Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
voicemode-connect
mbailey
Remote voice via VoiceMode Connect. Use when users want to add voice to Claude Code using their phone or web app, without local STT/TTS setup.
ln-111-root-docs-creator
levnikolaevich
Creates 4 root documentation files (CLAUDE.md, docs/README.md, documentation_standards.md, principles.md). L3 Worker invoked by ln-110-project-docs-coordinator.
gguf-quantization
NousResearch
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
obliteratus
NousResearch
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods (+ 4 Python-API-only), 15 analysis modules, 116 model presets across 5 compute tiers. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
guidance
NousResearch
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
dspy
NousResearch
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
claude-code
NousResearch
Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.
axolotl
NousResearch
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
peft-fine-tuning
NousResearch
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
llava
NousResearch
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
openhands
NousResearch
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
flow-next-export-context
gmickel
Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on /flow-next:export-context.
skill-parallel-agents
nyldn
Multi-tentacled orchestration using Double Diamond methodology. Use when: PRIORITY TRIGGERS (always invoke immediately):. "/octo:multi" (explicit command). "run this with all providers", "run with all providers"
skill-resume-enhanced
nyldn
Enhanced session resumption resilient to context clearing. Use when: AUTOMATICALLY ACTIVATE when:. User says "resume", "continue", "pick up where we left off". User asks "what was I working on", "where did we leave off"
flow-discover
nyldn
Multi-AI research using Codex and Gemini CLIs (Double Diamond Discover phase). Use when: AUTOMATICALLY ACTIVATE when user requests research or exploration:. "research X" or "explore Y" or "investigate Z". "what are the options for X" or "what are my choices for Y"
skill-knowledge-work
nyldn
Override context auto-detection (Dev vs Knowledge mode)
skill-validate
nyldn
Multi-AI validation combining debate, quality scoring, and issue extraction
flow-define
nyldn
Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase). Use when: AUTOMATICALLY ACTIVATE when user requests clarification or scoping:. "define the requirements for X". "clarify the scope of Y"
skill-debate-integration
nyldn
Internal: quality gates and export for AI debates. Use when: AUTOMATICALLY ACTIVATE when:. User runs /debate command. AI Debate Hub (.dependencies/claude-skills/skills/debate.md) is present
sys-configure
nyldn
Configure Claude Octopus providers and preferences. Use when: Use this skill when the user wants to "configure Claude Octopus", "setup octopus",. "configure providers", "set up API keys for octopus", or mentions octopus configuration.
flow-develop
nyldn
Multi-AI implementation using Codex and Gemini CLIs (Double Diamond Develop phase). Use when: AUTOMATICALLY ACTIVATE when user requests building or implementation:. "build X" or "implement Y" or "create Z". "develop a feature for X"
skill-debate
nyldn
Structured three-way AI debates between Claude, Gemini, and Codex. Use when: AUTOMATICALLY ACTIVATE when user says:. "/debate <question>". "run a debate about X"
skill-context-detection
nyldn
Auto-detect work context (Dev vs Knowledge) for workflow tailoring
skill-meta-prompt
nyldn
Generate optimized prompts using proven techniques. Use when: Use PROACTIVELY when user wants to:. "create a prompt for", "write a prompt for". "optimize this prompt", "improve this prompt"