QianYuan.AIAgenticFramework

In the author's own words, from each skill's SKILL.md — showing the first 15 of 117 files.

• agent-browser-automation

  Headless browser automation CLI for AI agents using native Rust binary with Chrome DevTools Protocol

  skills/agent-browser-automation/SKILL.md on GitHub (opens in a new tab)

• api-gateway

  Connect to external services through Maton-managed API routes. Use this skill only after the user names the target app, account, and task. Start with read/list calls when possible and follow the app-specific reference before any change.

  skills/api-gateway/SKILL.md on GitHub (opens in a new tab)

• carrier-product-review

  运营商产品审查，覆盖业务流程合理性、功能领先性、客户与老板视角、UI交互主流设计、反人类设计与易用性、改进建议六大维度。

  skills/carrier-product-review/SKILL.md on GitHub (opens in a new tab)

• charging-pile-experience-analysis

  充电桩经营与充电量经验分析，覆盖充电量同比下降、充电量流失、收益下降的归因拆解、排查路径和运营建议。

  skills/charging-pile-experience-analysis/SKILL.md on GitHub (opens in a new tab)

• git-essentials

  Essential Git commands and workflows for version control, branching, and collaboration.

  skills/git-essentials/SKILL.md on GitHub (opens in a new tab)

• proactive-agent

  Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes memory architecture with pre-compaction flush (so context survives when the window fills), reverse prompting (surfaces ideas you didn't know to ask for), security hardening, self-healing patterns (diagnoses and fixes its own issues), and alignment systems (stays on mission, rem…

  skills/proactive-agent/SKILL.md on GitHub (opens in a new tab)

• self-improving-agent

  A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.

  skills/self-improving-agent/SKILL.md on GitHub (opens in a new tab)

• summarize

  Use the steipete/summarize CLI to summarize URLs, local files, stdin, YouTube links, podcasts, and media with LLM models. Use when installing or running summarize, configuring provider/API keys, tuning length/language/json/extract/slides flags, setting ~/.summarize/config.json defaults, or troubleshooting CLI errors.

  skills/summarize/SKILL.md on GitHub (opens in a new tab)

• weather-query

  查询中国各地实时天气和天气预报，包括温度、湿度、风速、空气质量等信息。Use when users ask about weather conditions, forecasts, or climate information for locations in China.

  skills/weather-query/SKILL.md on GitHub (opens in a new tab)

• brainstorm

  Collaborative discovery and design framing for ambiguous or high-risk work. Use when requirements are unclear, multiple approaches are possible, or you need to turn an idea into a validated design brief before planning or coding.

  .agents/skills/brainstorm/SKILL.md on GitHub (opens in a new tab)

• brainstorming

  Structured ideation before any implementation. Use when starting any non-trivial task.

  .agents/skills/brainstorming/SKILL.md on GitHub (opens in a new tab)

• find-skills

  Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

  .agents/skills/find-skills/SKILL.md on GitHub (opens in a new tab)

• pdf

  Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file o…

  .agents/skills/pdf/SKILL.md on GitHub (opens in a new tab)

• skill-creator

  Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

  .agents/skills/skill-creator/SKILL.md on GitHub (opens in a new tab)

• using-superpowers

  Bootstrap skill — teaches the agent how to find and invoke skills. Use when starting any new task or session.

  .agents/skills/using-superpowers/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• claude-code-best-practiceby shanraisshan from vibe coding to agentic engineering - practice makes claude perfect 68.4k stars · 9 skills
• MemOSby MemTensor Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savin… 12.2k stars · 7 skills
• claude-code-tipsby ykdojo 45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running it… 10.3k stars · 9 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 110k stars · 30 skills
• claude-memby thedotmack Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and inject… 109k stars · 20 skills
• rufloby ruvnet 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems.… 80.5k stars · 30 skills