GitHub
ba
Task tracker for LLM sessions. Use "$ba ready" to see available work, "$ba claim " to take ownership, "$ba finish " when done.
Skills IA Documentation
Découvrez les skills Documentation, comparez leurs dépôts et consultez leurs instructions.
Catégories: Documentation
Documentation Effacer les filtres
Explorer
GitHub
make-skill-template
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities...
GitHub
claude-agent-sdk-reference
Document for build custom AI agents with the Claude Agent SDK, include full SDK Reference and Example Codes.
GitHub
claude-skills-reference
Document for build custom skill for claude code, with full Reference and Example Codes.
GitHub
vector-mcp-retrieve
Vector Mcp Retrieve capabilities for A2A Agent.
GitHub
vector-mcp-collection-management
Vector Mcp Collection Management capabilities for A2A Agent.
GitHub
cabinet-meeting
Conduct a Cabinet meeting when User asks for "Cabinet meeting", "convene the Cabinet", "get perspectives from [agents]", or needs multi-agent consultation on complex decisions. Can be ad-hoc for specific decisi...
GitHub
log-to-obsidian
Review a session or the git history for today and summarize this for our daily reporting
GitHub
meeting-intelligence
Prepare for meetings by gathering context and creating comprehensive agendas
GitHub
proofkit-fmodata
Type-safe FileMaker OData client with Drizzle-inspired ORM and TypeScript code generation. Use when working with FileMaker databases in TypeScript projects, querying FM data, defining typed schemas, generating...
GitHub
add-to-inbox
Create a new note in the Obsidian inbox with user-specified content, including project context
GitHub
understand
Multi-specialist collaborative analysis to understand how features, functions, or components work
GitHub
debug-get-voxel-grid
Debug tool: Get observed voxel grid with agent-relative coordinates
GitHub
project-initialization
Initialize a project with AI agent rules and documentation. Use when setting up a new repository for AI agent collaboration.
GitHub
customer-workspace
Customer workspace initialization skill (Japanese UI). Provides inbox (information accumulation), meeting minutes management, and auto-classification rules. Use for "setup customer workspace" or "add inbox feat...
GitHub
refactoring
Guidelines and techniques for identifying code smells and refactoring code, based on Refactoring.guru principles and adapted for Vanilla JS Chrome Extensions.
GitHub
code-refactoring-small
Refactor overly large code units into smaller, more focused components. Use when code has grown too large or complex.
GitHub
elixir-genius
Use when designing or architecting Elixir/Phoenix/LiveView applications, creating comprehensive project documentation, planning OTP supervision trees, defining domain models, structuring multi-app projects with...
GitHub
mc-pillar-up
Atomic pillar-up: jump and place block under self to ascend by 1 block. Handles timing internally.
GitHub
databricks-ml-pipeline
End-to-end machine learning pipelines on Databricks including data exploration, feature engineering, model training with hyperparameter optimization, MLflow experiment tracking, model registration to Unity Cata...
GitHub
allow-agent-commands
Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
GitHub
agent-command-authoring
Create Claude Code slash commands and OpenCode command files that delegate to skills. Use when creating new commands or refactoring existing ones to follow the delegation pattern.
GitHub
subagent-authoring
Create subagent definitions for Claude Code and OpenCode that delegate to skills. Use when creating new subagents or refactoring existing ones to follow the delegation pattern.
GitHub
review-work
Multi-specialist collaborative work review using independent subagents for comprehensive analysis
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.