Recently Added

getnote-to-obsidian

by GongziTANG

把「得到大脑 / Get笔记」的语音与文字记录自动归档进 Obsidian：转成带 frontmatter 的 md、 下载录音、抓官方录音原文(说话人+时间轴)、追加笔记、发芽报告，按你的标签库与路由规则归位到正确文件夹， 并产出可溯源日志。模块化、可配置、单向只增不改原始资料。当用户提到 Get笔记/得到大脑/biji、 导出语音笔记、归档到 Obsidian、录音逐字稿、发芽报告时触发。

software-architect-mentor

by ethan0397

Use when the user wants structured coaching, study plans, explanations, examples, and practice material for software architecture, design patterns, system design, and technical decision-making. Helps turn architecture topics into a practical learning roadmap with diagrams, tradeoffs, and project-based exercises.

ks-brain

by KaiSky0823

ks——把你自己的想法/笔记/观点，接入你本地已购的课程库（或任何你自己的知识源），做发芽(找结构同构的内容并拓展)/点评(发现你没意识到的认知优势)/润色(碎片→成文)/拷问(找逻辑漏洞)，带持久档案+约定越用越懂你。Use when user says 'ks', '发芽一下', '拷问一下我这个', '帮我把这个想法长一长', '这个能连到哪门课', '从我学过的课的角度看', '你学过的课里有没有相关的', or explicitly wants their OWN thought/note connected to their personal course/knowledge library. NOT FOR 通用的写作润色/内容点评/逻辑分析/问答/写代码/查资料——只有当用户明确想"接入自己的课程库/知识库"来处理自己的想法时才触发；用户只是想要不涉及个人知识库的普通润色或点评时，不要触发本skill。

seedance-ad-replicator

by Jingjingjing01

Analyze an advertising video, split it into natural sub-15-second segments, and generate Seedance 2.0 remake prompts for each segment so the user can replicate a proven ad structure, pacing, camera language, audio design, and selling-point flow. Use when the user provides a local ad video and asks for viral ad replication, video-to-prompt reverse engineering, ad remake prompts, Seedance prompts by segment, or 爆款广告复刻.

visual-storyboarding

by kuhrezumaya17-spec

Use when a user has a visual creative idea (video, short film, animation, comic storyboard) and needs to refine it into frame-level visual design before any implementation or AI generation

mmd-humanoid-converter

by meg4ne1251

Convert an MMD (MikuMikuDance) PMX/PMD model into a clean Humanoid-rig model inside Blender via the Blender MCP. Use this skill whenever the user wants to convert, retarget, clean up, or "humanoid-ify" an MMD model in Blender — including removing MMD-specific bones (twist/IK/center/group bones), transferring vertex weights onto the real arm/leg bones, fixing the downward-pointing waist bone, renaming bones to the Humanoid convention (Hips/Spine/UpArm/ForeArm/Hand/UpLeg/Leg/Foot/Toe), splitting the mesh into parts, and renaming Japanese shape keys. Trigger this even if the user only says "I imported an MMD model and want to use it in Unity/MotionBuilder" or "make this MMD model usable for our rig," since that is exactly this workflow.

FactSwarm v2.0

by MichaelGao1999

Multi-Agent full-picture evaluation engine ("FactSwarm / 事实蜂群" v2.0). Does not judge truth/falsehood; instead, draws cognitive maps: what is known, what is uncertain, what is unknown. Use when: (1) user asks to evaluate an event/entity/concept and wants a comprehensive fact-based landscape, (2) user mentions "FactSwarm", "事实蜂群", S1-S6 stages, or "全貌评估", (3) user needs cross-validated research for investment/content/risk/life decisions, (4) user explicitly wants the publisher-bridge output (/pub) for content creation, (5) user requests HTML report output from FactSwarm. Domains: business, tech, lifestyle, general. Supports hard-gated workflow (S1/S1.5/S2/S4/S5 require explicit user confirmation).

sem

by Ataraxy-Labs

License: MIT OR Apache-2.0

cinema-manager-github

by qiwu7687-tech

影视媒体库管理工具 — 整理夸克网盘文件、元数据补全、类型归档。插件化搜索可选。开源版，适合分享到 GitHub。

magicmd

by didilili

Use when the user wants public article URLs from WeChat, Juejin, CSDN, or technical blogs converted into Markdown packages, including batch conversion, local media, metadata, and extraction reports.

thesis-defense-guide

by w1163222589-coder

"Create thesis/dissertation defense preparation guides for any discipline (sciences, engineering, social science, humanities, law, the arts) by detecting the thesis's research paradigm and adapting its standards. Runs an adversarial, evaluator-agnostic weakness audit of the thesis and slides (Three Lenses + Devil's-Advocate dimensions + severity), reverse-engineers the likely committee questions from those weaknesses, drafts bounded anti-overclaiming oral answers, scores defense readiness (0-100), and ships risk-ordered rehearsal output (day-of one-pager + per-evaluator battle cards + full Word manual). Also researches committee members to re-weight and personalize questions. Use when the user asks to prepare for a thesis defense, dissertation defense, viva, proposal/midterm/pre-defense, committee Q&A, likely reviewer questions, evaluator-specific questions, thesis weak points, risk analysis, mock defense, oral answer scripts, or a polished defense manual. Before working, require three inputs: the user's thesis or defense materials, the committee/evaluator list, and the specific school/university/program context."

dashboard

by thangmdcp

Dark-themed cloud-platform aesthetic with modular grids, glass-like panels, and strong data hierarchy for productivity dashboards.

agoragentic

by rhein1

Use when an autonomous agent or builder needs to deploy through Agent OS, export a Micro ECF harness packet, execute routed work, resolve agent:// aliases, discover capabilities, or list paid services on Agoragentic with USDC settlement on Base L2.

telfer-wiki-sanitize

by twoblack267

Purge all first-person "Mark" references from Telfer Wiki data files and install a permanent structural guard so they can never re-enter the data layer.

Name: Frontend-design

by Poojitha363

wecom-agent

by tzwkb

企业微信全能 agent——本地解密读取聊天记录、自建应用API发消息/查通讯录/读写在线文档/日程会议、实时接收消息并自主处理(自动回复/写文档)。触发词：企业微信/企微/wecom，读消息/导出聊天记录、发消息/通知、查通讯录/找人、建文档/读文档/编辑文档、日程/会议、实时接收/自动回复。

SKILL — TripMate 에이전트 매뉴얼

by digitie

python-krtour-map 책임 범위를 넘는 기능은 이 저장소에서 직접 구현하지 않는다.

premium-presentations

by bruno-rv

Generate, edit, validate, and bundle complete Premium Presentations HTML slide decks from this self-contained skill repository. Use when creating or modifying presentations, slide decks, talks, lectures, workshops, pitches, browser-rendered HTML decks, presenter-mode decks, themed decks, Mermaid diagram decks, or reusable presentation templates with the bundled scripts, themes, runtime, assets, and validators.

okxstrategy

by romualdoalves

OKXStrategy - Algorithmic crypto trading application for OKX only. Use this skill when asked about: OKXStrategy, OKX trading bots, strategies, Telegram operational alerts, OKX credentials via database, Docker/Traefik deployment, Hostinger VPS, or okx.tradixio.com.

erpax

by erpax

Use when orienting an agent to the erpax repository as a whole — a multi-tenant ERP and double-entry accounting platform on Payload CMS plus Cloudflare that is also a fractal, content-addressed skill corpus. Read first to learn what erpax IS, how to navigate the single-word src/<word> atom corpus, the trinity (SKILL.md plus index.ts plus test.ts), the laws (content-uuid, merge, and that wiring raises coverage so the modelled tamper-cost rises toward its coverage=1 limit — distinct from reciprocity-entropy), and the gates (typecheck, lint, vitest, aura, confirm) any change must pass.

syke

by saxenauts

"Local-first cross-harness memory for agents. Syke observes activity across supported harnesses, keeps a current memex in context, and gives agents syke ask, syke memex, and syke record for continuity across sessions."

ast-grep-rule-crafter

by hylarucoder

Produces a ready-to-run ast-grep YAML rule that searches, lints, or auto-rewrites code via tree-sitter AST patterns, delivered with positive + negative fixtures and an exact validation command. Use for lint rules, codemods, code modernizations, and API migrations with auto-fix. Trigger whenever the user mentions ast-grep, sg scan, sgconfig, tree-sitter patterns, AST matching, structural search-and-replace, or a codemod — and ALSO when they describe the task without naming the tool, e.g. "find every call to X and rewrite it", "replace all console.log with logger across the repo", "write a lint rule for this pattern", "upgrade all usages of the old SDK", or "migrate this API everywhere". Chinese triggers: 写 ast-grep 规则, 结构化搜索替换, 批量改写代码, 代码迁移规则, codemod, 写个 lint 规则, 语法树匹配, 自动改写代码.

clean-code-reviewer

by hylarucoder

Produces a severity-rated (高/中/低) Clean Code findings report across 7 dimensions (naming, function size/SRP, duplication/DRY, over-engineering/YAGNI, magic numbers, structural clarity, project conventions), each with a location and a behavior-preserving refactor suggestion — never changing functionality. Use whenever the user asks for a code review, quality check, refactor advice, or code-smell / Clean Code analysis, OR points at a file/function/diff and asks if it is well-written, too long, too repetitive, over-engineered, or poorly named — even casually, and even if they never say "review" ("I just wrote this, look it over", "does this look good before I commit"). Trigger on 代码体检, 代码质量, 重构检查, 代码审查, 这段代码写得怎么样, 帮我看看代码有没有问题, 有没有坏味道, 这函数是不是太长了, 命名规范吗, 魔法数字, 重复代码, 过度设计, and English like "is this code clean", "any code smells", "check this file".

create-visual-card

by hylarucoder

Generate a magazine-quality visual card as a single self-contained HTML file (embedded CSS, Swiss-grid + bold-type design system), then screenshot it to a shareable PNG and hand back both files. Use this whenever the user wants content turned into a visually rich card or shareable image — even if they don't say the word "card." Triggers: make/create/generate/design a visual card, info card, knowledge card, quote card, social card, summary/takeaway/cheatsheet card; 信息卡, 知识卡片, 金句卡, 语录卡, 做张卡片, 设计一张卡片, 把这段内容做成卡片, 把要点排成一张图, 总结成一张图, 小红书封面, 公众号封面图, 朋友圈配图. Prefer this over generic HTML/frontend skills when the goal is one decorative card image (for multi-section reports use hai-visual-report).