GitHub
core
Atlas skill for Personal AI Infrastructure core. AUTO-LOADS at session start. USE WHEN any session begins OR user asks about identity, response format, contacts, stack preferences.
Skills IA research llm ai
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: research llm ai
research llm ai Effacer les filtres
Explorer
GitHub
create-skill
Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.
GitHub
headless-adapters
Discover, create, and validate headless adapters for agent integration. Includes scaffolding tools and compliance testing for the Agent Client Protocol.
GitHub
scaffold-rules
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
GitHub
convertcommands
Atlas skill for converting Claude Code slash commands to OpenCode commands format. USE WHEN migrating from Claude Code to OpenCode or when you have existing slash command definitions to port.
GitHub
gsd
Get Shit Done - Context engineering and spec-driven development system for Claude Code
GitHub
session-handoff
Generate a complete handoff prompt for seamless continuation in a new session. Use when context is filling up or before ending a productive session.
GitHub
multi-agent-orchestrator
Use this skill when coordinating work across multiple specialized skills (django-backend-dev, vue3-typescript-agent, tailwind-task-agent), when translating complex user requests into sequenced tasks, when plann...
GitHub
multi-agent-orchestrator
Use this skill when coordinating tasks for work across multiple specialized agents needing vue3, django, or tailwinds; when translating complex user requests into sequenced agent tasks, when planning and tracki...
GitHub
creator-intelligence
Transform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and workflows across sessions. Use this skill when setting up personal AI systems, building contex...
GitHub
cron-engineering
Meta-science of writing actionable cron prompts. Transform passive \"reflect on...\" crons into active \"DO THIS NOW\" loops. Principles, patterns, and anti-patterns for self-improving automation.
GitHub
ultrathink
Deep reasoning protocol for exhaustive, multi-dimensional analysis and production-ready code generation. Suspends brevity for maximum depth and irrefutable logic.
GitHub
cogames-command
Craft or adjust `cogames` commands for train/play/eval with missions, variants, and policies. Use when asked for a CoGames command.
GitHub
spl-to-apl
Translates Splunk SPL queries to Axiom APL. Provides command mappings, function equivalents, and syntax transformations. Use when migrating from Splunk, converting SPL queries, or learning APL equivalents of SP...
GitHub
meta-skill-creator
スキルを作成・更新・プロンプト改善するためのメタスキル。 **collaborative**モードでユーザーと対話しながら共創し、 抽象的なアイデアから具体的な実装まで柔軟に対応する。 **orchestrate**モードでタスクの実行エンジン...
GitHub
testing
Testing strategy orchestrator. Use when discussing test types, test order, or choosing how to test something. Auto-apply for general testing questions.
GitHub
sync-nim-python
Compare Nim and Python scripted agent implementations and align behavior. Use when asked to port or ensure parity between Nim and Python.
GitHub
ask-gemini
Geminiに意見を聞く、セカンドオピニオンを求める。コードレビュー、設計相談、アーキテクチャの相談、別のAIの意見が欲しいときに使用。「Geminiに聞いて」「別の意見」「セカンドオピニオン」などのリクエストで起動。
GitHub
ai-chain-modularize-plan
Create a plan to modularize the AI include chain.
GitHub
prompt-engineer
Provides expert guidance for writing and optimizing prompts for large language models. Use this skill when: (1) user mentions "prompt", "prompting", or "prompt engineering", (2) user requests to write, create,...
GitHub
checkpoint-find
Locate the latest checkpoint for a run id and provide a follow-up play/eval command. Use when asked to find a checkpoint.
GitHub
session-memory
Session memory management for pseudo-code prompting - preserves transformation context, learned patterns, and user preferences across sessions
GitHub
segment-image
This skill should be used when the user asks to "segment an image", "identify objects", "extract objects", "generate masks", "find objects in image", or needs AI-powered image segmentation.
GitHub
gemini-rlm-min
Minimal implementation of Recursive Language Models (RLM) using Gemini 2.0 Flash and a local Python REPL. Enables processing of massive contexts via the Gemini CLI.
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.