技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: agpl

英文目录

AI agent skill for generating browser-editable presentations with multiple visual themes and export to HTML, PDF, and PPTX.

5.2K
Stars
85/100
信任
分类: presentation审计

An AI agent skill that generates editable web-based PPT presentations with 12 themes, 1020 layouts, and one-click PPTX export.

3.8K
Stars
85/100
信任
分类: productivity审计
Arc71

High-performance analytical database. 19.9M records/sec ingestion, 8.4M+ rows/sec queries. Ingestion, compaction, SQL, retention, continuous queries — one binary. Open Parquet on your storage. S3/Azure native. Air-gap ready. No vendor lock-in. AGPL-3.0.

609
Stars
71/100
信任
分类: devops审计

Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.

405
Stars
66/100
信任
分类: agent-frameworks审计

Open-source construction ERP - BOQ, PDF/CAD/BIM takeoff, AI cost matching. 42 regional catalogues, 21 languages, 71 modules. AGPL-3.0. v3.0 - pip install openconstructionerp

378
Stars
66/100
信任
分类: document-processing审计

Agent skill for creating HyperFrames motion videos from articles, products, websites, and README files.

113
Stars
71/100
信任
分类: media审计

AI agent skill for generating editable PPTX presentations with web-based editing and export.

18
Stars
66/100
信任
分类: presentation审计

eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.

246
Stars
64/100
信任
分类: devops审计

🚀 100% local RAG system with one-command setup. Your data never leaves your server. AGPL-3.0

57
Stars
61/100
信任
分类: document-processing审计

Pick an AI slide-deck skill and a concrete visual style from a curated registry, filtering on the requirements that decide it — editable in PowerPoint, speaker notes, a mandated corporate template, offline, PDF — with sample imagery and the style ids each project actually uses. Use when the user wants to make a presentation, deck or slides and has not already chosen a tool; asks which slide skill to use or what the difference between them is; wants to know what a style looks like before committing; or names a style id such as soft-editorial or swiss-grid. This skill routes to the skill that makes the deck — it does not make decks itself.

31
Stars
63/100
信任
分类: research审计

Post-interview review — reconstructs the Q&A from transcript or memory, captures interviewer intel and next-round forecasts, and turns the round into a revision list for the script. Use when the user says they just finished an interview, 刚面完 / 复盘一下 / 面试录音转文字给你 / 这轮被问了什么, or pastes an interview transcript or recollection. Do NOT use for practice sessions (mock-interview) or pre-interview research (job-intel).

11
Stars
65/100
信任
分类: research审计

Runs a realistic mock interview in chat — builds an interviewer persona from the intel file, asks one question at a time with pressure follow-up chains, then scores the candidate on structured delivery, evidence density, role fit, follow-up resilience and recitation-smell, writing a report to the workspace. Use when the user wants practice, says 模拟面试 / 陪我练一下 / 当一回面试官 / 压力面 / mock interview, or when an interview is within 48 hours and the script is ready. Do NOT use for writing answers (interview-script) or reviewing a real past interview (debrief).

11
Stars
64/100
信任
分类: research审计