skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
25,572 results
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
Comprehensive Feishu (飞书) management toolkit for documents, knowledge bases, bitables, and cloud storage.
WeChat Mini Program Skyline rendering engine. Use when developing with Skyline renderer, including components (scroll-view, swiper, draggable-sheet), WXSS…
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default):…
Neural web search, content extraction, company and people research, code search, and deep research via the Exa MCP server. Use when you need to: (1) search the…
Reviews Claude Code agent definition files for tool-access security, triggering quality, and system prompt clarity. Use when reviewing changes to…
Reviews CLAUDE.md files for security, structure, and directive clarity. Use when reviewing changes to CLAUDE.md at a project root, in .claude/, or scoped to a…
Reviews Claude Code settings and hook definitions for security, permission scoping, and command safety. Use when reviewing changes to .claude/settings.json,…
One iteration of an unattended development loop. Use when invoked by name
Automatically file GitHub issues when claude-mpm errors are encountered during a session
Interview you one question at a time, each with a recommendation, to settle a big outcome before agents work alone. Use when: selected by name.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent…
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Enhanced skill creation framework emphasizing philosophy-first design, anti-pattern prevention, and variation encouragement. Use when creating new skills,…
Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions.…
Guides the agent through migrating a Capacitor app project to a newer major version. Supports migrations from Capacitor 4 through 8, including multi-version…
Execute Starknet transactions using Cartridge Controller sessions with human-authorized policies. Use when the user wants to execute Starknet smart contract…
Case progress and status ledger management. The sole write engine for case case.yaml (adding tasks, advancing tasks, registering deadlines, updating case stages, validation, legacy migration), the progress loading and write-back contract for Agent sessions, and case progress monitoring and reconciliation. When a user or Agent...
Multica workspace skill batch sync tool. Batch import or update skills into the Multica skill database according to a source manifest (GitHub / ClawHub / skills.sh / local files), supporting three modes: init / update / plan. The sync target is the Multica database, not local...
Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all…
Unified team skill for full lifecycle - spec/impl/test. Uses team-worker agent architecture with role-spec files for domain logic. Coordinator orchestrates…
Manages Claude Code skills - creates, updates, and maintains skills following established design principles. Use when the user asks to create a skill, update a…
Create or update a personal Pstack mode from repository-scoped history and explicit preferences.