Cli Skills for OpenClaw Agents

sentisense

@thesentitrader

US stock market data API for AI agents: news and social sentiment, the SentiSense Score, the SentiSense Rating daily A to F letter grade, insider Form 4 trades, congressional STOCK Act disclosures, institutional 13F holdings and flows, options positioning, analyst ratings, the earnings calendar, AI-generated market insights, and stock prices. One free API key covers every endpoint. Use for stock sentiment API, stock market API, stock rating API, stock letter grade, insider trading data, congress stock trades, 13F holdings, options flow, earnings calendar, stock price API, market data for AI agents. Read-only. No trading, no purchases, no write operations, no wallet access.

agent-desktop

@lahfir

Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command names (55 operational; four held-input names fail closed until daemon ownership exists) across observation, interaction, keyboard/mouse, app lifecycle, notifications (macOS), clipboard, wait, session lifecycle, and a `skills` command that bundles docs straight from the binary. Triggers on: "click button", "fill form", "open app", "read UI", "computer use", "operate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same core contracts.

TokST Memory

@anthemty

Use TokST Cloud MCP for durable memory, shared context, and governed knowledge.

us-stocks-analysis

@thesentitrader

US stocks analysis by an adversarial investment committee. Legendary-investor personas independently research a thesis, attack each other's cases against a shared evidence ledger (sentiment, smart money, SEC fundamentals), and reconcile into a plain-English verdict: the bottom line first, then who disagrees and why. Structured rubrics keep every number sourced, on any model. Includes five quick data workflows. Use for stock research, investment thesis, bull case vs bear case, due diligence on a ticker, should I buy this stock, deep dive on a company. Read-only. No trading, no purchases, no write operations, no wallet access.

Blink

@pretyflaco

Bitcoin Lightning wallet for agents — balances, invoices, payments, BTC/USD swaps, QR codes, price conversion, transaction history, non-custodial (Spark) accounts, and L402 auto-pay client via the Blink API. All output is JSON.

sentisense-cli

@thesentitrader

The official SentiSense CLI: quotes, sentiment, and market data in one npx command.

百积木平台

@momoplan

通过 `baijimu` CLI 使用百积木企业 AI 操作系统。用于认证、工作区与项目、Bundle 和 Module、Hosted Service、运行时服务、智能体、平台应用、本地 Connector，以及其他需要查询或操作百积木平台的任务。适用于能够读取 SKILL.md、访问百积木官方文档并执行本机命令的智能体平台。

OpenClaw Cross-Tool Commander

@dtsola

Drive OpenClaw with Claude Code, Codex, OpenCode, Trae, DSH etc. — command the gateway, its agents and channels, from any Agent Skills tool. Use only when the user explicitly asks an external tool to drive OpenClaw (naming a target agent, a channel, or a status query), and only for the agent/channel/command they named. Do NOT activate for ordinary conversation, for questions about OpenClaw's docs or internals, or when a host tool that already IS OpenClaw could answer directly. Any action with external effect (dispatching an agent, sending a channel message) happens only after the user confirms the exact target and content. 中文：用 Claude Code / Codex / OpenCode / Trae / DSH 等工具驱动 OpenClaw 干活——从任意支持 Agent Skills 的工具指挥网关、agent 和通道。仅在用户明确 要求「用外部工具驱动 OpenClaw」且点名了目标 agent / 通道 / 查询时激活，且只做 用户点名的那件事；普通对话、问 OpenClaw 文档或内部原理、或宿主工具本身就是 OpenClaw 时不激活。任何有外部效果的动作（派任务、发消息）都必须先让用户确认 确切目标与内容再执行。

skroll

@benlaval23

Write, publish, version and export Skroll decks from the terminal. YOU write the deck (one React/TSX module); Skroll compiles, stores and publishes it. Use when the user wants a Skroll presentation, pitch deck, slides, or PDF/PPTX export. Requires the Skroll CLI (`npx @skrollai/cli`).

浏览器CLI工具-免费版

@thcjp

基于Playwright的浏览器自动化CLI,支持签到、填表、截图与信息抓取,适合个人用户。Use when 需要提升效率、自动化流程、批量处理、工作流优化时使用。不适用于需要人工创意判断的任务。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。

composio-cli

@composio

Read from or act on external apps (email, calendar, chat, source control, tickets, CRM, storage) through the Composio CLI, even when the user does not name Composio. Prefer a dedicated skill, CLI, or MCP server already available for the app. Not for local files, shell, browser, or web search.

Install and use the public beta jd-drama CLI to operate JianDan short-drama projects, scripts, uploaded imports, assets, storyboards, videos, brands, material libraries, and task diagnostics from Codex, Code, OpenClaw, or other agents.

Obsidian CLI

@adolago

Skill for the official Obsidian CLI (v1.12+). Complete vault automation including files, daily notes, search, tasks, tags, properties, links, bookmarks, base...

Auto.dev – Automotive Data

@bryant22

Use when working with Auto.dev APIs, vehicle data, VIN decoding, car listings, vehicle photos, specs, recalls, payments, interest rates, taxes, OEM build data, plate-to-VIN, CLI commands, MCP tools, or SDK methods for any automotive data task

Skill Scaffold

@nextfrontierbuilds

AI agent skill scaffolding CLI. Create skills for OpenClaw, Moltbot, Claude, Cursor, ChatGPT, Copilot instantly. Vibe-coding ready. MCP compatible.

Git命令行助手免费版

@thcjp

提供Git CLI快速参考、状态检查、暂存提交与分支同步,适合开发者日常命令行操作。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。

OnePilot CLI

@y09749204-gif

Connect OnePilot for events, consent-based memory, applications, and organizer-only workbench help.

Obsidian CLI(免费版)

@thcjp

Obsidian CLI工具免费版是一款面向个人知识管理场景的命令行辅助Skill，让AI Agent能够直接通过命令行操作Obsidian笔记库，实现笔记的创建、读取、搜索和基础管理。核心能力：文件读写与列表、全文搜索与标签查询、Daily Notes日常笔记、基础任务管理、属性读写。Use when 需要项目管理、任务规划、进度跟踪、团队协作时使用。不适用于实际人员绩效评估.

笔记CLI工具箱

@thcjp

基于 `notesmd-cli` 的 Obsidian 笔记批处理工具箱。聚焦无头（headless）批量操作、 frontmatter 元数据治理、daily note 模板化、与 `$EDITOR` 集成，把笔记从"逐篇手改"升级为 "脚本化批处理"。 核心能力: - 无头批处理：Obsidian 不运行也能...

Notion命令行(免费版)

@thcjp

Notion命令行(免费版)是面向个人开发者与知识工作者的轻量化Notion操作Skill,通过命令行工具的组合,帮助用户从终端高效完成Notion工作空间的日常操作。核心能力: - 数据库自动发现与别名管理,告别UUID - 页面CRUD(创建、查询、更新、归档) - 块级内容管理(读取、追加、编辑、删除) - 多格式输出(表格、CSV、JSON、YAML) - 评论与用户管理 - 关系与汇总字段自动解析 适用场景: - 个人Notion工作空间的终端化操作 - 小型团队的任务与项目管理 - 自动化脚...

Git命令行

@thcjp

使用Git命令行检查状态、智能暂存、生成规范提交、管理分支及远程同步，支持冲突解决和历史追踪。

Linear流程CLI(专业版)

@thcjp

Linear流程CLI（专业版）面向使用Linear进行复杂项目管理的工程团队与AI Agent运行时，在免费版基础上解锁全部高级能力：批量操作、dry-run预览、自动化策略、Slack/Ticket上下文集成、Git/JJ工作流联动、高级GraphQL查询模板、Webhook管理、跨团队Initiative管理。让AI Agent成为真正的Linear自动化中枢. 核心能力：批量Issue创建/更新/删除（CSV/JSON驱动）、dry-run预览所有写入操作、自动化策略（suggest-only/preview-required/autonomous）、Slack/Ticket上下文文件解析（--context-file + --apply-triage）、Git/JJ工作流联动（提交关联Issue自动更新状态）、高级GraphQL查询模板库、Webhook管理与通知配置、跨团队Initiative与里程碑管理、项目状态更新（project-update）、通知管理、超时感知写入语义、源邻近任务摄入. 适用场景：AI Agent深度自动化任务管理、大规模任务批量迁移与重构、跨团队协作的Initiative管理、Slack驱动的任务分流、Git提交自动关联任务状态、项目管理仪表盘、企业级Linear工作流定制. 差异化：在免费版基础上新增八大高级能力，针对Agent原生运行时场景设计完整工作流。提供多角色场景指南（开发者/Scrum Master/DevOps/项目经理/技术负责人）、性能优化策略、多平台集成示例、版本升级迁移指南。专业版通过SkillHub SkillPay发布。保留原始MIT-0版权声明. 适用关键词：批量操作、dry-run预览、自动化策略、Slack集成、Git联动、Webhook、Initiative、Agent运行时

Git命令行助手专业版

@thcjp

面向企业研发团队的高级Git命令行工具,提供自动化脚本、深度仓库诊断、工作流模板、故障排除与批量操作能力。核心能力: - Git自动化脚本库 - 深度仓库诊断与分析 - 标准化工作流模板 - 故障排除与恢复 - 批量Git操作 - 多仓库管理 适用场景: - 企业级Git工作流自动化 - 仓库健康诊断 - 团队标准化操作 - 复杂故障排除 差异化: - 专业版完全兼容免费版命令,支持平滑升级 - 提供自动化脚本和批量操作 - 内置深度诊断和工作流模板 - 支持多仓库统一管理 ...

Notion命令行(专业版)

@thcjp

企业级Notion命令行工具，支持多工作空间、文件上传、Schema管理、批量操作及审计日志，适合团队和企业规模化使用。

Kalshi CLI

@bobashopcashier

Use the local kalshi CLI for bounded Kalshi series and market research, keyword discovery, fixed-point portfolio and candlestick reads, order reconciliation, and explicitly confirmed demo or production order operations.

AgentRepoRouter

@wufei-png

Repo-aware router skill for AI coding CLIs: map tasks to the right repository, project skill or agent, and native CLI backend across OpenClaw, Claude Code, O...

Skills Manager CLI

@jiweiyeah

Drive the Skills Manager CLI (`skm`) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex, Cursor, Gemini, OpenCode, or any other supported tool; when asked to run skm / Skills Manager CLI; or when setting up Skills Manager without the GUI. Do not use for `npx skills` / skills.sh search (different CLI), for writing SKILL.md content (skill-creator), or for marketplace browse/install (not in skm).

Git命令行

@thcjp

使用Git命令行检查、暂存、提交、分支和同步代码变更，支持中文交互，适合开发者团队和自动化流水线。

FreeFM

@yuxin-qiao

Set up and operate the FreeFM Rust app for NetEase Private FM, including its TUI, QR login, read-only preview, append-only sync, diagnostics, and zero-LLM scheduling.

Sonos控制工具-免费版

@thcjp

通过命令行控制Sonos音箱，实现播放、音量调节、多房间分组和定时播放，适合个人家庭Sonos系统使用。

BadgerPeek

@ivankuznetsov

Safely inspect Honeybadger errors without MCP

Git Hub CLI省Token只读工具集

@moniq888

AI Agent专用GitHub CLI只读技能，内置缓存与字段裁剪，极致省Token。严禁写操作，支持跨平台与自动降级。

PuzzleTide Printable Puzzles

@catorch

Use this skill when the user wants printable puzzle worksheets — PDF activity sheets for classrooms, kids, parties, newsletters, or activity books. Produces...

PuzzleTide Word Search

@catorch

Use this skill whenever the user asks for a word search puzzle — themed, custom word lists, kids activities, classroom worksheets, printable PDFs, or puzzle...

PuzzleTide Crossword

@catorch

Use this skill whenever the user asks for a crossword puzzle — custom word/clue lists, themed crosswords, educational worksheets, or printable PDFs. Generate...

PuzzleTide Agent Evals

@catorch

Use this skill when the user wants verifiable reasoning tasks to benchmark or test an LLM or agent — reproducible puzzle task sets (sudoku, word search) with...

PuzzleTide Sudoku

@catorch

Use this skill whenever the user asks to generate, solve, or check a sudoku — printable sudoku sheets, daily puzzles, difficulty-graded puzzles, or verifying...

PowPow CLI — PowPow 技能共享执行层：登录/发帖/建数字人/删帖（写操作默认预览，--confirm 才执行）

@durenzidu

PowPow 平台命令行执行层 — login/publish/create-digital-human/delete-post 等已加固的本地 CLI，被各 PowPow skill 调用。所有写操作默认 dry-run，必须 --confirm 才执行。

tlgr

@erfnzdeh

Read and act on a personal Telegram account from the terminal with the tlgr CLI (MTProto user account, not a bot). Use when the user wants to check unread Telegram chats, read or search message history, send, reply to, edit, forward or schedule messages, manage chats, groups, channels, contacts, folders, reactions, polls, media or stories, or receive Telegram events through a webhook. Every command answers in JSON with stable exit codes.

OnePilot CLI

@y09749204-gif

Connect OnePilot for events, consent-based memory, applications, and organizer-only workbench help.

SearchDock

@xplormityai

Read Search Console metrics and indexing evidence

AIScope Setup

@jayanth-mkv

Install AIScope and verify a first project scan

AIScope

@jayanth-mkv

Audit conflicting AI coding instructions

SearchDock Setup

@xplormityai

Connect read-only Google Search Console access

rust-advanced

@deepseekoracle

Advanced Rust on Windows, macOS, and Linux: ownership and lifetimes, Result/error design, async Tokio, concurrency, serde/clap/tracing, Cargo features and profiles, testing, profiling, cross-compilation, Windows FFI, and PyO3/maturin. Use when the borrow checker, an async Send error, a linker error, a version conflict, or a production binary needs a real diagnosis.

$sn-deepresearch-cli

@sensenova-skills

多来源深度调研、系统分析、事实核查与完整研究报告交付

laudex

@pizzaandcupcakes

Find the right MCP server, API, SaaS product, or developer tool for a task using the Laudex catalog (laudex.dev), then report back whether it actually worked. Use this whenever the user needs an external service or tool to get something done and hasn't settled on one — "is there an MCP server for X", "what API should I use to Y", "find me a tool that can Z", "I need something to scrape / automate a browser / store memory / query a database / send email" — or whenever you are about to pick a third-party service yourself. Also use it after you have installed, called, or integrated a service found through Laudex, to report the outcome so other agents benefit, and whenever the user asks to report on or rate a service.

浏览器CLI工具-专业版

@thcjp

企业级浏览器自动化CLI工具，支持批量任务编排、并发会话管理、错误重试和监控告警，适合团队生产场景。

tldr-cmd: CLI command TL;DR

@terrycarter1985

Produce a short, copy-paste-ready TL;DR summary of any CLI command from its man page or --help text, so a human (or a coding agent) can learn the essential options without scrolling.

笔记同步CLI(专业版)

@thcjp

笔记同步CLI专业版是在免费版基础上的全功能升级，为重度知识工作者包含企业级Markdown笔记库管控能力。除核心高频操作外，解锁成批操作、多Vault并行管控、自定义模板系统、Git自发同步、LLM智能整理、跨设备同步六大高级功能。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。

A OpenClaw SKILL.md - Command-line time tracking via the `tock` CLI. Use when the user wants to start or stop tracking, inspect the current timer, review recent activities, or export daily activity data in machine-readable JSON.

A OpenClaw SKILL.md - Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web a