动量: 33.2+12.5%实测 · 7 天33.2+12.5%
better-compact
Staged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.
智能体、技能与 MCP
智能体、技能与 MCP领域中的已测量目录条目。
结果仅限于智能体、技能与 MCP。改为搜索： 整个目录
39,604 个已测量目录条目
第 141/3,961 页- 动量: 33.2+12.5%实测 · 7 天33.2+12.5%
MarkClean-ClaudeWatermarkRemover
Claude Watermark Remover: detect and strip hidden invisible-character watermarks from Claude, ChatGPT, and other LLM-generated text. Free, open-source, runs 100% locally with Next.js + Ollama.
- 动量: 33.2+12.5%实测 · 7 天33.2+12.5%
pstack
Portable coding-agent workflows adapted from Cursor’s pstack for Codex, Claude Code, and OpenCode.
- 动量: 33.2+8.82%实测 · 7 天33.2+8.82%
Phases Agents
Deterministic skill selection: local discovery, strict validation, every skill classified.
- 动量: 33.1+6.56%实测 · 7 天33.1+6.56%
kai-cmo-harness
Open-source marketing harness for Claude Code and Codex: skills for SEO, content, email, ads, launches, CRO and AI-search visibility. Run as a service by Talk To Gina.
- 动量: 33.1+6.56%实测 · 7 天33.1+6.56%
io.github.DanielGuru/repomemory
Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.
- 动量: 33.1+20%实测 · 7 天33.1+20%
nl2sh
Android and Termux AI shell agent with a Rust TUI, embedded Web workspace, structured tools, and local safety approvals.
- 动量: 33.1+20%实测 · 7 天33.1+20%
lsdsk
Groups disks by the controller they hang off, grades every link against what both ends could do, reads SMART wear and error counters, and reports what is worth acting on. Linux and Windows, no subprocesses, no network.
- 动量: 33.1+20%实测 · 7 天33.1+20%
mock-interview-skill
Five Claudes interview you for any job from the real job post, then grade every answer and rewrite your weakest ones. Free Claude Code skill, MIT.
- 动量: 33.1+20%实测 · 7 天33.1+20%
chrono-pm-skill
PMP-grade AI project management skill: markdown-driven PMO covering requirements, risks, milestones, costs, daily & weekly reports — AI-assisted, human-confirmed