GitHub
scene-designer
Activate this skill when users need help creating, modifying, or arranging visual elements in OBS scenes. Triggers include requests like "add a text overlay", "create a new scene", "move my webcam", "resize the...
Skills IA Entreprise
Découvrez les skills Entreprise, comparez leurs dépôts et consultez leurs instructions.
Catégories: Entreprise
Entreprise Effacer les filtres
Explorer
GitHub
audio-engineer
Activate this skill when users need help with audio configuration, troubleshooting, or optimization in OBS. Triggers include requests like "fix my audio", "adjust microphone levels", "mute desktop audio", "bala...
GitHub
pr-review-loop
Manage the PR review feedback loop: monitor CI checks, fetch review comments, and iterate on fixes. Use when: (1) pushing changes to a PR and waiting for CI/reviews, (2) user says "new reviews available", (3) i...
GitHub
aws-diagram
Generate AWS architecture diagrams from infrastructure JSON. Use when user asks to "generate diagram", "create AWS diagram", "visualize infrastructure", or "draw architecture".
GitHub
aws-discover
Discover AWS infrastructure and save to JSON. Use when user asks to "discover AWS", "explore AWS account", "scan AWS infrastructure", or "create infrastructure JSON".
GitHub
conductor
Maintain Conductor-compatible project context, tracks, specs, and plans.
GitHub
funsloth-local
Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints
GitHub
funsloth-check
Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.
GitHub
funsloth-hfjobs
Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring
GitHub
funsloth-runpod
Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints
GitHub
funsloth-upload
Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation
GitHub
funsloth-train
Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
GitHub
pda-reframing
Rephrase tasks and requests by avoiding Demand Avoidance triggers for someone with PDA autism spectrum disorder. It transforms demands into exploration and autonomous actions.
GitHub
doc-management
Documentation lifecycle management skill. Activates when user mentions documentation, docs, sync, quality, validation, releases, or setup. Routes to appropriate agent (doc-expert for orchestration, doc-writer f...
GitHub
doc-writer-expertise
Deep expertise for documentation content creation. Templates, platform formatting guides, and style principles. Auto-loads for doc-writer agent.
GitHub
doc-expert-expertise
Deep expertise for documentation lifecycle orchestration. Quality assessment frameworks, workflow patterns, delegation protocols, and release checklists. Auto-loads for doc-expert agent.
GitHub
codex-subagent
Helps you to run a subagent using codex exec
GitHub
mcp-builder
LLMが外部サービスと対話するための適切に設計されたツールを通じて、高品質なMCP (Model Context Protocol) サーバーを作成するためのガイド。Python (FastMCP)、Node/TypeScript (MCP SDK)、Rust (Tokio)で、外部APIやサービ...
GitHub
zed-editor
Zed Editorの特徴、ACP（Agent Client Protocol）の仕様、AI統合、パフォーマンス特性、設定方法について包括的な知識を提供します。Zed Editorに関する質問、ACP対応エージェントの統合、設定のカスタマイズが必要な場合に使...
GitHub
docs-director-skill
Handles multi-document operations with pattern matching and parallel execution, delegating to docs-manager-skill for each matched document
GitHub
faber-debugger
Universal debugger skill that diagnoses workflow issues and proposes solutions using a persistent knowledge base
GitHub
issue-creator
Create new issues in work tracking systems via Fractary CLI
GitHub
spec-archiver
Archives completed specifications to cloud storage with index management, GitHub commenting, and local cleanup
GitHub
handler-work-tracker-linear
[DEPRECATED] Linear handler - Use Fractary CLI instead
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.