GitHub
rlm-orchestrator
Master skill for Recursive Language Model thinking — orchestrates long-context reasoning by treating prompts as environments, not inputs. Spawns sub-agents and manages recursive decomposition.
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
ai-context-documentation
Use this skill when editing files in ai/ or .claude/ folders.
GitHub
debugging
Use this skill any time you need to debug something or figure out why a problem is happening.
GitHub
outer-review
Commission and process external AI analysis to reduce blind spots. Manual invocation only.
GitHub
optimistic-review
Identify content strengths and opportunities for expansion. Suggests new topics and connections.
GitHub
research-voids
Research voids (cognitive gaps, unchartable territories). Daily. Outputs research notes for voids articles.
GitHub
refine-draft
Improve the quality of draft content. Runs review and applies improvements while preserving voice.
GitHub
deep-review
Comprehensive single-document review combining pessimistic and optimistic analysis with improvements. Modifies content.
GitHub
codex-subagent
Spawn subagents to offload context-heavy work. Use for: deep research (3+ searches), codebase exploration (8+ files), multi-step workflows, exploratory tasks, long-running operations, documentation generation,...
GitHub
documentation
Use when writing or updating documentation - generates function docs, API specs, architecture diagrams (Mermaid), READMEs, code explanations. Activates when user says "document this", "write README", "explain t...
GitHub
obsi-concept-distiller
AI를 활용해 핵심 개념을 추출하고, 문맥을 분석하여 지식 베이스(20_Learning)와 양방향으로 연결합니다.
GitHub
dev-prompt-engineering
Anthropic의 Best Practice를 기반으로 고성능 프롬프트를 설계하고 최적화합니다.
GitHub
auto-learner
Use this skill to learn from mistakes. Activate when Claude makes tool call errors, incorrect assumptions, oversights, or when the user corrects Claude. Maintains auto-learning.md as a knowledge base of lessons...
GitHub
skill-creation
Use this skill when the user asks to create a new skill, custom command, or wants to know how skills work in Claude Code.
GitHub
video-transcribe
動画・音声の文字起こし。ローカルWhisper（無料）とOpenAI API（高速）の2モード対応。
GitHub
nanobanana-prompts
NanoBanana（Google Gemini画像生成）向けの高品質プロンプトを生成。画像生成、編集、フェイススワップ、背景変更、キャラクター一貫性のプロンプト作成を支援。
GitHub
gemini-image-generator
Generate images using Google Gemini NanoBanana via browser automation. Use this skill for general-purpose AI image generation from text prompts. Includes persistent authentication, automatic environment setup,...
GitHub
distributed-claude-sender
Send prompts to a remote Claude instance on a VPS for distributed AI collaboration, different model backends, or independent context.
GitHub
distributed-claude-receiver
You are a remote Claude instance running on a VPS. Receive messages via chat.sh wrapper, maintain persistent context, use Z.ai GLM backend via Doppler.
GitHub
skill-creator
Guide for creating Agent Skills that extend Antigravity's capabilities. Use when creating new skills, updating existing skills, or packaging skills for distribution. Supports workspace skills (.agent/skills/) a...
GitHub
rules-workflows
Expert Guide for orchestrating Agent behaviors via Rules and Workflows. Capabilities include Autonomous Reasoning, Agile Process Management, and Cross-Skill Orchestration. Use to standardize project context (Ru...
GitHub
ai-engineer
Expert AI Engineer role (10+ Years Exp). Focuses on production-grade GenAI, Agentic Systems, Advanced RAG, and rigorous Evaluation.
GitHub
fx-explore
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatc...
GitHub
creating-skills
Create and improve Agent Skills with structured planning and best practices. Use when designing new Skills, enhancing existing Skills, refactoring existing Skills, or ensuring Skill quality in Claude Code.
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.