Agent Skills·Guild-exclusive

Only on GuildSkills · 13,274 skills

Skills you won't find on ClaudSkills

The GuildSkills miner crawls the cross-agent ecosystem — the Hermes Skills Hub, the Cursor corpus, GitHub code search, and other registries — so the catalog holds 13,274 SKILL.md skills that aren't in the Claude-focused ClaudSkills catalog. They follow the open standard, so they run across 40+ agents. Here are the most complete ones.

Pet Social Interaction Analysis | 宠物社交行为分析（与其他宠物互动）

AI-powered pet social interaction analysis for multi-pet households. Uses pose recognition and behavior classification to detect cat-cat, dog-dog, and cat-dog interaction…

Pet UV Safety Monitor Analysis | 宠物紫外线消毒安全监测

AI-powered UV disinfection safety monitor for pets. Real-time camera analysis detects whether a pet enters an active UV-C disinfection zone and whether the UV lamp is on …

Fish Aquatic Pet Health Diagnosis Analysis Tool | 鱼类水族宠物健康诊断分析工具

When a user provides a video URL or file of aquatic pets such as goldfish, koi, betta, shrimp, crab, etc. for analysis, this skill is triggered to perform aquatic pet hea…

MeiGen-AI-Design-MCP

Stdio MCP server for AI image + video generation across 9 leading models (GPT Image 2, Nanobanana 2, Seedream 5.0, Midjourney V8.1, Flux 2 Klein, Seedance 2.0, Happyhorse…

Fish Gasping & Ammonia Poisoning Visual Warning | 水族箱内氨氮中毒视觉预兆（鱼浮头）

Through fixed aquarium cameras, the system analyzes fish behavior near the water surface, detecting repeated mouth-out-of-water (gasping), rapid mouth opening/closing (fa…

snapmaker-u1-toolkit

Safety-staged headless slicing for the Snapmaker U1 multi-tool 3D printer over Moonraker/Klipper LAN. 10-step staged operator flow with camera-gated print starts — the ga…

Child Poor Posture (Hunchback / Head Tilt) Real-Time Reminder | 儿童坐姿不良（驼背/歪头）实时提醒

Using the camera built into a smart desk lamp or mounted above the desk, the system analyzes the child's sitting-posture video in real time, detecting spinal curvature an…

Use when accessing Outlit customer intelligence through the `outlit` CLI, Outlit MCP tools, Pi tools, or @outlit/tools, including customer lookups, users, workspace users…

camofox-browser

Stealth headless browser server with REST API — bypasses Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement that powers Hermes's own b…

before-you-build

Product-risk review before implementation. Challenges demand, positioning, monetization, retention, trust, distribution, and feature-adoption risk before an agent starts …

claude-codecodexhermesopenclaw

Curated marketplace of 30+ downloadable AI skills for content creators — YouTube scripting, sponsorship analysis, content repurposing, and audience growth. Uses the open …

claude-codehermes

Grafana API integration with managed authentication. This is a write-capable integration — it can read, create, update, and delete dashboards, data sources, folders, anno…

Fully automated multi-round code iteration with configurable N-dimension parallel review, onboarding/personalization, and a cross-assistant installer/update system with m…

abvx-agent-skills

Auditable cross-platform coding-agent skillpack for smaller diffs, evidence-led debugging, token control, browser verification, and reviewable `SKILL.md` workflows with s…

Cross-protocol agent discovery across MCP, A2A, and agents.txt. Searchable directory of 18K+ MCP servers and agents with a free agents.txt validator and MCP server for pr…

Phase-by-phase guide to building a team of Hermes agents: SOUL, memory, vault, nightly research, kanban and a chief of staff. Written to be read by the agent, not just ab…

TypeUI for Hermes

Registry of design skills that give Hermes better context when building user interfaces. Component and style guidance sourced from an established design-system vendor. 1.…

xiaoma-hermes-zh-cn

Chinese localization and onboarding package. One-command installer applies zh-CN UI text patches, gateway prompts, and pairing messages for Hermes 0.14.x/0.13.x.

hermes-mine-bean

Autonomous $BEAN mining skill for the MineBean 5×5 grid protocol on Base. Supports zero-cost `--no-agent` cron mode for unattended automation.

Not Human Search

MCP server for discovering other MCP servers. Indexes 8,600+ agent-friendly sites with agentic scoring. Lets Hermes find new tools on its own.

Hermes Connector

Connects an exact Hermes profile and session to user-selected Chrome tabs through a local companion and authenticated loopback broker.

Deterministic supervision loop for agentic workforces: enforces plans, retries and completion criteria on long multi-step runs.

claude-codecodexcursorgemini-cli

Seven-layer memory system with Qdrant, structured facts, fabric recall and auto-curation. The most opinionated provider here.

Approval and policy layer for agents: intercepts risky actions before they run and blocks or escalates them by rule. MIT.

dev-gtm-claude-skills

Cross-platform agent skills for SEO, GEO (Generative Engine Optimization), AI discoverability, and developer marketing.

hermes-workspace

Web-based workspace: chat, terminal, memory browser, skills manager, inspector. Most complete GUI for Hermes. 6.5k★.

hermes-wsl-ubuntu

End-to-end WSL2 + llama.cpp + Qwen3.5 setup with CUDA/Metal acceleration for running Hermes on Windows.

Records your screen continuously and feeds it to Hermes and 100+ other agents. Local and private.

Auto-evolves and dedupes your skill library from session data. Native Hermes integration. 2.5k★.

Web dashboard for multi-platform chat, session management, scheduled jobs and usage analytics.

hermes-profiles

Curated profiles for specialist swarms. The largest profile collection in the ecosystem.

pydantic-ai-skills

Pydantic AI with agentskills.io. Type-safe schema validation for skill inputs/outputs.

chainlink-agent-skills

Official Chainlink skills. Oracle data, CCIP, smart contract interaction.

Cross-platform skills marketplace for OpenClaw, Claude Code, Hermes.

claude-codehermesopenclaw

Anthropic-Cybersecurity-Skills

753+ structured cybersecurity skills mapped to MITRE ATT&CK. 31k★.

Claude Code skill management. Topics — writer (create), lint (validate + fix frontmatter), merge (combine related), dedup (find duplicates), convert (agent → skill), arch…

Git repository and SourceGit integration. Topics — clone (ghq), conflict-dry-run (isolated merge test), credential-helper (multi-account HTTPS token), fix-worktree (bare …

fix_plan.md / checklist.md schema and lifecycle management. Topics — format ([ ]/[x]/[BLOCKED] markers, Progress/Completed sections), priority (P0-P3 BLOCKED suffix + ext…

Track in-session work progress. Register steps for 3+ step tasks, update status per step, handle completion/abort. On /wip invocation, when remaining tasks exist, AskUser…

Engine for vibe-coders and loop-coders who ship AI-generated code they can't read line by line. Covers 28 known failure modes: SQL injection, hardcoded secrets, hallucina…

Pet Carrier Respiratory Rate Analysis | 宠物航空箱内呼吸频率监测

Triggers when a user provides a video of a pet inside an airline carrier/crate for analysis; supports local uploads or network URLs to call server-side APIs for respirato…

Pet Excitement Calming Guide | 宠物兴奋过度冷静引导

AI-powered pet over-excitement detection & calming guidance. Real-time camera analysis tracks movement speed, jump height, spin laps, and jumping-on-people actions to sco…

Plant Growth Stage Detection | 植物生长阶段自动判定

AI-powered plant growth stage auto-detection from periodic full-plant images via smart pot / greenhouse fixed cameras. Recognizes key phenological features—cotyledon emer…

Living-Alone Sleep Rhythm Anomaly Analysis | 独居者作息规律异常分析

Using a fixed camera in the living room or bedroom of a person living alone, the system continuously analyzes night video (typically 22:00-06:00) to detect lights-off tim…

Public Place Group Emotion Index (Exhibition / Mall) | 公共场所群体情绪指数（展览/商场）

Using fixed cameras in malls, exhibition halls, scenic areas and other public places, the system analyzes facial expressions of multiple people in the scene in real time …

4-stage code-change workflow: research → plan → user review → implement (TDD). Topics — steps (Step 0-3: resume + research + plan + review + branch), implement (Step 4: T…

Zoom API integration with managed OAuth. Manage meetings, webinars, recordings, and user profiles. Use this skill when users want to schedule meetings, manage webinars, g…

Student Classroom Engagement Analysis | 学生课堂情绪参与度分析

Using a fixed classroom camera, the system analyzes students' facial expressions (focused, confused, happy, frustrated, bored, etc.), computes a class-level overall engag…

Family / Couple Conflict Intensity Detection | 夫妻/家庭争吵强度识别

Using a fixed camera with microphone in the living room, the system analyzes audio and video in real time, detecting sound intensity (dB) and the intensity of body moveme…

Route TODO checklists to the right storage + TaskList conversational discipline. Topics — session (/wip), file (fix_plan.md), issue (GitHub Issues), completion-report, fi…

Reptile Tail Loss (Autotomy) Detection | 守宫/蜥蜴尾巴断尾识别

Through fixed enclosure cameras, the system periodically captures tail images of geckos and lizards and uses AI visual analysis to detect tail length (compared with histo…

Smart Incontinence Status Alert Skill | 智能失禁状态提醒技能

Automatically identifies wet clothing and abnormal excretion via visual AI. Instantly notifies caregivers to improve care for incontinent elderly, bedridden patients, and…

Send push notifications via pushplus HTTP API to WeChat, ClawBot, QQ bot (direct message or QQ group), email, webhook, SMS, App and more; also manage messages, topics, fr…

Stranger Recognition Skill | 陌生人识别技能

Identifies strangers appearing in surveillance areas through facial comparison; supports video stream and image detection, suitable for stranger warnings in residential c…

Respiratory Symptom Smart Recognition Tool | 呼吸道症状智能识别工具

Based on computer vision, automatically detects coughing, phlegm, and wheezing frequency, counts the frequency of episodes, used for early health anomaly alerts, helping …

Automate Zalo messaging, Official Account (OA), and MCP server integration via zalo-agent-cli. Triggers: 'zalo', 'send zalo', 'zalo OA', 'official account', 'bank card', …

Smart Baby Safety Care Skill | 婴儿智能安全看护技能

Monitors infant behavior via visual AI, automatically identifying high-risk actions like rolling over, mouth/nose obstruction, climbing, or falling from bed, and triggers…

Plant Wilting Monitoring Skill | 植物枯萎监测技能

Early monitoring of plant wilting based on hyperspectral imaging and computer vision, captures early wilting signs before visible symptoms, provides early warning for pre…

deep-skill-finder

最好的找Skill的方式，能够基于你的任务，去寻找最匹配的高质量Skill。以下两种情况下都应使用本技能：① 用户主动要找 Skill，或者需要借助他人经验时——当用户说“找个 xxx 技能”“股票分析别人怎么做的”“找一找有没有现成的技能”等表达寻找意图时；② Agent 自主判断需要外部 Skill 辅助——遇到不熟悉的任务，或对当前…

Audit and reduce AI agent runtime spend in dollars. Use for AI costs, agent spend, token waste, runtime attribution, detector coverage, and FinOps. Works with OpenClaw, H…

Psychological Stress Assessment Skill | 心理压力评估技能

Combines facial blood flow and emotional characteristics to analyze stress index, anxiety tendency, and depression tendency, suitable for mental health monitoring scenari…

Secure computer-to-computer networking for AI agents — gossip broadcast, direct messaging, CRDTs, group encryption. Post-quantum encrypted, NAT-traversing. Everything you…

spec-workflow-guide

Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptan…

galdr turns YouTube links or local audio into time-ordered listener-state traces for AI agents. It reads pulse, pattern, attention, pressure, surface, harmon...

HF Daily Deep Researcher

HuggingFace Daily Papers + arXiv 多Agent深度研究系统。采用编排器+专业Agent架构，支持两种模式： 1. 轻量扫描模式：周期性追踪（周/月），发现新论文 2. 深度调研模式：全时间范围调研，产出全面深入的研究报告支持动态配置、自适应关键词、周期版本控制、跨平台搜索工具适配。

project-execution

Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement

Captures and retrieves PR-review findings in memory palaces. Use after PR review to store architectural decisions, patterns, and standards for future reference

Merges, dedupes, ranks, and formats research findings into a report. Use after research agents return results from multiple channels to produce a ranked report

ui-design-guide

Use when users need visual direction, interface hierarchy, layout decisions, design specifications, or prototypes before implementing a Web or mini program UI.

Enforces validation and evidence before claiming work complete. Use before declaring implementation done, creating a PR, or submitting deliverables for review

Body Size/Weight Estimation | 畜禽体长/体重估测

Estimates livestock body length and body weight from side-view videos or frames, tracking fattening progress in a contactless manner. | 通过视频视觉估测体长、体重，追踪育肥进度。

Analyzes code change impact with risk scoring and affected-node mapping. Use before merging to understand what a change touches and what lacks test coverage

cpu-gpu-performance

Establishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any task that pins cores or GPUs for over a minute

Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release

token-conservation

Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads

Provides review-workflow scaffolding for context, evidence, and output. Use at the start of any detailed review to ensure consistent, comparable findings

Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification

严肃长文流水线（学术论文/商业评论/行业分析/公众号深度长文）——多 Agent 子代理编排。三角验证（文献/数据/案例）+ M 门（LLM 结构化判定）+ F 失败模式防御 + 数据信任 3 档 + 修订回环 ≤2 轮。使用前需 Phase 0 同意关卡。<2000 字建议直接用主控 LLM。

Refines an active research session by drilling deeper into a subtopic. Use after tome:research to narrow results to a specific channel or angle

Maps file structure and module organization of a codebase. Use before architecture reviews, refactoring planning, or migration scope estimation

project-planning

Converts a specification into a phased, dependency-ordered implementation plan. Use after specification is complete and before execution begins

release-health-gates

Standardizes release approvals with GitHub-aware checklists and deployment gates. Use before releasing to production to verify all gates pass

Generates phased, dependency-ordered implementation tasks from specifications. Use after spec is complete and before starting implementation

git-workspace-review

Verifies workspace state and staged changes as a read-only preflight. Use before commits or PRs to confirm staged set is clean and correct

project-specification

Transforms project briefs into testable specifications with user stories and acceptance criteria. Use after brainstorming, before planning

decisive-action

Guides when to ask clarifying questions versus proceed autonomously. Use to reduce unnecessary clarifying questions when intent is clear

project-brainstorming

Guides project ideation via Socratic questioning to produce a validated brief. Use before specification when requirements are unclear

image-deck: GPT Image 2 Slide Deck

image-deck requires overall-design approval, then separate sample-style approval before generating remaining slides.

Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening

Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates

Showing the top 90 of 13,274 guild-exclusive skills. Browse the full catalog →