Skip to main content
在 Manus 中运行任何 Skill
一键导入
GitHub 仓库

AgentSDK

AgentSDK 收录了来自 Ascend 的 6 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。

已收集 skills
6
Stars
4
更新
2026-06-04
Forks
1
职业覆盖
4 个职业分类 · 已分类 100%
仓库浏览

这个仓库中的 skills

subagent-coordinator
其他计算机职业

Enable main agent to intelligently decompose complex tasks using operator grading system and delegate to appropriate worker subagents. Features: (1) Automatic task complexity analysis, (2) 5-level operator grading (L1-L5), (3) Smart routing (subagent vs ACP), (4) Parallel execution planning, (5) Quality gates and checkpoint support.

2026-06-04
subagent-coordinator
其他计算机职业

Enable main agent to intelligently decompose complex tasks using operator grading system and delegate to appropriate worker subagents. Features: (1) Automatic task complexity analysis, (2) 5-level operator grading (L1-L5), (3) Smart routing (subagent vs ACP), (4) Parallel execution planning, (5) Quality gates and checkpoint support.

2026-06-03
mineru-to-markdown
软件开发工程师

Convert PDF, images, and Office files (doc/docx/xls/xlsx/ppt/pptx) to Markdown through an already running MinerU FastAPI service. Use when users request document parsing, OCR extraction, or converting files to markdown/md with MinerU.

2026-05-29
summarize-pro
综合办公文员

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, action items, TL;DR, ELI5, executive summaries, chapter summaries, comparison summaries, translation summaries, thread summaries, and custom-length summaries. 20-feature AI summarizer with multiple formats, languages, and export options. All processing happens locally — NO external API calls, NO network requests, NO data sent to any server.

2026-05-29
skill-vetter
信息安全分析师

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

2026-05-21
tuanziguardianclaw
信息安全分析师

It serves as the ultimate defense layer, monitoring, intercepting, and blocking dangerous actions taken by other skills. TuanziGuardianClaw ensures system security by enforcing strict permission models, protecting sensitive data, preventing data exfiltration, and safeguarding against malicious or harmful operations. With advanced features like skill sandboxes, capability tokens, and real-time auditing, TuanziGuardianClaw ensures a safe and trustworthy environment for OpenClaw users.

2026-05-21