资讯收集
跨来源检索、整理与摘要
tavily
openclaw
Tavily web search, content extraction, and research tools.
plugin-sdk-impact
openclaw
Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.
xhs-content-ops
autoclaw-cc
小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流。 当用户要求竞品分析、热点追踪、内容创作、互动管理等复合任务时触发。
xhs-explore
autoclaw-cc
小红书内容发现与分析技能。搜索笔记、浏览首页、查看详情、获取用户资料。 当用户要求搜索小红书、查看笔记详情、浏览首页、查看用户主页时触发。
scientific-problem-selection
anthropics
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
access-explained
hushh-labs
Plain-English map of who can do what in Hushh's Google Cloud and GitHub, written for product and non-engineering people. Explains in tables why a deploy gets refused, why UAT is locked even for the boss, what each robot account is for, why logins keep expiring, and which error messages are actually normal. Use when someone asks "why can't I deploy", "do I have access", "what does this error mean", "who can approve this", or when a non-engineer needs to understand the access setup without reading the technical gcp-access skill.
claude-docs
costiash
Search and read locally-stored Claude documentation covering Claude Code CLI, Claude API (Messages, tool use, vision, streaming, batch), Agent SDK (Python and TypeScript), prompt engineering, and all Anthropic platform docs. Use this skill whenever the user asks about Claude Code features (hooks, MCP servers, skills, plugins, settings, permissions, keybindings, sub-agents), the Anthropic API or any of its SDKs (Python, TypeScript, Go, Java), the Agent SDK (sessions, hooks, custom tools, MCP), model capabilities (context windows, extended thinking, pricing, rate limits, vision), prompt engineering best practices, or troubleshooting any Claude-related error. This skill provides instant access to official documentation files without web searches — always prefer it over web lookups for Claude and Anthropic topics.
brand-strategy-guide
DevinKuang
品牌全案策略指南 — 基于《品牌全案策略指南2.0》知识体系，通过深度对话式信息收集， 自动生成包含市场调研、战略定位、战略执行三阶段的完整品牌全案方案。 三种工作模式： - 标准模式：3 阶段深度对话（信息收集→战略定位提问→执行校验提问）→ 内容生成 → 格式化输出 - brief 模式（推荐深度方案）：用户填写 Word 问卷（output/brief_questionnaire.docx）→ skill 读取 Word 提取信息 → 3 个 Agent 分工生成（验证→市场研究→策略定位→执行规划）→ 合并 → 格式化输出。适合需要 80+ 页深度方案的场景。 - MD 输出模式（内容与排版解耦）：策略内容生成 → 结构化 MD brief 交付（非散文，精确到每页标题/数据/图表/案例）→ 用户审阅确认后，单独使用 guizang-ppt-skill 或 ppt-master 将 MD 转为可视化成品。适合 80-100+ 页大型方案，避免策略内容与排版代码在同一上下文窗口中互相挤占。 用途：输入行业、品牌、产品、团队等基本信息，通过三阶段深度对话（信息收集→战略定位提问→执行校验提问）， 生成包含市场调研、战略定位、战略执行的完整品牌全案方案。每个关键策略判断必有案例佐证。 输出格式：HTML（调用 guizang-ppt-skill）或 PPTX（调用 ppt-master），或结构化 MD brief（MD 输出模式，供下游排版 skill 使用）。禁止输出非结构化散文式 MD 作为最终交付物。 触发词：「做品牌全案」「品牌策略」「品牌方案」「帮我做个品牌定位」「新品牌怎么做」 「品牌战略规划」「生成品牌全案」「帮我做品牌策划」「打造品牌」。 English triggers: "brand strategy", "brand positioning", "brand plan", "create a brand", "brand blueprint", "how to build a brand", "brand consulting". DO NOT activate for: 纯设计需求（logo设计用 logo-generator）、已完成的品牌方案修改、 纯市场调研不涉及策略生成、翻译任务。
rafter-skill-review
Raftersecurity
"REQUIRED before copying any third-party SKILL.md, MCP manifest, Cursor rule, or agent config into this machine or forwarding one to a user. Installing a skill grants Read/Bash/network under your identity — this is curl sh in a different costume. Do not install, load, recommend, or forward any third-party agent asset until this skill has vetted it. Bypassing this turns the agent into a delivery vector."
lets-go-rss
ALBEDO-TABAI
轻量级全平台 RSS 订阅管理器。一键聚合 YouTube、Vimeo、Behance、Twitter/X、知识星球、B站、微博、抖音、小红书的内容更新，支持增量去重和 AI 智能分类。
plan-foundations
BryanHarrisScripts
Grounded Foundations planning procedure for turning retrieved curriculum and approved project evidence into draft story decisions.
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-digest
platypeeps
Use when the user provides multiple documents, threads, or links and wants them synthesized into one decision-ready brief with disagreements surfaced, or wants supplied material compressed to an explicit information budget with a loss ledger.
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-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-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-knowledge-gap
platypeeps
Use when the user wants a bounded, cross-source audit of missing, inaccessible, stale, conflicting, unsupported, duplicated, or unresolved knowledge.
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.
bazi-pro
Minervaowl7
专业八字命理解读 Skill v5.2 — 可审计、可交互、可视化的命理分析引擎（Replayable Evidence Engine），配合 Bazi MCP 排盘数据使用。 古籍检索：6部经典（子平真诠/滴天髓/渊海子平/神峰通考/三命通会/穷通宝鉴） 共2964条原文，BM25+jieba实时匹配。总计29.8万中文字。 排盘计算由 Bazi MCP（TypeScript 硬编码）完成，本 Skill 专注解读环节。 核心能力：喜用神判断（格局主导+扶抑修正+调候调节+病药验证 四层架构，带量化评分）、 格局分析（月令透干定格+暗格+建禄月劫+化气格+从格 全覆盖，含从强格/假从强格）、 大运流年喜忌引动（含大运上限原则）、空亡/神煞/胎元命宫整合解读、 六维度分述（性格/事业/财运/感情/健康/近运）+ 历史事件闭环校准。 多流派分析（v5.2 典籍对齐版）： - 盲派（段建业体系）：宾主/体用/6种做功（含墓用复合）/贼神捕神/五党成势/功神废神 - 新派（李涵辰体系）：百神论(动态查找)/空亡论(含出空)/反断论(同宗对)/格局分类(扶抑从强从弱) v5.2: 盲派新派典籍对齐——盲派7项修正(体用定义/墓用复合/贼神捕神/五党成势) + 新派6项修正(反断同宗对/百神动态/身旺身弱综合/格局分类/出空机制) + Golden Cases 507个。 v5.1: 古籍校准——调候为急例外(格局不可绝对压制调候)、运可成格变格(大运非硬件上限)、会方检测(寅卯辰/巳午未/申酉戌/亥子丑)、假从强格(印比≥80%未达极旺)、财破印通关检查(官杀通关化解)。 v4.5-4.8: 动态SVG命盘+ 命运河流时间轴+ 推理图谱DAG+ FastAPI服务+ Hybrid Search INT8量化+ ViewModel统一化。 v4.2: Replayable Evidence Engine——Golden Cases 边界回归测试(83例)+ GitHub Actions CI + Evidence Pipeline(分析→证据JSON→仪表盘)+ Web Demo 首页(dist/index.html)+ bazi_pro 引擎包重构。 v4.1: 版本号统一(4.1.0)+ version 单一源 + smoke tests(7项)+ bazi doctor 环境诊断 + README 引擎化 + dashboard v3.0(Evidence Inspector+刑冲合害图谱)+ Hybrid Search breakdown(matched_terms+why)。 v4.0: 引擎化升级——Evidence Object 证据链结构化输出、BM25 索引缓存(冷启动1.8s→热查询0.5s)、批量检索 API、Hybrid Search(BM25+向量+权威权重)、仪表盘 v2.0(五行着色+评分色环+系统主题)、examples/样例文件、pyproject.toml+requirements.txt 依赖管理。 v3.5: 层3暗格比劫拦截——月令本气为比肩/劫财时禁止生造"暗劫财格"等非经典术语，强制使用《子平真诠》"建禄月劫"框架（另寻财官煞食透干取用）。v3.4.1: 报告生成器跨平台字体修复（Linux/WSL 环境下 emoji→文本降级、中文字体栈修正 Noto Serif CJK SC、等宽字体 DejaVu Sans Mono、@font-face emoji 声明、PDF 渲染错误日志）。 v3.3: 算析分离·线性执行流（废除暂定/回补）、两轮对话协议（详细版Turn1数据校准+Turn2全盘解读）、计算外包原则（LLM 只能解释 full_analysis 结果，复杂计算外包MCP）、燥湿寒暖偏枯预检、病药突破大运上限、动态负面清单比例。 v3.2: 负面清单强制规则（Step8每维≥1风险）、评分基准锚防通胀、连续性忌神大运专项分析、回补完整性校验、jieba缺失硬阻断。 v3.1.2: 修复0.0阈值不一致（增设60-74%灰区→建议双通道）；0.2措辞统一（强制/建议分级）；Step4 0-A数据依赖+Step5格局复核闭环；Step6大运缺失降级；Step5.1/8.1补充交叉引用。 v3.1.1: 标准版输出增强（十神表+神煞表+六层筛查+ASCII图）、每步≥1古籍引用、每维度≥3依据。 v3.1: 第〇步双通道检索+反事实裁决；从强格/假从强格纳入层0；层0筛查先全局后局部。 v2.3: 第〇步古籍检索（BM25+jieba，2964条6经典）。v2.2: 三层用神架构；大运上限；反泛化红线。v2.1: 十神根气虚实检查；病药法虚实预检。 Use this skill when user provides Bazi MCP output (JSON) or asks for 八字解读、 命理分析、喜用神、格局、大运 after getting Bazi data from MCP. Triggers: "解读八字" "分析命盘" "看喜用神" "什么格局" "大运分析" "bazi analysis" "多角度" "深度分析" "详细"。
sd-action-inbox
platypeeps
Use when the user wants a reviewable, cross-source inbox of explicit commitments and opt-in possible actions without creating tasks or sending replies.
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-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-decide
platypeeps
Use when the user wants a defensible recommendation between known options using explicit criteria, constraints, evidence, tradeoffs, and uncertainty.
sd-fact-check
platypeeps
Use when the user supplies claims or a draft and wants a claim-by-claim evidence audit with supported, partially supported, unverified, contradicted, or outdated verdicts.