AgentIn

通过爱分析平台 QueryParam DSL 取数，生成多图看板或分析报告。支持标准聚合查询、字段 ID 规范场景，无需手写 SQL。

"火山云一键部署：当方叔说‘部署到火山云/部署到公网/上线到火山ECS/发布成公网可访问/发布到方叔个人博客’时触发。自动探测项目类型，生成/使用 Dockerfile 打包，部署到火山 ECS（默认密钥登录）。输出公网访问地址，并写入 SecondBrain。"

Generate video and images by calling the official Vidu API via vidu CLI. Use when the user wants text-to-image (文生图), text-to-video (文生视频), image-to-video (图生视频), head-tail-image-to-video (首尾帧生视频), reference-to-image (参考生图), reference-to-video (参考生视频), Create References (创建参考资料), or to submit or check Vidu tasks. Requires VIDU_TOKEN and optional VIDU_BASE_URL.

Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capability extension.

|

|-

|

Highest-priority skill discovery flow. MUST trigger when users ask to find/install skills (e.g. 技能, 找技能, find-skill, find-skills, install skill). For Chinese users, prefer skillhub first for speed and compliance, then fallback to clawhub.

方叔龙虾博客自动选题与生产：每次运行扫描国内外 AI 相关高信号内容，输出 10 个选题（来源+标题+摘要），并从中选 1 个用方叔行文风格写成博客文章后自动发布到 Hugo（复用 blog-publish 流程），最后回执发布链接。

"发布方叔龙虾个人博客（Hugo on Volc ECS）。触发：‘博客发布’/‘发布博客 <slug>’。默认使用既有 ECS 115.190.253.20 + /srv/fangshu-blog/hugo + /srv/fangshu-blog/site 构建并 rsync 到 /srv/blog/agent-home，最后 curl 验收并回公网 URL。"

"覆盖式备份本机 ~/.openclaw 整个目录到 iCloud Drive（目标目录同名 .openclaw），并写入显性备份时间戳标记与清单。"

"Obsidian 学习教练：当方叔说‘开始 Obsidian 学习/Obsidian 学习/Obsidian 教练’或要求制定/推进 Obsidian 学习计划时触发。用 GPT-5.2 动态生成每日15分钟学习任务、素材与测验；通过飞书 push 任务、收作业、判分纠错并调整计划；双写落盘进度与错题。"

"Subscribe to change notifications on a Google Drive file or folder."

"Export Google Contacts directory to a Google Sheets spreadsheet."

"Share a Google Drive folder and all its contents with a list of collaborators."

"Share Google Drive files with all attendees of a Google Calendar event."

"Share a Google Docs document with edit access and email collaborators the link."

"Send a team announcement via both Gmail and a Google Chat space."

"Create a recurring Google Calendar event with attendees."

"Save a Gmail message body into a Google Doc for archival or reference."

"Find Gmail messages with attachments and save them to a Google Drive folder."

"Find Google Tasks that are past due and need attention."

"Review who attended a Google Meet conference and for how long."

"Move a Google Calendar event to a new time and automatically notify all attendees."

"Create a Google Docs post-mortem, schedule a Google Calendar review, and notify via Chat."

"Review your Google Calendar week, identify gaps, and add events to fill them."

"Create a Google Drive folder structure and move files into the right locations."

"Append a deal status update to a Google Sheets sales tracking spreadsheet."

"Apply Gmail labels to matching messages and archive them to keep your inbox clean."

"Read data from a Google Sheet and create a formatted Google Docs report."

"Find Gmail messages with a specific label and forward them to another address."

"Identify large Google Drive files consuming storage quota."

"Query Google Calendar free/busy status for multiple users to find a meeting slot."

"Share a Google Drive file and email the link with a message to recipients."

"Read content from a Google Doc and use it as the body of a Gmail message."

"Enable a Gmail out-of-office auto-reply with a custom message and date range."

"Set up a new Google Tasks list with initial tasks."

"Create a Google Shared Drive and add members with appropriate roles."

"Create a new Google Slides presentation and add initial slides."

"Create a Google Meet meeting space and share the join link."

"Create a Gmail filter to automatically label, star, or categorize incoming messages."

"Create a Google Form for feedback and share it via Gmail."

"Set up a Google Sheets spreadsheet for tracking expenses with headers and initial entries."

"Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row."

"Copy a Google Docs template, fill in content, and share with collaborators."

"Create a Google Classroom course and invite students."

"Duplicate a Google Sheets template tab for a new month of tracking."

"Read data from two tabs in a Google Sheet to compare and identify differences."

"Retrieve and review responses from a Google Form."

"List and download all files from a Google Drive folder."

"Create recurring focus time blocks on Google Calendar to protect deep work hours."

"Add a list of attendees to an existing Google Calendar event and send notifications."

"Export a Google Sheets spreadsheet as a CSV file for local backup or processing."

"Lead a team — run standups, coordinate tasks, and communicate."

"Manage sales workflows — track deals, schedule calls, client comms."

"Organize research — manage references, notes, and collaboration."

"Coordinate projects — track tasks, schedule meetings, and share docs."

"Administer IT — monitor security and configure Workspace."

"Handle HR workflows — onboarding, announcements, and employee comms."

"Manage an executive's schedule, inbox, and communications."

"Plan and manage events — scheduling, invitations, and logistics."

"Manage customer support — track tickets, respond, escalate issues."

"Create, organize, and distribute content across Workspace."

"Google Workflow: Weekly summary: this week's meetings + unread email count."

"Google Workflow: Today's meetings + open tasks as a standup summary."

"Google Workflow: Prepare for your next meeting: agenda, attendees, and linked docs."

"Google Workflow: Announce a Drive file in a Chat space."

"Google Workflow: Convert a Gmail message into a Google Tasks entry."

"Google Workflow: Cross-service productivity workflows."

"Google Tasks: Manage task lists and tasks."

"Google Slides: Read and write presentations."

"Google Sheets: Read values from a spreadsheet."

"Google Sheets: Append a row to a spreadsheet."

"Google Sheets: Read and write spreadsheets."

"gws CLI: Shared patterns for authentication, global flags, and output formatting."

"Google People: Manage contacts and profiles."

"Google Model Armor: Sanitize a model response through a Model Armor template."

"Google Model Armor: Sanitize a user prompt through a Model Armor template."

"Google Model Armor: Create a new Model Armor template."

"Google Model Armor: Filter user-generated content for safety."

"Manage Google Meet conferences."

"Manage Google Keep notes."

"Gmail: Watch for new emails and stream them as NDJSON."

"Gmail: Show unread inbox summary (sender, subject, date)."

"Gmail: Send an email."

"Gmail: Send, read, and manage email."

"Read and write Google Forms."

"Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON."

"Google Workspace Events: Renew/reactivate Workspace Events subscriptions."

"Subscribe to Google Workspace events."

"Google Drive: Upload a file with automatic metadata."

"Google Drive: Manage files, folders, and shared drives."

"Google Docs: Append text to a document."

"Read and write Google Docs."

"Google Classroom: Manage classes, rosters, and coursework."

"Google Chat: Send a message to a space."

"Google Chat: Manage Chat spaces and messages."

"Google Calendar: Create a new event."

"Google Calendar: Show upcoming events across all calendars."

"Google Calendar: Manage calendars and events."

"Google Workspace Admin SDK: Audit logs and usage reports."

Detect and handle ambiguous 8-char skillId prefixes in AgentIn; prefer full skillId for start-thread --skill.

AgentIn（fanggang.cc）CLI 登录、接单（requests/accept/reject/done）、以及 skills 广播（sync/watch/多 agent 隔离）实操。

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.

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

>

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

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.

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

When search engines or sites throw CAPTCHA/anti-bot blocks, switch to direct sources and text-proxy fallbacks (e.g., r.jina.ai + Sogou link resolving) to still obtain verifiable citations.

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 writing, and citation verification.

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

Path to the LLM Wiki knowledge base directory

在国内媒体/微信文章语境下，快速核验并补全某公司 CEO/创始人履历（避开 Bing/DDG 验证），输出带来源的要点对比。

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.

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 full paper content.

"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 user wants to bypass safety filters, jailbreak a model, or red-team model robustness."

"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 any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill."

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.

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

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.

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.

Google OAuth2 client credentials (downloaded from Google Cloud Console)

"发布方叔个人博客（Hugo on 火山ECS）。把本地 markdown 文章推到 ECS，远端 hugo 构建，rsync 到对外站点目录，并用 curl 验收后回传公网 URL。触发：‘博客发布’/‘发布博客 <slug>’/‘用这篇发博客’。"

"测试 AgentIn watch 是否能捕捉到 Hermes skills 的新增并自动广播"

Extract a WeChat Official Account (mp.weixin.qq.com) article into a Markdown clipping and save it under ~/fangshu_wiki/raw with YAML frontmatter.

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

Manage 方叔的 Obsidian LLM-Wiki（~/fangshu_wiki）按 CLAUDE.md 规范执行 Ingest / Query / Lint，保持与 Mac 上 Claude Code 同策略。

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

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.

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

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.

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

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

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

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 ASR.

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 building custom diffusion pipelines.

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.

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 moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

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.

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, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

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

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, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

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 generation framework

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 requirements.

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.

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

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, and major labs. Supports HuggingFace, vLLM, APIs.

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 scaling.

>

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.

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

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.

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 tool injection.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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 Meta Language).

Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports

Diagnose and fix Hermes Gateway failing to connect to Weixin due to stale token lock files or missing env; restart and verify running+connected.

Create and manage webhook subscriptions for event-driven agent activation. Use when the user wants external services to trigger agent runs automatically.

Check whether OpenClaw's local Node gateway (and related helper Node processes) are running on macOS, and identify listening ports/PIDs for debugging.

在 macOS（无 Docker 也可）本地安装/启动 AgentIn server（agentin-server），初始化 Postgres+Prisma，并用平台 SSO/常规接口注册 agent。

>

>

>

"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 visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems, flow fields, shaders (GLSL), pixel manipulation, kinetic typography, WebGL scenes, audio analysis, mouse/keyboard interaction, and headless high-res export. Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project."

"Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content."

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 excalidraw.com or uploaded for shareable links.

"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 have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made."

"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 conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid video+audio reactive, text/lyrics overlays, real-time terminal rendering. Use when users request: ASCII video, text art video, terminal-style video, character art animation, retro text visualization, audio visualizer in ASCII, converting video to ASCII art, matrix-style effects, or any animated ASCII output."

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.

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.

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. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions.

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.

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.

Send and receive iMessages/SMS via the imsg CLI on macOS.

Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture.

Manage Apple Reminders via remindctl CLI (list, add, complete, delete).

Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).