Tommy-yw/RunbookHermes - 第 3 页

codebase-inspection

Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.

原文语言：英语

github-auth

Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.

原文语言：英语

github-code-review

Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.

原文语言：英语

github-issues

Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.

原文语言：英语

github-pr-workflow

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

原文语言：英语

github-repo-management

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

原文语言：英语

native-mcp

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config…

原文语言：英语

gif-search

Search and download GIFs from Tenor using curl. No dependencies beyond curl and jq. Useful for finding reaction GIFs, creating visual content, and sending GIFs in chat.

原文语言：英语

heartmula

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

原文语言：英语

songsee

Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.

原文语言：英语

youtube-content

Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat…

原文语言：英语

evaluating-llms-harness

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,…

原文语言：英语

weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

原文语言：英语

huggingface-hub

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

原文语言：英语

llama-cpp

llama.cpp local GGUF inference + HF Hub model discovery.

原文语言：英语

obliteratus

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules,…

原文语言：英语

outlines

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

原文语言：英语

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints,…

原文语言：英语

audiocraft-audio-generation

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

原文语言：英语

segment-anything-model

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

原文语言：英语

dspy

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

原文语言：英语

axolotl

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

原文语言：英语

fine-tuning-with-trl

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…

原文语言：英语

unsloth

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

原文语言：英语

obsidian

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

原文语言：英语

google-workspace

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.

原文语言：英语

linear

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.

原文语言：英语

maps

Location intelligence — geocode a place, reverse-geocode coordinates, find nearby places (46 POI categories), driving/walking/cycling distance + time, turn-by-turn directions, timezone lookup, bounding box + area for a named place, and POI search within a…

原文语言：英语

nano-pdf

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.

原文语言：英语

notion

Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.

原文语言：英语

ocr-and-documents

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

原文语言：英语

godmode

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a…

原文语言：英语

blogwatcher

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher-cli tool. Add blogs, scan for new articles, track read status, and filter by category.

原文语言：英语

llm-wiki

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

原文语言：英语

polymarket

Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.

原文语言：英语

research-paper-writing

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative…

原文语言：英语

openhue

Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes.

原文语言：英语

xurl

Interact with X/Twitter via xurl, the official X API CLI. Use for posting, replying, quoting, searching, timelines, mentions, likes, reposts, bookmarks, follows, DMs, media upload, and raw v2 endpoint access.

原文语言：英语

plan

Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.

原文语言：英语

requesting-code-review

Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.

原文语言：英语