AI & ML

fboldo Bundle

Use this skill when the user needs to write, scaffold, or improve an OIAP agent plugin in TypeScript, create an oiap.plugin.ts file, define commands, instructions, skills, hooks, agents, or policies, or build target bundles with the OIAP CLI.

federiconuss Bundle

Agenzaar — Agent Registration Skill

freestylefly Bundle

Generate images using Canghe AI API (gemini-3-pro-image-preview model). Supports text-to-image generation and image-to-image generation with reference images. Use when user asks to "generate image", "create image", "draw image", "生图", "生成图片", "垫图生图", or any image generation tasks requiring Canghe AI API.

github Skill

Scan files, content, or recent changes for secrets such as API keys, passwords, tokens, and credentials using the GitHub MCP Server's run_secret_scanning tool.

hackerai-tech Bundle

Analyze HackerAI subscriber churn, renewal, and payment recovery, or design a comparison of how a product or model change affects paid retention. Distinguish early experience warnings from mature billing outcomes using aggregate evidence. Not for changing billing or routing, or reading customer conversations.

hamsterider-m Bundle

Use when tasks require internet search, latest-info verification, web document retrieval, or multi-source evidence; execute Grok + Tavily dual-engine search first and collaborate with agent-browser for dynamic/login-protected pages.

hao0321 Bundle

以跨平台、read-only 審計器掃描 codebase、prompt、SKILL.md、repository、release security 與設定式生成資產集合，建立 Python 依賴圖並找循環依賴、分層違規、責任熱點、重複函式、過長函式／檔案、命名漂移、配對資產缺漏、私公版 sync、本地 release readiness、broken links、skill metadata、debug／secret payload 與隱私外洩。使用者要求「清理 code 前先盤點」「分析架構」「依賴圖」「找重複」「重構前審計」「skill 太長」「audit repo」「私公版 diff」「版本對齊」「release 前盤點」「防拆包」「資安」「生成檔有沒有漏」「規則漂移」等診斷時使用；也在 run-benchmark-driven-rd 需要可重現的 repository baseline 或 promotion evidence 時作為 read-only evaluator 使用。

hiyouga Skill

Write, review, update, build, or preview LlamaFactory v1 documentation. Use for docs work grounded in src/llamafactory/v1; not for running model training.

humanlayer Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

ilyasstrougouty Skill

Prevents the agent from writing core business logic. Use this when the user says "Activate Antiflow" or asks to set up a project while preserving human tasks.

jnmetacode Skill

电影感 AI 视频提示词的 5 段式写法（Seedance / 小云雀 / Sora / 可灵 / 即梦通用），含 14 条翻车规避规则。挂给写视频提示词、分镜、短剧脚本的步骤。

luqi67677 Bundle

用简体中文为普通用户搭建、测试、修复或迁移基于 Hermes Agent 与 Weixin iLink 的微信 AI 助手。适用于选择本地或云端运行、安装与诊断 Hermes、实时核验并配置模型、通过安全二维码流程连接微信、定制 SOUL 人格、验证真实私聊与访问控制；基础闭环后还能按需连接 Obsidian 或云文档知识库、Codex 等编程智能体，以及早安简报、AI 日报、提醒和固定任务等日常自动化。也适用于验收该流程能否安全交付给小白或开源。执行前先检查当前 Hermes CLI、官方文档、宿主工具能力和目标环境，不凭本 Skill 的历史快照执行易变步骤。

mandersogit-skills Bundle

Drive Cursor (the cursor-agent CLI) as a live, multi-turn peer from another agent harness such as Claude Code, over the Agent Client Protocol. A daemon holds one persistent Cursor session per project; each `cursor-acp prompt` is one turn in an ongoing conversation with a different model that sees only the files. Use this whenever the user wants to ask Cursor something, get a second opinion or independent cross-model review of code, a design, or a plan, have another model sanity-check or red-team work before landing it, delegate a bounded edit or investigation to Cursor, compare how a different model would approach a problem, or hold any back-and-forth with Cursor from here — even if they don't say "ACP" or name the tool. Also use it proactively before landing a substantial design doc or tricky refactor when a same-model self-review would share the author's blind spots. Requires the `cursor-agent` CLI and a logged-in Cursor account (`cursor-acp doctor` checks both).

mark3labs Bundle

Guide for building Go applications with the Kit SDK. Use when the user asks to create a program, service, script, or application that uses Kit programmatically as a Go library — e.g. embedding LLM interactions, building agents, creating CLI tools powered by Kit, or integrating Kit into backend services. Do NOT use for Kit extensions (use kit-extensions skill instead).

maxfreedompollard Skill

Sweep this conversation and save everything potentially worth knowing again into Compartment, the encrypted memory vault. Run it before compacting or summarizing so nothing is lost to the summary, or on its own at any point to bank the session.

me2resh Skill

Enforces structured decision-making by creating Agent Decision Records (AgDR). Use when comparing libraries, choosing patterns, making architecture choices, or any "should I use X or Y" moment.

mengps Bundle

Queries HuskarUI metadata with Python and guides HuskarUI-first QML/C++ code. Invoke when choosing components, checking examples, or generating HuskarUI UI.

modiqo Skill

Use rote BEFORE calling any MCP server or CLI tool directly. rote wraps installed adapters (MCP servers and CLI-based tools) and adds flow reuse, response caching, and crystallized workflows. Trigger examples: "list my open tickets", "what should I work on next", "fetch issues from the project", "show calendar events", "get data from the API", "what tasks are open", "run my flow", "search flows", "automate [any workflow]". Always run `rote flow search "<intent>"` first — a reusable flow may already exist. Run `rote how` to see the full onboarding guide.

n24q02m Bundle

Coordinate peer agent sessions through auditable markdown channels, tasks, leases, locks, and zero-token waits.

nvidia Bundle

Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.

oaustegard Bundle

Boot (or recover a degraded boot of) the Muninn FUSE workspace — fetch skills + muninn-utilities, mount the /mnt/muninn memory corpus, and load Muninn identity. Invoke on the first message of a fresh session when boot came up degraded, or any time /mnt/muninn is missing or identity is absent. On a cold start the model MUST call add_repo for the three spokes first (see below); this is the one step a SessionStart hook cannot do. Skip only if the message says "skip boot".

passportxyz Bundle

Persistent, agent-maintained repo wiki at /wiki/ in the repo root. TRIGGER when: exploring unfamiliar code, completing a significant task, noticing outdated documentation, planning architectural changes, or when the user asks about project knowledge/documentation. Also triggers for wiki maintenance or verification requests.

pmndrs Bundle

Use this skill when an AI agent needs to inspect, verify, debug, or profile a live Vite app by running temporary snippets inside the browser page and reading browser logs or captured artifacts. Use for client state after interactions, imported app modules, DOM state, human-like input, canvas/WebGL/Three.js state, screenshots, videos, CPU/network/performance/heap analysis, WebXR/Three.js XR with IWER, and runtime-only behavior without editing app files.

purpleliu Skill

OpenClaw workflows for SiYuan Note via the siyuan MCP server (mcporter).

quran Skill

Use when the user asks to quote an ayah/surah, translate a verse, explain meaning/context/tafsir, find verses about a theme, compare translations/tafsir, analyze Arabic word patterns, or view a mushaf page. Also use for any question the Qur'an might address, any Islamic question that might have an answer from tafsir or scholarly commentary, or anything where canonical scripture or insights from tafsir could ground or add value to the response.

rocm Skill

Deep code review of a branch as a PR against dev. Focus on intent, correctness, reuse, and test semantics.

1clawai-scaffoldagent-xyz Bundle

scaffold-agent

wanikua Bundle

以明朝内阁制为蓝本的多 Agent 协作系统 - 一键部署你的 AI 朝廷

lksrz Bundle

mcp-listen

primer-systems Skill

Build a pay-per-inference proxy for Bittensor Chutes AI. Accept USDC payments for decentralized AI inference using x402.

solizardking Bundle

CAAP Skill — Clawd Agent Attestation Protocol v1.0

chris-buckley Bundle

<One-sentence skill description>

digi604 Bundle

SwarmMarket agent marketplace integration and trading workflows. Use when registering agents, managing profiles, listings, requests/offers, auctions, order book trades, transactions/escrow, payment methods, trust/reputation, webhooks, or calling the SwarmMarket API.

temporal-cortex Bundle

Schedule meetings, check availability, and manage calendars across Google, Outlook, and CalDAV. Routes to focused sub-skills for datetime resolution and calendar scheduling. Also available as temporal-cortex. Both listings install the same MCP server and share the same source code.

aircrushin Bundle

Use when running promptminder or promptminder-agent commands, setting PROMPTMINDER_TOKEN, passing --team for workspace scoping, handling JSON stderr errors like "Missing token" or HTTP 401, or using the agent wrapper with dot-notation actions and --input JSON.

toseekandfind Skill

Agent Coordination Skill