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…
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.
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.
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.
A paid-advertising audit skill for reviewing Google Ads, Microsoft Ads, and Meta accounts across account structure, tracking, bidding, creative, audiences, and competitor positioning.
A paid-media creative strategy skill for writing ad copy, improving responsive search ads, designing asset groups, and planning creative tests across Google, Meta, Microsoft, and programmatic platforms.
A social-advertising strategy skill for Meta, LinkedIn, TikTok, Pinterest, X, and Snapchat. It covers campaigns that attract new people and campaigns that target people who have already interacted with a business.
A paid-search strategy skill for Google Ads, Microsoft Advertising, and Amazon Ads, covering campaign structure, budget allocation, and bidding approaches.
A display and programmatic-ad buying skill for networks such as Google Display Network, DV360, and The Trade Desk. Programmatic buying uses software to purchase online ad placements, while DSPs are the platforms used to manage those purchases.
A search-query analysis skill for reviewing paid-search reports, finding search intent, and building negative-keyword structures. Negative keywords stop ads from showing for unwanted searches.
A paid-media tracking skill for designing conversion tracking with tools such as GTM, GA4, Google Ads, Meta CAPI, and LinkedIn Insight Tag. Conversion tracking records actions such as purchases, sign-ups, or enquiries.
A behavioural-design skill for changing the timing and style of software interactions to influence user motivation and help users complete their goals.
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.
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.
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 55▲
+1 4mo agoA38 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: