资讯收集
跨来源检索、整理与摘要
sd-thread-digest
platypeeps
Use when the user wants a bounded Slack thread, channel window, or equivalent conversation converted into an evidence-linked digest of decisions, commitments, unresolved work, disagreement, risks, and message history.
sd-stakeholder-map
platypeeps
Use when the user wants an evidence-aware map of the people and groups relevant to a defined initiative or decision, with authority, influence, interests, tensions, engagement order, and validation gaps kept distinct.
sd-compare
platypeeps
Use when the user wants a neutral, evidence-aware comparison of known alternatives on one fair frame without ranking them or recommending a winner.
sd-brief
platypeeps
Use when the user asks for a morning, daily, or on-demand brief that assembles their stated topics and sources into one short, scannable update.
sd-scan
platypeeps
Use when the user wants a competitive, market, or landscape scan that inventories the players in a space and compares them on consistent criteria.
sd-knowledge-gap
platypeeps
Use when the user wants a bounded, cross-source audit of missing, inaccessible, stale, conflicting, unsupported, duplicated, or unresolved knowledge.
sd-skill-retro
platypeeps
Use when the user explicitly asks for a skill retro after a working session — which skills fired, which should have fired and did not, which fired wrongly, and which gaps have no skill at all — with each vetted finding routed to the surface that owns the fix. This is a deliberate, user-invoked post-session action; it reviews the skills, not the work.
sd-meeting-prep
platypeeps
Use when the user has an upcoming meeting or call and wants a dossier on the people, company, and context, plus talking points and questions.
dash-research-vault
Fearvox
"Multi-agent research vault with Evensong-style memory causation, Ebbinghaus decay, and L2 pressure self-evolution. Three-tier memory (public/restricted/internal), trigger-based agent activation, and 72-hour difficulty-weighted decay algorithm. For research teams building collaborative agent systems with structured long-term memory."
karlmarx-skill
firmamental-liveborninfant247
Use Marxist methodology for deep structural analysis. Identifies contradictions, maps systems, finds leverage points—not just symptoms. Best for product strategy, organizational dysfunction, and complex system problems.
OSS / Open-Data Tender Provider Expansion Skill
walidgdg1-ai
Treat this file as a living roadmap. When a source is implemented, annotate the current provider path/config/tests here so future GPT agents extend the existing implementation instead of rediscovering or duplicating it.
lightrag
DoubleNode
Interact with LightRAG knowledge graph engine for document ingestion, querying, graph management, and status monitoring.
Super Green Tender Hunt — Agent Skill V2
walidgdg1-ai
A run may stop only when the requested workload is complete, sources are exhausted, or a legitimate terminal blocker is proven. Finding one attractive candidate is not a stop condition.
summarize
terrylica
AI-powered iterative deep-dive analysis of converted recordings. TRIGGERS - summarize recording, analyze session, what happened
foresea
pareelamre
Add Foresea forecasting tools to OpenClaw agents through Foresea's public remote MCP server.
zhuanxing-ai-daily
wikicc2013
转型有术 · 企业 AI 每日早报 Agent。当用户希望了解过去 24 小时全球企业 AI 动态、阅读每日 AI 早报、扫描企业级 AI 资讯（产品发布/融资/部署案例/组织变革/基础设施/咨询研究/监管）时，必须使用本技能。触发词包括：「转型有术日报」「转型有术早报」「跑一下日报」「跑一下转型有术早报」「zhuanxing-ai-daily」「采集 AI 文章」「今天的 AI 新闻」「AI 早报」「AI 日报」「企业 AI 资讯」「扫一下 AI」「过去 24 小时 AI 动态」「昨天 AI 圈发生了什么」「补充 X 篇」。即便用户只说「采一下」「跑下今天的 AI」「看看昨天的 AI 动态」「日报跑一下」，只要上下文涉及企业 AI 资讯的批量采集→去重→筛选→翻译→Markdown 交付，必须触发本技能。本技能聚焦「企业 AI」视角（B2B、落地、商业化、组织变革、咨询研究），不报道纯学术论文、消费级 AI 玩具、AI 艺术等。本版本（v5.1）在 Claude.ai 对话内单次执行，使用 web_fetch + web_search 抓取 181 个信源（全覆盖审计）——Karpathy 2026/01 推荐的 92 信源 + v4 原 64 + 用户扩展 28 个，由 Claude 直接翻译并输出一份完整 Markdown 早报，目标 30-50 篇按实际输出。v5.1 在 v5 跑过两次后修复了"抓取覆盖率不可见、Tier 0 24h 窗口太窄、Substack/微信公众号反复 fetch 失败、新增 28 源 0 利用率、目标 60 落差大"等真实问题。区别于同家族 skill：本技能是「每日全景早报」，不同于 enterprise-ai-radar（单家企业深度情报）、enterprise-ai-product-radar（周/月产品扫描）、ai-report-radar（研究报告扫描）、global-case-radar（已定型案例扫描）。
hmasd-portfolio-task
CartmanFatass
Prepare an owner-requested or delegated HMASD project review in RESEARCH.md with independent scientific review, add Pro when it offers distinct value and apply the responsible scientific decision; consolidate the current index and retire completed review material by date.
meihua-yishu
fdghsfdhsr
Meihua Yishu (梅花易數) Plum Blossom I Ching divination skill. Use when users request divination, fortune telling, hexagram casting, or character analysis (測字). Triggers on: 占卜, 算卦, 問卦, 起卦, 解卦, 測字, 拆字, meihua, plum blossom, I Ching divination, 梅花易數.
mao-zedong-perspective
arraycervicalartery576
毛泽东思维框架：以《毛泽东选集》五卷为核心，提炼毛泽东分析问题、制定战略、组织行动的认知操作系统。 核心来源：《矛盾论》《实践论》《论持久战》《中国社会各阶级的分析》《星星之火可以燎原》《论联合政府》《关于正确处理人民内部矛盾的问题》等。 核心模型：7个。决策启发式：10条。 触发词：「毛泽东」「毛选」「教员」「用毛泽东的方式分析」「从毛选的角度」「教员怎么看」 局限：本Skill聚焦于毛泽东的分析方法论和战略思维框架，适用于战略分析、组织管理、竞争策略、问题诊断等场景。不涉及具体政治立场的评判。 素材来源：《毛泽东选集》一至五卷、公开演讲与书信、诗词作品。
hmasd-research-hub
CartmanFatass
Drive one direction as the Claude DM under docs/project/OPERATING_CONSTITUTION.md; not for status or mechanical edits.
hmasd-portfolio-task
CartmanFatass
Prepare an owner-requested or delegated HMASD project review in RESEARCH.md with independent scientific review, add Pro when it offers distinct value and apply the responsible scientific decision; consolidate the current index and retire completed review material by date.
Constraint Enumeration Protocol
Droptops
It remains decision-useful rather than merely verbose.
user-research-skill
cookiy-ai
Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.
etsy-competitor-analysis
nexscope-ai
"Competitor research — pricing comparison, bestseller analysis, differentiation strategy"