跳转至

技能清单（Skills）

自动从 ~/.hermes/profiles/friend/skills/ 镜像。每天 04:00 cron 自动同步。

共 119 个 active skill，分 27 个 category。

_root（5）

  • cazalis-dissolve-system-v3 — Cazalis zigai 7套衣服溶解换衣系统的最终工作版本（V3 FX Controller），含完整的4状态循环架构、clip对应关系、wd配置、Shorts/Bra/Foot_Heel规则、多Avatar架构、以及部署验证要点
  • dogfood — Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports
  • liltoon-dissolve-material-batch — Batch-configure lilToon dissolve parameters on multiple clothing materials remotely via Unity MCP. Covers the exact property values, scene-based material discovery, and solving stubborn materials via
  • server-health-audit — Safe server environment audit and optimization — check services, clean stale configs, remove dead cron jobs, free disk space. Never breaks running services.

  • vrchat-av3emulator-research — Comprehensive research on Lyuma's Av3Emulator for VRChat avatar creation — installation, features, conflicts, and usage guide. Lyuma's Av3Emulator for VRChat avatar creation — installation, features, conflicts, and usage guide.## apple（4）

  • apple-notes — Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).

  • apple-reminders — Manage Apple Reminders via remindctl CLI (list, add, complete, delete).
  • findmy — Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture.
  • imessage — Send and receive iMessages/SMS via the imsg CLI on macOS. pture.

  • imessage — Send and receive iMessages/SMS via the imsg CLI on macOS.## autonomous-ai-agents（6）

  • claude-code — Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.

  • codex — Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
  • hermes-agent — Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference
  • interagent-communication — 两个 Hermes Agent 实例通过 API Server 互调，实现跨实例协作
  • openclaw-task-delegation — Deploy and delegate complex tasks to OpenClaw agent — wrapper scripts + task guide + handoff protocol, respecting OpenClaw's sandbox constraints and 8-tool-call limit.
  • opencode — Delegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessions. Requires the opencode CLI installed and authenticated. review, and long-running autonomous sessions. Requires the opencode CLI installed and authenticated.## creative（12）

creative（12）- architecture-diagram — Generate dark-themed SVG diagrams of software systems and cloud infrastructure as standalone HTML files with inline SVG graphics. Semantic component colors (cyan=frontend, emerald=backend, violet=data

  • ascii-art — Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.
  • ascii-video — Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversi
  • baoyu-comic — Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画",
  • baoyu-infographic — Generate professional infographics with 21 layout types and 21 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks t
  • creative-ideation — Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I
  • [excalidraw](creati idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I
  • [excalidraw](creatiidea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I
  • excalidraw — Create hand-drawn style diagrams using Excalidraw JSON format. Generate .excalidraw files for architecture diagrams, flowcharts, sequence diagrams, concept maps, and more. Files can be opened at excal
  • manim-video — Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture di
  • p5js — Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visua
  • pixel-art — Convert images into retro pixel art with hardware-accurate palettes (NES, Game Boy, PICO-8, C64, etc.), and animate them into short videos. Presets cover arcade, SNES, and 10+ era-correct looks. Use `
  • popular-web-designs — >
  • songwriting-and-ai-music — > popular-web-designs.md) — >

  • songwriting-and-ai-music — >## data-science（3）

  • a-share-short-term-screening — A股短线强势股筛选 — 从实时数据采集（新浪/东方财富API）到多因子+技术面综合分析的完整流程

  • jupyter-live-kernel — >
  • tradingagents-astock-quick-recommend — A股荐股分析的完整工作流。核心经验：不要死磕固定候选池 + 不要依赖单一LLM源 + 用实时数据替代LLM通用知识。用户空仓时偏好防御性/确定性强的标的。 -quick-recommend.md) — A股荐股分析的完整工作流。核心经验：不要死磕固定候选池 + 不要依赖单一LLM源 + 用实时数据替代LLM通用知识。用户空仓时偏好防御性/确定性强的标的。## devops（9）
  • feishu-group-policy-fix — 飞书机器人群组策略排障 — 默认白名单导致群消息被拒的解决方案
  • lark-cli-install — Install and configure lark-cli (飞书官方 CLI) from source, bind to Hermes Agent, and complete OAuth authorization.
  • minimax-coding-plan-compat — MiniMax Coding Plan (sk-cp- Token Plan Key) 的各种 API 调用限制和兼容方案。Coding Plan Key 只能调 MCP 工具，不能直接调 Chat Completions/文本生成 API。
  • server-environment-audit — Comprehensive server environment audit and safe optimization — check all services, configs, cron jobs, disk, and memory, then fix issues without breaking running services.
  • shared-vector-search — Hermes 与 OpenClaw 共享的向量语义检索+写入 — 共用 LanceDB + doubao-embedding-vision，支持双向同步
  • skill-inventory-to-wiki — 扫描服务器上所有 SKILL.md 文件（Hermes active + OpenClaw 遗留），解析 frontmatter 提取 name/description/category，去重后生成按分类组织的 wiki 页面并部署。
  • webhook-subscriptions — Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR pus otifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR pusotifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push not
  • wiki-deploy — Wiki 部署流程 — DB→渲染→mkdocs build→rsync。LanceDB 是唯一数据源 h not

  • wiki-deploy — Wiki 部署流程 — DB→渲染→mkdocs build→rsync。LanceDB 是唯一数据源## email（1）

  • himalaya — CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME## gaming（14）

gaming（14）- animatorcontroller-csharp-pitfalls — Critical pitfalls when modifying Unity AnimatorController via C# API — struct value types, sub-asset serialization, and safe alternatives

  • minecraft-modpack-server — Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
  • pokemon-player — Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.
  • vrchat-4state-toggle-dissolve-system — VRChat 4状态循环换衣系统实战方案 — Int参数控制互斥 + Toggle菜单 + lilToon Dissolve。Cazalis zigai项目实战验证。
  • vrchat-blendshape-body-adjustment — 通过 Unity MCP 远程调整衣服 prefab 的 Blendshape 来适配 Cazalis zigai 等修改过体型的模型
  • vrchat-clothing-dissolve-workflow — 完整的 VRChat 换装+溶解工作流 — 从录制 ON/OFF/Hide 动画、配置 lilToon 材质、搭建 4 状态 Animator Layer、到 Int 参数菜单联动。基于 Cazalis zigai 项目实战验证，包含每步的具体参数数值和关键帧数据。
  • vrchat-dissolve-transition-system — VRChat渐变换衣系统 — 基于lilToon Dissolve + 每套衣服独立Layer + Int参数控制切换。从B站教程视频"落羽松_Taxod"逐帧分析提取的完整方案。
  • [vrchat-dress-bra-link-layer](gaming/vrchat 衣服独立Layer + Int参数控制切换。从B站教程视频"落羽松_Taxod"逐帧分析提取的完整方案。
  • [vrchat-dress-bra-link-layer](gaming/vrchat衣服独立Layer + Int参数控制切换。从B站教程视频"落羽松_Taxod"逐帧分析提取的完整方案。
  • vrchat-dress-bra-link-layer — Correct implementation of Dress-Bra/Shorts linkage in VRChat FX Controller — higher layer overrides underwear when Dress is worn
  • vrchat-foot-heel-linkage — Link Foot_Heel blendshape to wardrobe clothing states via animation clips in FX Controller Layer
  • vrchat-gogo-loco-integration — GoGo Loco (NSFW Locomotion) 整合到已有 VRChat Avatar 的完整流程 — 基于 Modular Avatar 方案，含浮空/飞行/姿势控制。Cazalis zigai 项目专用。
  • vrchat-ma-blendshape-sync-fix — 修复 ModularAvatarBlendshapeSync 组件的 MA-1005 警告（referencePath / Blendshape 字段错填），含 Unity MCP 反射批量修复脚本和 Cazalis 服装包已知 bug
  • vrchat-study-session — VRChat改模深度学习定时任务 — 每次执行时加载知识库、研究未覆盖的深层技术点、追加笔记到 /root/.hermes/profiles/friend/wiki/vrchat_modding_study.md
  • vrchat-toggle-parameter-linkage — Complete guide for adding new Toggle-based clothing controls to VRChat avatars — ensuring the full linkage chain from Menu Toggle → VRCExpressionParameters → FX Controller conditions → AnimationClip i

  • vrchat-unity-mcp — VRChat Unity MCP connection via Cloudflare Tunnel — connection, protocol, and environment inspection VRChat Unity MCP connection via Cloudflare Tunnel — connection, protocol, and environment inspectionent inspection ent inspection## github（6）

  • 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.

  • 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 met
  • 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.
  • 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.
  • 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.

  • 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. secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.## leisure（1）

  • find-nearby — Find nearby places (restaurants, cafes, bars, pharmacies, etc.) using OpenStreetMap. Works with coordinates, addresses, cities, zip codes, or Telegram location pins. No API keys needed.

mcp（3）

  • mcporter — Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
  • 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 auto

  • volcengine-askecho-search — 火山方舟联网搜索 MCP（askecho-search-infinity）—— 国内可用的真·联网搜索 API，直调 feedcoopapi 端点。按量计费，Key 从 OpenClaw 配置共享。 火山方舟联网搜索 MCP（askecho-search-infinity）—— 国内可用的真·联网搜索 API，直调 feedcoopapi 端点。按量计费，Key 从 OpenClaw 配置共享。## media（5）

  • bilibili-video-download-analyze — Download Bilibili videos from restricted network environments (China server, no browser access) — bypasses B站反爬 via direct API, downloads video+audio streams separately, merges with ffmpeg, and extrac

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

mlops（1）

  • 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.

mlops-cloud（1）

  • modal — Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scal ut infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scal## mlops-evaluation（2）

  • lm-evaluation-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 p

  • 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 imize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform## mlops-inference（6）

  • gguf — GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU re

  • guidance — Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained genera
  • llama-cpp — llama.cpp local GGUF inference + HF Hub model discovery.
  • 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
  • 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'

  • 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 GP ying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GP## mlops-models（5）

  • audiocraft — 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 melod

  • clip — OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content m
  • segment-anything — 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
  • stable-diffusion — State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or bu

  • whisper — 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 par to English, and language identification. Six model sizes from tiny (39M params) to large (1550M par## mlops-research（1）

  • 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

mlops-training（6）

  • axolotl — Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
  • grpo-rl-training — Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
  • peft — 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 a
  • pytorch-fsdp — Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
  • trl-fine-tuning — 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

  • unsloth — Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization or fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization## note-taking（1）

  • obsidian — Read, search, and create notes in the Obsidian vault. （1）

  • obsidian — Read, search, and create notes in the Obsidian vault.## productivity（7）

  • 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

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

  • powerpoint — Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from a es: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from a## red-teaming（1）

  • 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 , GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and## research（6）

  • arxiv — Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read

  • 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.
  • liltoon-source-analysis — Systematic approach for analyzing lilToon shader source code — tracing the alpha/dissolve pipeline execution order, finding property definitions, and understanding how shader features interact. Based
  • llm-wiki — Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
  • polymarket — Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.

  • 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 e fting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated e## smart-home（1）

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

social-media（2）

  • xitter — Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.
  • 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 ing, timelines, mentions, likes, reposts, bookmarks, follows, DMs, media upload, and raw v2 endpoint## software-development（8）

software-development（8）- fanwei-e9-ot-control — 泛微E9表单根据申报加班人数动态控制加班明细必填/只读，自动赋值申请人工号完整代码

  • 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.
  • requesting-code-review — >
  • subagent-driven-development — Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).
  • systematic-debugging — Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
  • test-driven-development — Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
  • write-file-recovery-procedure — Recovery procedure when write_file accidentally overwrites a large file instead of appending. Covers detection, data recovery via session search, and safe reconstruction using terminal/cat instead of

  • writing-plans — Use when you have a spec or requirements for a multi-s ns](software-development/writing-plans.md) — Use when you have a spec or requirements for a multi-sns](software-development/writing-plans.md) — Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples. prehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.## vrchat（2）

  • liltoon-batch-brightness-fix — 修复VRChat暗环境模型变黑，批量调整lilToon的_LightMinLimit参数

  • vrchat-simplified-avatar-creation — 从完整版VRChat Avatar创建精简版变体的完整工作流 — 场景内Instantiate、移除多余子对象、创建独立Params/Menu、处理共享材质、设置taozhuang默认值