itgoyo/multica-skills

310+ reusable AI agent skills for Multica / Hermes Agent

5Stars on the repository
200Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

whisper

169

itgoyo/multica-skills

Skill Claude CodeCodex

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

not rated 5 4mo ago B 67 tokens

dspy

170

itgoyo/multica-skills

Skill Claude CodeCodex

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.

not rated 5 4mo ago A 35 tokens

axolotl

171

itgoyo/multica-skills

Skill Claude CodeCodex

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.

not rated 5 4mo ago A 47 tokens

grpo-rl-training

172

itgoyo/multica-skills

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

not rated 5 4mo ago A 26 tokens

peft-fine-tuning

173

itgoyo/multica-skills

Skill Claude CodeCodex

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.

not rated 5 4mo ago A 82 tokens

pytorch-fsdp

174

itgoyo/multica-skills

Skill Claude CodeCodex

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2.

not rated 5 4mo ago B 37 tokens

fine-tuning-with-trl

175

itgoyo/multica-skills

Skill Claude CodeCodex

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

not rated 5 4mo ago A 69 tokens

unsloth

176

itgoyo/multica-skills

Skill Claude CodeCodex

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.

not rated 5 4mo ago A 39 tokens

obsidian

177

itgoyo/multica-skills

Skill Claude CodeCodex

Read, search, and create notes in the Obsidian vault.

not rated 5 4mo ago A 17 tokens

paid-media-auditor

178

itgoyo/multica-skills

Skill Claude CodeCodex

An advertising-account auditor for reviewing Google Ads, Microsoft Ads, and Meta accounts across structure, tracking, bidding, creative, audiences, and competitors.

not rated 5 4mo ago A 63 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A paid-media creative strategist for writing ad copy, improving responsive search ads, designing asset groups, and planning creative tests.

not rated 5 4mo ago A 52 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A paid-search advertising specialist for planning Google Ads, Microsoft Advertising, and Amazon Ads accounts, budgets, and bids.

not rated 5 4mo ago A 60 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A display-advertising and programmatic buying specialist for purchasing ads across websites and ad-buying platforms. A DSP is software used to buy digital advertising automatically.

not rated 5 4mo ago A 46 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A conversion-tracking specialist for connecting advertising platforms, analytics tools, and website code so conversions are recorded correctly. GTM is Google Tag Manager, and GA4 is Google Analytics 4.

not rated 5 4mo ago A 60 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A behavioral-design tool that changes the timing and style of software interactions to influence user motivation and completion.

not rated 5 4mo ago A 32 tokens

product-manager

187

itgoyo/multica-skills

Skill Claude CodeCodex

A simulated senior product manager focused on delivering products across business software, consumer apps, and platforms.

not rated 5 4mo ago A 67 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A product-planning tool for ranking requirements and planning development sprints. A sprint is a short, fixed period in which a team completes selected work.

not rated 5 4mo ago A 45 tokens

itgoyo/multica-skills

Skill Claude CodeCodex

A product-research tool for studying industry trends and anticipating technology changes over the next 6 to 18 months.

not rated 5 4mo ago A 43 tokens

google-workspace

190

itgoyo/multica-skills

Skill Claude CodeCodex

Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration for Hermes. Uses Hermes-managed OAuth2 setup, prefers the Google Workspace CLI (gws) when available for broader API coverage, and falls back to the Python client libraries otherwise.

not rated 5 4mo ago A 54 tokens

linear

191

itgoyo/multica-skills

Skill Claude CodeCodex

Manage Linear issues, projects, and teams via the GraphQL API. Create, update, search, and organize issues. Uses API key auth (no OAuth needed). All operations via curl — no dependencies.

not rated 5 4mo ago A 43 tokens

nano-pdf

192

itgoyo/multica-skills

Skill Claude CodeCodex

Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.

not rated 5 4mo ago A 38 tokens

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: