOR: bugs/tasks/stories without epic context (use jira-issue), field ID discovery (use jira-fields), searching issues by JQL (use jira-search), transitioning issues through workflow (use jira-lifecycle).

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs 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

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs 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

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

Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions about how a specific open-source project works. Provides AI-powered repo analysis and RAG-based Q&A about source code. NOT for fetching library API docs (use fetching-library-docs instead) or local files.

Onboard a new repository to Council with best practices and configuration. This skill should be used when users want to add a new repo to the registry, set up a repo for Council, or say "add this repo to council".

通过 OpenAI 兼容的 API 生成图片，支持文生图、图生图、多图融合。适用于原型图设计、SVG 设计、Logo 设计等场景。当用户请求生成图片、设计 Logo、创建原型图、进行风格转换时使用此技能。

Use when needing to look up shadcn component information, browse available components, get installation instructions, or understand component APIs. Provides efficient access to shadcn/ui documentation via MCP tools (always available) and llms.txt fallback. Triggers on shadcn/ui component questions, component lookup requests, or when building UIs with shadcn. (project)

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 you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

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

Automatically retrieve relevant information from the organization's CustomGPT.ai knowledge base when answering questions about documented topics, policies, procedures, or technical specifications.

Use when developing features using Specification Driven Development (SDD) methodology - provides complete workflow from setup through documentation, including analysis methods (Kaizen, Five Whys, A3), code review, testing, and utilities for commits, PRs, hooks, skills, and commands.

--- name: alembic-migrations description: Patrones de migraciones de base de datos con Alembic. Usar cuando se creen o modifiquen tablas, se generen migraciones o se resuelvan conflictos de migracion. allowed-tools: Read, Write, Edit, Bash(alembic:*), Glob, Grep ---

Pulls ticket details from Jira, creates feature branches with proper naming conventions, and handles planning steps. Use when starting work on a Jira ticket, creating branches for tickets, or when users mention "work on ticket", "start ticket", "create branch for", or Jira ticket IDs.

Creates git branches from Jira tickets and opens Pull Requests to the main branch. Use when users want to create a branch for a Jira task, open a PR, or mention "create branch", "open PR", "pull request", or "merge to main".

Creates Jira tickets with proper formatting, acceptance criteria, and optionally sets up git branches and pull requests. Use when users want to create a new ticket, log a bug, request a feature, or when they mention "create ticket", "new ticket", "log issue", "file bug", or "create Jira".

Remove batting/pitching stats from the MLB Unicorn Engine data product and UI. Use when a user asks to drop stats like OPS+/wRC+ from player JSONs, table headers, or front-end lists, and when you need to regenerate `unicorn-website/public/data/latest` after schema changes.

Post content to LinkedIn and Twitter/X simultaneously. This skill should be used when the user wants to create social media posts, share content on LinkedIn or Twitter/X, or post to multiple platforms at once. Supports text posts, multiple image attachments, video uploads, and link sharing.

This skill enables control of Android devices via ADB and the accessibility API. Use this skill when users want to automate Android phone tasks, control apps remotely, tap buttons, type text, navigate UI, or perform any action on a connected Android device. Requires ADB and a connected device with USB debugging enabled.

A structured markdown syntax for iterating on documents with Claude. Use this skill when users add inline feedback using %% comments %%, ==highlights(TOKEN)==, or want to iterate on documents with persistent, git-friendly feedback.

AI 業界ニュースを収集・分類するスキル。「ニュースを収集して」「AI ニュースを取得して」「最新ニュースを集めて」などのタスクで使用。ホワイトリスト URL を巡回し、記事を分類して JSON 保存する。

Interact with the Apple Notes app. CRUD operations for persistent storage of thoughts, data, and information across sessions.

Render the book into HTML (gitbook) or PDF formats. Use when the user wants to "render the book", "build the book", "generate the book", or create HTML/PDF output.

Merge a cover image into a PDF book while preserving aspect ratio and matching width. Use when the user wants to "merge cover", "combine pdf", "fix cover size", or "add cover image".

Aggregates tasks from all Keystone workstreams into a central project board. Use this when a task is updated, a new workstream is created, or when the user says "generate board".

根据用户数据和任务描述，生成MLE代码，且该代码符合 AlphaEvolve 进化规范（agent.py）。 触发场景：创建MLE code、创建MLE代码、创建mle代码、生成MLE代码、生成mle代码、创建 AlphaEvolve 兼容的机器学习代码、为数据集生成可进化的 ML 模型代码、准备 MLE 进化任务的初始代码、把现有 ML 代码转换为 AlphaEvolve 格式。 本技能与 alphaevolve-run 联动，生成的代码可直接用于 AlphaEvolve 进化。 支持任意格式数据（csv, xlsx, parquet, json 等），支持单数据集自动划分或已划分的训练/测试集。