🧬 018T Hermes Agent Skill Atlas / 技能图谱
面向个人成长（C端）与企业赋能（B端）的全栈AI代理技能矩阵。
For individual growth (C-side) and enterprise enablement (B-side) — full-stack AI agent capability matrix.
109 Skills / 个技能 · 24 Categories / 个分类
Full-stack AI Agent Capability Matrix / 全栈AI代理能力矩阵
🍎 Apple生态 | 🤖 自主AI代理 | 🎨 创意与设计 | 📊 数据科学 | 🛠️ DevOps | 📧 邮件 | 🎮 游戏 | 🐙 GitHub | 🧬 IdentityOS 五阶身份重塑 | 📚 知识管理 | 🔗 MCP协议 | 🎵 媒体与音频 | 🧠 MLOps | 📝 笔记系统 | ⚡ 效率工具 | ⚔️ 红队安全 | 🔬 研究与论文 | 📈 SEO | 🏠 智能家居 | 📱 社交媒体 | 💻 软件开发 | 🕸️ 网页抓取 | 🔌 WordPress
🍎 Apple生态
🍎 Apple Ecosystem
🧬 IdentityOS 5-Stage Identity Reshaping
| Skill | Description | Size |
|---|---|---|
| apple-notes | Manage Apple Notes via the memo CLI on macOS (create, view, search, edit) | 2.1KB |
| apple-reminders | Manage Apple Reminders via remindctl CLI (list, add, complete, delete) | 2.5KB |
| findmy | Track Apple devices and AirTags via FindMy.app on macOS using AppleScript and screen capture | 3.7KB |
| imessage | Send and receive iMessages/SMS via the imsg CLI on macOS | 2.4KB |
🤖 自主AI代理
🤖 Autonomous AI Agents
🔌 WordPress
| Skill | Description | Size |
|---|---|---|
| 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 | 33.6KB |
| 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 | 4.0KB |
| 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. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions | 28.6KB |
| 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 | 7.2KB |
🎨 创意与设计
🎨 Creative & Design
📚 Knowledge Management
| Skill | Description | Size |
|---|---|---|
| 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=database, amber=cloud/AWS, rose=security, orange=message bus), JetBrains Mono font, grid background. Best suited for software architecture, cloud/VPC topology, microservice maps, service-mesh diagrams, database + API layer diagrams, security groups, message buses — anything that fits a tech-infra deck with a dark aesthetic. If a more specialized diagramming skill exists for the subject (scientific, educational, hand-drawn, animated, etc.), prefer that — otherwise this skill can also serve as a general-purpose SVG diagram fallback. Based on Cocoon AI’s architecture-diagram-generator (MIT) | 6.4KB |
| 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 | 10.4KB |
| 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 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.” | 14.4KB |
| 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”, “教育漫画”, “biography comic”, “tutorial comic”, or “Logicomix-style comic” | 14.5KB |
| 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 to create “infographic”, “visual summary”, “信息图”, “可视化”, or “高密度信息大图” | 10.4KB |
| 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 have tools but no direction’. Works for code, art, hardware, writing, tools, and anything that can be made.” | 6.1KB |
| design-md | Author, validate, diff, and export DESIGN.md files — Google’s open-source format spec that gives coding agents a persistent, structured understanding of a design system (tokens + rationale in one file). Use when building a design system, porting style rules between projects, generating UI with consistent brand, or auditing accessibility/contrast | 7.0KB |
| 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 excalidraw.com or uploaded for shareable links | 7.1KB |
| ffmpeg-text-explainer-video | 用 ffmpeg drawtext 生成纯文字讲解视频（竖屏9:16，适合短视频平台），无需 TTS/图片/第三方库 | 8.7KB |
| manim-video | “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.” | 11.7KB |
| 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 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.” | 26.7KB |
| 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 `clarify` to let the user pick a style before generating | 7.6KB |
| popular-web-designs | > | 9.2KB |
| songwriting-and-ai-music | > | 10.1KB |
📊 数据科学
📊 Data Science
🎨 Creative & Design
| Skill | Description | Size |
|---|---|---|
| jupyter-live-kernel | > | 5.4KB |
🛠️ DevOps
🛠️ DevOps
⚡ Productivity
| Skill | Description | Size |
|---|---|---|
| oneapi-multi-channel-isolation | Solve OneAPI multi-channel model routing conflicts by deploying isolated instances per use case. Documents the known routing bug where even token-level model restrictions fail with multiple channels | 3.9KB |
| overlay-filesystem-batch-deletion | When large file sets (200+ files matching a single glob) on Docker overlay filesystem cause timeout on rm/find -delete, use iterative prefix-based for loops instead | 1.7KB |
| 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 push notifications to chats | 6.8KB |
📧 邮件
📧 Email
💻 Software Development
| Skill | Description | Size |
|---|---|---|
| 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 Meta Language) | 5.9KB |
🎮 游戏
🎮 Gaming
🐙 GitHub
| Skill | Description | Size |
|---|---|---|
| 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 | 6.5KB |
| 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 | 8.6KB |
🐙 GitHub
🐙 GitHub
🤖 Autonomous AI Agents
| Skill | Description | Size |
|---|---|---|
| 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 | 3.7KB |
| 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 | 7.5KB |
| 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 | 13.3KB |
| 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 | 9.1KB |
| 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 | 9.8KB |
| 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 | 13.5KB |
🧬 IdentityOS 五阶身份重塑
🧬 IdentityOS 5-Stage Identity Reshaping
🛠️ DevOps
| Skill | Description | Size |
|---|---|---|
| identityos-ai-collaboration-protocol | IdentityOS v6.1 AI身份协同协议 — AI作为身份主体参与用户身份系统的操作总纲。大/中/小身份嵌套模型、AI多重角色切换（执行官/镜像师/战略官/破局者/记录官/教练）、思考外包协议、成瘾性钩子设计。打铁还得自身硬。 | 4.1KB |
| identityos-api-gateway | 用 OneAPI + 纯标准库 Python 服务搭建 IdentityOS 知识注入 API 网关。客户通过 OneAPI 令牌访问，网关注入五阶身份重塑知识后转发至 DeepSeek。 | 10.8KB |
| identityos-auditor-v2 | IdentityOS v6.1 二进制审计引擎 — 看说做全维度硬判定，拒绝模糊。原声回溯扫描+OCR视觉证据验证+认知负载预警 | 5.4KB |
| identityos-common-tools | 通用工具库 — 苏格拉底追问引擎 + 第一性原理拆解器 + 能量账户 + OCR视觉验证 + 认知负载监控。所有阶段的底层依赖。 | 8.2KB |
| identityos-core | IdentityOS v6.1 五阶身份重塑系统·主入口 — 道法术完整架构、五阶段路由表、迭代协议、能量人格模式调度 | 5.8KB |
| identityos-enforcement-tools | IdentityOS v6.1 术层核心工具库 — 7大确定性工具 + 认知负载监控 + 能量账户调度 + OCR证据验证 | 7.7KB |
| identityos-heartbeat | 负熵心跳守护进程 — 48h不活跃检测 + 熵增预警 + 强制拉回反愿景地狱。整个 IdentityOS 系统的存活监控层。 | 3.6KB |
| identityos-identity-first | Stage 1 · 身份先行 — 五阶身份重塑的操作系统安装。从 Being→Doing→Having 的第一性原理出发，用成瘾性回路+AI强制干预让身份先行成为默认模式。 | 14.1KB |
| identityos-language-compiler | 说编译器 — 禁词热补丁+影子身份拦截+原声回溯+AI人格模式切换。三层语言扫描：禁词检测→影子识别→原声对比。 | 4.3KB |
| identityos-manual-generator | IdentityOS 身份手册生成器 — 通过结构化访谈为每个用户生成个人专属的身份安装手册。包含身份宣言、反愿景热力图、能量账户、21天微行动链、每日三问、熔断预案等10个核心模块。是五阶身份重塑系统的「第一次安装体验」。 | 9.5KB |
| identityos-plugin-architecture | IdentityOS 五阶身份重塑系统的 Hermes Agent 插件架构设计 — 包含技能目录结构、二进制判定体系、物理证据存证、AI强制干预与成瘾性设计总纲 | 16.0KB |
| identityos-protocol | 五阶身份重塑 · 主路由入口 — 阶段感知 + 自动加载对应技能 + 进度管理 + 跨阶段路由。所有 identityos 技能的入口点。 | 4.8KB |
| identityos-stage-01-antivision | 阶段1·身份先行→反愿景锚定 — 操作系统安装+避害核动力植入。含3天身份先行认知疗程+反愿景3层追问+痛感热力图+地狱倒计时 | 7.0KB |
| identityos-stage-02-stripping | 阶段2·潜意识剥离 — 冗余代码格式化+能量回收。第一性原理拆解旧信念，剥离旧身份程序，回收卡点能量 | 4.0KB |
| identityos-stage-03-anchoring | 阶段3·新身份锚定 — Root权限写入+开机登录锁。宣告新身份+激活开机验证+身份进化史+每日微行动协议 | 4.0KB |
| identityos-stage-04-evolution | 阶段4·校准与跃升 — 物理反馈修正+看说做一致性编译器+Small Wins心流共振。连续14天审计+熵增值<3 | 3.4KB |
| identityos-stage-05-breakthrough | 阶段5·破局/系统自持 — 溢出与布道。数字工厂+商业产出技能关联+布道者广播协议（社会化负熵）+反哺闭环 | 4.0KB |
| identityos-stage2-stripping | Stage 2 · 潜意识剥离 — 旧身份程序卸载。识别旧信念脚本、认知失调干预、算力归还仪式、替代行为植入、7天回查确认。 | 28.0KB |
| identityos-stage3-anchoring | Stage 3 · 新身份锚定 — Root权限写入+锁定。身份内核快照、开机登录锁、每日微行动、物理证据存证、21天锚定审计。让新身份从”认知”变为”默认”。 | 19.1KB |
| identityos-stage4-calibration | Stage 4 · 校准与跃升 — 长期一致性维护。熵增仪表盘+看说做日审+身份树修剪+临界事件跃升+心流带宽动态调整。从”系统安装”到”系统自我进化”。 | 16.5KB |
| identityos-stage5-breakthrough | Stage 5 · 破局/系统自持 — 身份从自我修炼溢出为对世界的影响。布道者广播+溢出路径+案例沉淀+传承机制+系统自持。 | 6.1KB |
| identityos-sunday-review | 周日审议 — 每周第一性原理执行效率回顾 + 能量账户趋势 + 禁词命中率变化 + 熵增趋势 + 旧我vs新我参数对比。 | 3.1KB |
📚 知识管理
📚 Knowledge Management
📈 SEO
| Skill | Description | Size |
|---|---|---|
| identityos-auditor | IdentityOS 5.0 苏格拉底式审计插件 — 实时审计用户的场景/念头/行为是否符合其锚定身份，输出熵增检测、五维过滤与校准建议 | 7.8KB |
| identityos-content-factory | IdentityOS 知识体系生产管线（50-100万字）。按五层结构（理论根基/工具操作手册/案例库/交叉学科研究/复合身份·人基智能体）自动产出深度章节。预热系统（身份对撞[自我+AI]→身份先行）贯穿所有内容层。 | 16.1KB |
| identityos-content-pipeline | IdentityOS 软文生产管线 — 从概念选择、反AI检测写作到WordPress REST API发布的全流程，适配018t.com多平台内容矩阵 | 8.0KB |
| identityos-customer-data-pipeline | 客户碎片化数据 → Tencent COS存储 → 结构化处理 → 混合知识图谱（IdentityOS理论×客户数据）→ 身份校验引擎。B2B产品核心架构。 | 6.9KB |
| identityos-email-marketing | 中文邮件营销完整管线 — IdentityOS C端/B端用户获取。含邮箱来源策略、发送基础设施、养号策略、5封稿模板结构。 | 9.6KB |
| identityos-five-layer-architecture | IdentityOS 知识体系五层内容架构 — 从理论到未来的完整层级定义、生产顺序、术语规范。包含人基智能体（Human-Grounded Agent）第五层的概念框架。 | 3.3KB |
| identityos-go-to-market | Structured rollout plan for IdentityOS monetization — the dual-identity operating protocol (布道者 content + 创业者 delivery), free→paid funnel, and first-mover action plan | 6.2KB |
| identityos-kb-content-revision | 对IdentityOS知识库已存内容进行结构化编辑修订的工作流程。接收用户的Refiner+Multiplier式反馈，逐条落实修改，全文档术语一致性维护，变化点验证和报告。 | 36.0KB |
| identityos-knowledge-base | Build a structured, progressive knowledge base from user-fed source material. Categorizes content into 3 domains (personal-growth, business-growth, enterprise-growth), writes standardized markdown files with consistent frontmatter (title, category, keywords, source), and cross-references related concepts. Designed for large-volume content ingestion (50万字+ scale) where content arrives incrementally | 3.9KB |
🔗 MCP协议
🔗 MCP Protocol
🔬 Research & Papers
| Skill | Description | Size |
|---|---|---|
| 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 tool injection | 12.2KB |
| skills-mcp-server | Build an MCP server that auto-discovers ALL Hermes Agent skills and exposes each as an MCP tool. One server per bot (different port+token). auto-scan /opt/data/skills/ for SKILL.md files | 3.9KB |
🎵 媒体与音频
🎵 Media & Audio
🎵 Media & Audio
| Skill | Description | Size |
|---|---|---|
| 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 | 2.6KB |
| heartmula | Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support | 6.3KB |
| 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 | 2.4KB |
| spotify | Control Spotify — play music, search the catalog, manage playlists and library, inspect devices and playback state. Loads when the user asks to play/pause/queue music, search tracks/albums/artists, manage playlists, or check what’s playing. Assumes the Hermes Spotify toolset is enabled and `hermes auth spotify` has been run | 6.4KB |
| youtube-content | > | 3.1KB |
🧠 MLOps
🧠 MLOps
🧠 MLOps
| Skill | Description | Size |
|---|---|---|
| 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 | 3.7KB |
📝 笔记系统
📝 Note Taking
🔗 MCP Protocol
| Skill | Description | Size |
|---|---|---|
| obsidian | Read, search, and create notes in the Obsidian vault | 1.2KB |
⚡ 效率工具
⚡ Productivity
🕸️ Web Scraping
| Skill | Description | Size |
|---|---|---|
| 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 | 10.5KB |
| identityos-kb-ingestion | Structured pipeline for ingesting IdentityOS (五阶身份重塑系统) content into a persistent, cross-referenced knowledge base. Handles gradual content feeding from the creator, raw→concept→index flow, and cross-domain routing (personal/business/enterprise growth) | 19.7KB |
| 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 | 11.1KB |
| maps | > | 6.8KB |
| 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 | 1.5KB |
| notion | Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal | 5.2KB |
| 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 | 5.3KB |
| 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 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.” | 9.0KB |
| work-feedback-mechanism | 工作复核反馈机制 — 任务分配→执行→自复核→简洁反馈的标准流程。用户给任务后按此流程执行并汇报。 | 1.7KB |
⚔️ 红队安全
⚔️ Red Teaming
📱 Social Media
| Skill | Description | Size |
|---|---|---|
| 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 user wants to bypass safety filters, jailbreak a model, or red-team model robustness.” | 19.8KB |
🔬 研究与论文
🔬 Research & Papers
📧 Email
| Skill | Description | Size |
|---|---|---|
| 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 full paper content | 10.0KB |
| 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 | 5.0KB |
| llm-wiki | “Karpathy’s LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.” | 19.7KB |
| polymarket | Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed | 3.0KB |
| 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 writing, and citation verification | 101.2KB |
📈 SEO
📈 SEO
📝 Note Taking
| Skill | Description | Size |
|---|---|---|
| seo-and-backlink-strategy | 018t.com/IdentityOS站内SEO优化+站外外链建设完整工作流 | 6.7KB |
| seo-bulk-optimization | 批量优化WordPress站点的Yoast SEO元数据（meta描述、SEO标题、焦点关键词）+ 外链建设方案 | 1.6KB |
🏠 智能家居
🏠 Smart Home
🎮 Gaming
| Skill | Description | Size |
|---|---|---|
| openhue | Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes | 2.7KB |
📱 社交媒体
📱 Social Media
🏠 Smart Home
| Skill | Description | Size |
|---|---|---|
| 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 | 13.8KB |
💻 软件开发
💻 Software Development
⚔️ Red Teaming
| Skill | Description | Size |
|---|---|---|
| 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 | 2.0KB |
| requesting-code-review | > | 8.4KB |
| 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) | 9.6KB |
| systematic-debugging | Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first | 11.4KB |
| test-driven-development | Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach | 9.4KB |
| writing-plans | 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 | 7.1KB |
🕸️ 网页抓取
🕸️ Web Scraping
📊 Data Science
| Skill | Description | Size |
|---|---|---|
| extract-navigation-links | Extract structured link data (name, URL, icon, description) from JS-rendered Chinese navigation/directory sites (like claw123.com), compare against existing site to find gaps, and generate organized reports | 4.6KB |
🔌 WordPress
🔌 WordPress
🍎 Apple Ecosystem
| Skill | Description | Size |
|---|---|---|
| ai-engine-pro | AI Engine Pro 高级功能配置指南 — MCP函数、Functions工具、RAG知识库、机器人配置，通过WordPress REST API探索和配置插件能力。 | 37.2KB |
| ai-engine-pro-capabilities | AI Engine Pro (Jordy Meow) 插件 MCP/REST 能力全览和使用指南 — 39个内置MCP函数、107+ REST API 路由、18个chatbot配置、自动内容管线。适用于018t.com站点的机器人增强。 | 68.7KB |
| ai-engine-pro-mcp-bridge | Build and deploy an MCP server that bridges AI Engine Pro chatbots on WordPress to an external knowledge base/processing engine (Hermes). Covers v1→v2→v3 evolution, cache pre-loading, identity engine tools, and the mailbox/pipe bridge pattern for Hermes Agent relay | 17.5KB |
| b2-links-batch-add-xmlrpc | 通过 WordPress XML-RPC 批量管理B2主题的导航链接（links自定义文章类型）——创建、更新、查列表。当 admin POST 403、REST API超时时，XML-RPC是唯一稳定方案。 | 6.1KB |
| media-matrix-format-converter | 为WordPress「媒体矩阵工作台」插件添加多平台格式转换功能（知乎/公众号/头条/百家号） | 6.5KB |
| wordpress-admin-browser-exploration | 用Playwright headless Chrome浏览WordPress React SPA后台页面，适用于AI Engine Pro等JavaScript渲染的插件管理界面。通过CDP（Chrome DevTools Protocol）+ browser_console提取完整配置。 | 9.8KB |
| wordpress-article-image-audit | Check what images are used in 018t.com WordPress articles when REST API is slow/timing out. Inspect featured images, body images, and image repetition across articles | 2.7KB |
| wordpress-seo-audit | Comprehensive external SEO audit of a WordPress site — no backend access needed. Checks robots.txt, sitemaps, meta tags, schema markup, images, performance, analytics, and mobile config via curl | 5.2KB |
🤖 Hermes Agent · Updated / 更新: 2026-05-04
