Zeng Shiqiang

maddness/agent-research-radar

Радар фундаментальных публикаций про автономных AI-агентов в блогах AI-лабораторий и продуктовых команд (Anthropic, Claude, OpenAI, Cursor, LangChain, Amp, Cognition). Собирает ленты и HTML-индексы за окно дат, отсеивает продуктовые анонсы и релизы моделей, оставляет глубокие посты про архитектуру агентов: память и контекст, long-running циклы, self-improvement, оркестрация, экономика прогона, эвалы, риски длинных горизонтов. Отдаёт дайджест со ссылками, сутью каждого поста и тем, что забрать в свою работу. Use when (используй когда): пользователь хочет узнать, что нового вышло в блогах про AI

24601/surreal-skills

Expert SurrealDB 3 architect and developer skill (tracks v3.1.4+). SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, security, deployment, performance tuning, SDK integration (JS, Python, Go, Rust, Java, .NET, C, PHP, Swift, Kotlin, Ruby), Surrealism WASM extensions, SurrealML scope coverage (preview), built-in MCP (v3.1+) and standalone SurrealMCP, LangChain Python integration, editor tooling (LSP v0.1.6, tree-sitter, CodeMirror v1.0.6, VS Code/JetBrains/Neovim/Zed), and ecosystem integrations (Surrealist v3.9, Surreal-Sync, Surrea

wrsmith108/claude-md-optimizer

Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native mechanism, and rewrites the main file with zero information loss. Triggers: optimize CLAUDE.md, AGENTS.md too long, reduce copilot-instructions.md, agent instructions file too large, shrink context file, apply progressive disclosure, instructions file bloated

dualface/ste-zht

Make the agent report results to the user by the ASD-STE100 (Simplified Technical English) principles, in Traditional Chinese (Taiwan): key information first, one word one meaning, one fact per sentence, fixed status words, honest verification state, short sentences. Once active, applies to every reply in the session until the user says "停止 ste-zht" or "stop ste-zht". 讓 Agent 按 ASD-STE100 原則用繁體中文向使用者回報結果. Trigger: "/ste-zht", "用繁中 STE 規範輸出", "按 ASD-STE100 用繁體中文回報", "簡化技術中文（繁體）", "report in STE Traditional Chinese".

dragonknightk/ncm-listening-profile

当用户想在 Windows 或 macOS 上采集网易云音乐/NetEase Cloud Music 桌面版听歌画像数据、导出主歌单和听歌排行、生成本地 JSONL/CSV/aggregate 文件与 AI 分析 prompt 时使用。此 Skill 通过 CDP 启动或连接本机网易云音乐客户端，在已登录页面上下文用网易云 `/api` 采集用户创建歌单、主歌单、最近一周听歌排行和所有时间听歌排行；本 Skill 不在采集会话内做人格或画像分析。

peopleworks/SignsofAI

Detect and remove the tells of AI-generated writing in BOTH English and Spanish, and read back the evidence honestly. Use when the user asks to "de-AI" / "humanize" / "un-slop" a draft, to examine whether text carries the tells (delve, tapestry, "it's not just X, it's Y", "here's the thing", em-dash overuse, an assistant's own closing line left in the document), to compare documents for overlap, or mentions signs-of-ai / SignsOfAI. Backed by the SignsOfAI engine — for a measured 0–100 score, sentence-rhythm burstiness, originality, citations, a writer baseline or perplexity, hand off to that e