Import an OpenClaw setup (memories, skills) into Hermes.
Skills in this repository
lukemcqueen/hermes-cortex - Page 7
SkillsMP has collected 311 skills from lukemcqueen/hermes-cortex. Open a skill to review its source and details.
lukemcqueen/hermes-cortexShowing 40 of 311 collected skills.
Run PyTorch training across GPUs with minimal changes.
Embedding database for RAG and semantic search.
Zero-shot image classification and image-text search.
Fast vector similarity search at billion scale.
Speed up long-sequence transformer training and inference.
Constrain LLM output with grammars; guarantee valid JSON.
Outlines: structured JSON/regex/Pydantic LLM generation.
Structured LLM outputs validated with Pydantic.
On-demand GPU cloud instances for ML training.
Vision-language chat: VQA, captioning, image dialogue.
Serverless GPU cloud for ML jobs and model APIs.
Curate LLM training data: dedupe, filter, PII redaction.
Fine-tune large LLMs with LoRA on limited GPU memory.
Managed vector DB for production RAG and search.
Fully sharded data-parallel training for large models.
Clean training loops with built-in distributed support.
Vector search engine for production RAG systems.
Train sparse autoencoders to interpret model features.
Reference-free preference alignment, simpler than DPO.
RL post-training for LLMs with Megatron and SGLang.
Text-to-image generation, inpainting, and img2img.
High-throughput LLM inference on NVIDIA GPUs.
Pretrain LLMs at scale with PyTorch 4D parallelism.
TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.
Fetch Canvas LMS courses and assignments via API token.
Publish sites to {slug}.here.now and store files in Drives.
Provision Twilio numbers, SMS/MMS, and AI outbound calls.
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
Free keyless web, news, and image search via ddgs.
Serve an interactive codebase knowledge graph web UI.
Follow the money via public records and sanctions data.
Free keyless meta-search aggregating 70+ engines.
Set up op CLI, sign in, and read or inject secrets.
Small changes with real verification, bounded retries, self-healing. One change at a time. Never batch. Never skip verification. Triggers: 'fix tests', 'make tests pass', 'refactor', 'change-test loop', 'debug failing test'
Session management skill — checkpoint/restore, context compression, progress tracking, and recovery for maintaining continuity across agent sessions.
When scripts fail with NameError after a mass-edit commit.
Use when an arq worker crash-loops or runs no jobs.
Review agent commits for enforcement compliance.
Verify your health endpoint is externally reachable by testing the URL end-to-end instead of assuming local-only based on process checks.