191 attribution-first agent skills for Hermes Agent, Claude Code, Cursor — one installer, 28 categories, searchable catalog. See NOTICE for upstream attribution.
Skill Claude CodeCodex
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Skill Claude CodeCodex
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude Code
Compact the current conversation into a handoff document for another agent to pick up.
Skill Claude CodeCodex
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Skill Claude CodeCodex
Search/download GIFs from Tenor via curl + jq.
Skill Claude CodeCodex
HeartMuLa: Suno-like song generation from lyrics + tags.
Skill Claude CodeCodex
Audio spectrograms/features (mel, chroma, MFCC) via CLI.
Skill Claude CodeCodex
Spotify: play, search, queue, manage playlists and devices.
Skill Claude CodeCodex
YouTube transcripts to summaries, threads, blogs.
Skill Claude CodeCodex
Setup and optimize cryptocurrency mining operations — AI-powered mining (soul.md protocol), parallel agent deployment, accumulation strategies, and performance optimization.
Skill Claude CodeCodex
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Skill Claude CodeCodex
W&B: log ML experiments, sweeps, model registry, dashboards.
Skill Claude CodeCodex
HuggingFace hf CLI: search/download/upload models, datasets.
Skill Claude CodeCodex
Use this skill for local GGUF inference, quant selection, or Hugging Face repo discovery for llama.cpp.
Skill Claude CodeCodex needs its repo
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Skill Claude CodeCodex
Outlines: structured JSON/regex/Pydantic LLM generation.
Skill Claude CodeCodex
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Skill Claude CodeCodex
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
Skill Claude CodeCodex needs its repo
SAM: zero-shot image segmentation via points, boxes, masks.
Skill Claude CodeCodex
DSPy: declarative LM programs, auto-optimize prompts, RAG.
Skill Claude CodeCodex needs its repo
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
Skill Claude CodeCodex
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: