GitHub
Skills harvested from GitHub repositories
14810 skills availablebrowser_visible-en
browseruse.start has only two launch modes: Default: managed CDP privatemode=true: Playwright-managed Parameter meanings...
QA_source_index-zh
回答 安装、配置、行为原理 类问题时，先 按关键词归类，再按下表 打开 1～2 个最可能命中的路径 阅读，避免长时间无目的遍历。 从用户问题中提取主题（对照下表左列或同类词）。 解析 $QWENPAWROOT：以 which qwenpaw...
guidance-en
Use this skill when the user asks about QwenPaw installation, initialization, environment configuration, dependency requ...
channel_message-zh
通常只有在用户明确要求向某个 channel / 会话发送消息，或你需要主动推送通知（如任务完成、提醒、告警）时，使用本 skill。 这是单向发送，不会返回回复。 用户明确要求发往某个 channel / 会话 任务完成后主动通知用户 定...
browser_cdp-zh
当前 browseruse 默认就是以 managed CDP 方式启动并接管本地 Chrome/Chromium，但这不等于每次都应该把 CDP 端口暴露给用户或其他工具。 本 skill 关注的是更“显式”的 CDP 用法： 扫描本地 ...
file_reader-zh
当用户要求读取或总结本地文本文件时使用此技能。PDF、Office 文档、图片、音频和视频不在此技能范围内，应由其专用技能/工具处理。 读取前先进行类型探测: file -b --mime-type "/path/to/file" 如果文件...
QA_source_index-en
When answering questions about installation, configuration, or behavioral principles, first classify by keyword, then op...
dingtalk_channel-en
This skill automates the creation of a DingTalk application and the binding of a QwenPaw channel using a headed browser....
sync-docs
Unified skill for syncing documentation with code state. Combines discovery, analysis, and CHANGELOG update into a singl...
repo-intel
Unified static analysis - git history intelligence, AST symbol mapping, and project metadata via agent-analyzer. const a...
perf-theory-tester
Test hypotheses using controlled experiments. Follow docs/perf-requirements.md as the canonical contract. Confirm baseli...
perf-theory-gatherer
Generate performance hypotheses for a specific scenario. Follow docs/perf-requirements.md as the canonical contract. Rev...
perf-investigation-logger
Append structured investigation notes to {state-dir}/perf/investigations/<id>.md. Follow docs/perf-requirements.md as th...
perf-benchmarker
Run sequential benchmarks with strict duration rules. Follow docs/perf-requirements.md as the canonical contract. const ...
perf-code-paths
Identify likely implementation paths for a performance scenario. Follow docs/perf-requirements.md as the canonical contr...
perf-baseline-manager
Manage baseline storage and comparison. Follow docs/perf-requirements.md as the canonical contract. One baseline JSON pe...
learn
Research any topic by gathering online resources and creating a comprehensive learning guide with RAG-optimized indexes....
perf-analyzer
Synthesize performance investigation results into clear recommendations. Follow docs/perf-requirements.md as the canonic...
enhance-skills
Analyze skill definitions for trigger quality, structure, and discoverability. Discover - Find all SKILL.md files Parse ...
enhance-plugins
Analyze plugin structures, MCP tools, and security patterns against best practices. const args = '$ARGUMENTS'.split(' ')...
enhance-hooks
Analyze hook definitions and scripts for safety, correctness, and best practices. const args = '$ARGUMENTS'.split(' ').f...
enhance-orchestrator
Coordinate all enhancement analyzers in parallel and produce a unified report. MUST run enhancers in parallel - Use Prom...
enhance-docs
Analyze documentation for readability, structure, and RAG optimization. const args = '$ARGUMENTS'.split(' ').filter(Bool...
enhance-claude-memory
Analyze project memory files (CLAUDE.md, AGENTS.md) for optimization. Searches for project memory files in order: CLAUDE...