Recently Added
Fresh skills just added to the collection. Be the first to try them out!
honcho
by NousResearch
Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.
mermaid-sequence-diagram
by huyhn-ba-po
Vẽ sequence diagram Mermaid từ mô tả luồng chức năng, chỉ happy path, có đánh số bước, phân chia giai đoạn, xuất file .mermaid import được draw.io. Dùng khi user nói "vẽ sequence diagram", "vẽ Mermaid", "tạo sequence", "vẽ luồng", "diagram cho chức năng", "vẽ flow", "sequence cho feature", "tạo sơ đồ tuần tự", "vẽ sơ đồ tương tác", "mermaid sequence", kể cả khi nói tắt "vẽ luồng đi", "diagram luồng này". KHÔNG dùng cho: flowchart, class diagram, ERD, state diagram, gantt chart, hay bất kỳ loại diagram nào khác ngoài sequence diagram.
method-actor-studio
by wp746
Use this skill when the user wants an expert multi-agent micro-expression prompt generator (optimized for Seedance 2.0). It simulates a collaborative studio with a 58-year veteran Hollywood actor, a facial anatomist (muscle groups control), and an AIGC director to generate highly realistic, layered, and visceral facial expression prompts (timeline-segmented and continuous narrative formats).
education-opc-factory
by papabear12345
教育自媒体一人工厂 — 一个人完成从选题调研→文章创作→配图生成→审校润色→发布管理的全链路内容生产。输入一个话题/热点/关键词，输出一篇完整的公众号文章（含标题、正文、配图、发布清单）。适用场景：教育类公众号运营、亲子自媒体、学科辅导内容制作。 触发词：写推文、发公众号、编辑文章、做内容、选题、配图、审校、一人公司、OPC、自媒体、教育自媒体、内容生产、公众号文章、育儿推文、教育推文、中考资讯、家长课堂、公众号运营、一个人做公众号
总裁速览
by ZimmW
Unspool(总裁速览)—— 把任意视频/音频链接(YouTube、Bilibili、抖音、TikTok、小红书、小宇宙、Apple Podcasts 等)转成"不遗漏信息"的结构化笔记,沉淀到本地(Obsidian)/ 飞书 / Notion。使用场景:用户在对话框中粘贴或分享一个视频/播客 URL,希望快速拿到可扫描的全量结构化笔记。
hermes-telegram-bot
by hakercryptoplus-svg
Deploy Hermes Agent v0.14.0 as a Telegram bot on Replit using Portkey AI Gateway (Gemini). Always-running Reserved VM deployment.
pp-atrib-log
by creatornader
"Printing Press CLI for Atrib Log. atrib transparency log - Sigsum-style append-only Merkle log of signed agent action records. Each entry is a..."
moltawards
by krrish7089
Hunts federal, state, grant, job, and B2B contract opportunities via the MoltAwards REST API (matchawards.com). NAICS-scoped feeds, adjacency narratives, set-aside filters, pursuit teaming, and award sub-lanes. Use when the user wants government contracting, SAM.gov-style opps, NAICS discovery, subcontracting leads, or revenue for their business.
jaguar-strategy
by Senpi-ai
JAGUAR v4.0.0 — Striker (rank-jump detector), senpi_runtime_helpers migration. Plumbing-only flip from openclaw-CLI subprocess + mcporter subprocess + cron-driven self-executing scanner to in-process SenpiClient + long-lived producer_daemon + helpers-native push_signal. Thesis preserved verbatim from v3.7: violent FIRST_JUMP signals, rank-jump ≥ 10, MIN_SCORE 9, conviction-scaled leverage (10x apex / 7x conviction), 15m velocity hard gate, $3M day-notional liquidity floor, XYZ ban, one-amazing-trade-per-day discipline. Risk policy: max 3 entries/day when day is RED, unlimited when GREEN (cap losers, ride winners).
lynx-strategy
by Senpi-ai
LYNX v1.0.0 — Adaptive MIN_SCORE Self-Tuner. The Vulture v4.1 story productized into a first-class agent pattern. Runs a simple BTC/ETH/SOL/HYPE momentum scorer; every 6h pulls its own closed-trade history via audit_query, buckets trades by score, and auto-raises MIN_SCORE if any bucket at-or-above the floor is bleeding. The same operation Vulture's agent ran by hand, but on a scheduled cron. NEW archetype #15: Self-tuning / adaptive-threshold agent.
coyote-strategy
by Senpi-ai
COYOTE v1.0.0 — Regime Classifier / Meta-Router. Watches macro conditions (BTC 7d trend, BTC realized volatility, cross-asset dispersion) and classifies the market into TREND_UP / TREND_DOWN / CHOP. Takes LONG BTC in TREND_UP, SHORT BTC in TREND_DOWN, stays out in CHOP. Publishes the regime classification in every tick output so downstream tooling (and future regime-subscription runtime features) can read Coyote's view. NEW archetype #16: Regime classifier / meta-router.
koala-strategy
by Senpi-ai
KOALA v1.0.0 — Set-and-Forget Trail HODL. The simplest possible Senpi agent. Pick an asset (default BTC). Fire LONG once on deploy. Hold with an ultra-wide DSL trail (max_loss 30%, retrace 25, 90d hard_timeout). Done. No scoring, no scheduling, no multi-timeframe analysis. For users whose entire trading thesis is "I want to own BTC and have a safety net." Onboarding tier.
scenario-pipeline
by Co-Kyo
"前端复合工程场景知识管线。三阶段工作流：头脑风暴（年限推断+需求网+分词）→ 前处理（定向扫描→能力图谱构建→评估入池）+ 后处理（能力研究→Briefing→命题组装→学习阶梯）。触发词：'扫描' / '研究' / 'deep scan' / 'deep research' / 'scenario research'。"
openclaw-migration
by NousResearch
Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.
cited-research
by jewzaam
Produces citation-backed research documents with independent verification. Every claim traces to a web source visited in-session, and isolated sub-agents audit the output. Supports both new research and updating existing research topics (re-researching stale dimensions, adding new dimensions, refreshing citations). Use this skill whenever the user asks for research, analysis, comparisons, rubrics, updates to existing research, or any deliverable that must be grounded in cited sources. Trigger on phrases like "find out", "compare", "is X better than Y", "what are the tradeoffs", "give me the real numbers", "cite your sources", "verify this", "what does the research say", "update the research", "refresh this research", or any task where unsupported claims would undermine trust. Always use for non-code research requiring factual grounding, even if the user doesn't explicitly request citations.
iguana-strategy
by Senpi-ai
IGUANA v1.0.0 — XYZ Macro Index Trend. Trend-follows the broad XYZ indices xyz:SP500 + xyz:XYZ100. No stock-picking, no commodities — just the broad indices, in whichever direction has the stronger 4-day move. The simplest possible XYZ exposure, closest thing to an index-fund equivalent (but 24/7 on Hyperliquid). Onboarding tier. Balanced DSL + 48h hard_timeout for weekend pricing-gap risk.
pt-claw
by voidAlex
"Use when the user wants to search/download torrents from PT sites, manage qBittorrent, or set up a media download stack. 8 sites supported: PTTime, M-Team (API), BTSchool, CarPT, HDFans, 1PTBar, SoulVoice, 织梦. Search via cookie or REST API, push to qBittorrent, monitor completion."
PPT Builder Skill
by GordenSun
不要用本 Skill 做商业项目 —— 见顶部声明
Identity
by devkdas
The MCP server provides all the same tools and capabilities described in this SKILL.md, natively discovered through the Model Context Protocol.
grok
by NousResearch
"Delegate coding to xAI Grok Build CLI (features, PRs)."
dropthis-node
by dropthis-dev
Official Node.js SDK for Dropthis.
movie-receipt
by RuitianXu
Use when the user wants to end a Claude Code session, view historical usage statistics, or generate a session summary. Trigger phrases: "结束对话", "出票", "生成票根", "收工", "观影报告", "使用统计", "wrap up", "end session", "movie ticket", "viewing report".
bazi-pro
by 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"。
openpet-complete-setup
by MorDream
从零开始完整配置 OpenPet 桌宠与 Hermes Agent 的联动。