GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
opc-resource-audit
Inventory all founder resources across 8 categories for a one-person company. Use when Codex needs to systematically confirm what resources the founder has — experience, network, skills, relationships, channels, assets, time/money constraints, hard limits — by first doing a broad scan of each category, then drilling into specifics (distribution, usable portions, how to use, cost of use), and producing a confirmed detailed resource inventory written to `opc-doc/`. Does NOT analyze directions, preferences, suitability, or risk tolerance — those belong to downstream skills.
opc-orchestrator
Orchestrate the full one-person company workflow across all OPC skills. Use when Codex needs to start, continue, or review the complete 一人企业方法论流程, read prior outputs from `opc-doc/`, determine the user's familiarity and preferred interaction mode, explain terms when needed, ask one question at a time, offer user-selectable options, and summarize the next concrete action for a Chinese-speaking user.
opc-niche-positioning
Find and position a viable niche market for a one-person company by combining market mapping and customer segmentation. Use when Codex needs to explain niche concepts when needed, check founder-resource prerequisites, ask one question at a time, generate multiple niche options, and write user-confirmed positioning outputs into `opc-doc/`.
opc-mvp-designer
Define the smallest viable experiment and MVP for a selected one-person company opportunity. Use when Codex needs to explain what MVP means when needed, verify prerequisites, ask one question at a time, present multiple MVP options, and write user-confirmed outputs into `opc-doc/`.
opc-dashboard-review
Review the operating health of a one-person company using lightweight metrics, bottleneck analysis, and stop-loss logic. Use when Codex needs to explain review concepts when needed, verify available outputs, ask one question at a time, present multiple bottleneck hypotheses, and write user-confirmed outputs into `opc-doc/`.
opc-conversion-loop
Design a conversion loop for a one-person company from reach to lead capture to purchase. Use when Codex needs to explain conversion concepts when needed, verify MVP prerequisites, ask one question at a time, present multiple conversion-path options, and write user-confirmed outputs into `opc-doc/`.
opc-business-model-design
Design a viable business model for a one-person company using Lean Canvas and a simplified Business Model Canvas. Use when Codex needs to explain the business-model concepts when needed, verify niche and value-proposition prerequisites, ask one question at a time, present multiple model choices, and write user-confirmed outputs into `opc-doc/`.
opc-asset-ops
Turn repeatable outputs of a one-person company into compounding assets. Use when Codex needs to explain asset-compounding concepts when needed, verify prerequisite outputs, ask one question at a time, present multiple assetization priorities, and write user-confirmed outputs into `opc-doc/`.
send-message
Use when the user asks to send a message to a specific contact in Lark. The agent should open search, locate the contact, enter the chat window, paste the message content, and send with Enter.
schedule-video-meeting
Automatically parse time and participants from natural language to schedule a video conference via UI automation.
docs-editor
Use when the user asks to edit a Feishu Document, insert elements, or modify specific text in a document. The agent should use keyboard shortcuts for precision instead of mouse clicks.
serena-mcp
暂无简介
playwright-mcp
暂无简介
neon-mcp
Use when working with Neon Postgres, Neon Auth, Neon Data API, database schemas, migrations, query tuning, connection strings, branches, slow queries, or SQL execution.
mcp-tooling
Use when choosing between MCP/tools in this project, especially Serena, ai-context PREVC, Context7 docs, Playwright browser automation, Neon database, bash, read/edit/search tools, or workflow setup.
context7-mcp
Use when fetching current external library documentation with Context7, including Next.js, React, Drizzle, Neon SDKs, Tailwind, shadcn, Zustand, or other package APIs.
browser-mcp
Use when validating UI behavior with Playwright MCP, browser automation, screenshots, accessibility snapshots, console logs, network requests, navigation, forms, or visual checks.
ai-context-mcp
Use when working with ai-context MCP, .context scaffolding, PREVC workflow, plans, agent orchestration, semantic context maps, skills, docs, or context sync.