Recently Added
Fresh skills just added to the collection. Be the first to try them out!
gzh-design
by isjiamu
微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown 先自动归一化），也支持"一键自动排版"（自动推断结构+选主题），还支持根据用户描述/参考图生成自定义主题组件库并保存本地复用。触发场景：(1) 用户提到"公众号排版""公众号文章""微信排版""gzh"，(2) 用户想把文章（md/docx/pdf/纯文本）转成公众号 HTML，(3) 用户说"自动排版""一键排版"公众号内容，(4) 用户想为公众号排版"生成新主题/自定义风格/按这张图做一套组件库"。不用于生成普通网页/落地页/PPT（用前端或 PPT 类 skill）。
linkedin-connect
by DawgZter
Connect or reconnect the user's LinkedIn account for LinkedIn automation. Use when the user asks to connect LinkedIn, set up LinkedIn automation, reconnect LinkedIn, or check whether LinkedIn is connected.
Commercial Scope & Revenue Recovery Agent
by viliusfetingis18-lab
MIT License – Open source for community contribution and commercial licensing.
ocas-forge
by indigokarasu
'Skill architect and builder. Designs, builds, and validates complete Agent Skill packages through a mandatory eight-phase pipeline: existence gate, research, classify, scope, architecture, plan, build, validate. Default output is the finished installable package. Not for skill evaluation (use skilllab''s Critique procedure) or variant proposals (use ocas-mentor).'
SKILL.md
by edmundtrinh
greptile — code search not needed with local codebase
shopify-product-photo-agent
by thibaultimbert
Use when a user wants Codex to connect to any Shopify store, extract product catalog images, generate new AI product photography from the actual product images, preview the results, and upload approved or explicitly requested images back to Shopify product listings.
hermes-multi-agent-orchestrator
by L-MORIA
Multi-agent orchestration for Hermes Agent using OpenCode Zen free models. 5 proven patterns: Council (parallel), Pipeline (sequential), Hybrid. Roles: Architect (Big Pickle Med), Planner/Researcher (Deepseek V4 Flash), Coder (North Mini Code), Synthesizer (Mimo V2.5), Reviewer (Nemotron 3 Ultra).
tinybrain
by javimosch
Train tiny neural networks in pure machin (MFL) and ship them as JSON artifacts any MFL app embeds — MLP + SGD backprop for labeled data (classifiers/regressors, incl. bag-of-words intent routing), neuroevolution (GA + fitness closure) for control tasks (game AI), a deterministic PRNG for reproducible runs, and an agent-first CLI (train/predict/eval/guide). Use when an MFL program needs a learned controller, classifier, or scorer — NOT for generative text.
thariq-workflow
by ennheng
Thariq's full-cycle agentic coding workflow for complex tasks.
borrowed-brain-pro
by tacticalwarningsubscriptionwarrant526
Distills any public figure's thinking into a structured, sourced "thinking profile," then applies it as an extra lens on a real decision. Trigger when the user names a person and asks to think/decide like them, wants their framework or mental model, asks "what would X think," or wants to build/update a saved profile. Also trigger when an existing profile in profiles/ is referenced for a new question, or when the user is unsure how to use this skill. If the user describes a decision without naming anyone and a relevant profile exists, surface it as a one-line suggestion only — never apply unprompted. Do NOT use for creative impersonation or fictional dialogue.
morning-ai
by GitLunYb
"Daily-scheduled AI news tracker. Collects updates from 80+ AI entities across 6 sources every 24 hours (default 08:00 UTC+8). Generates scored, deduplicated Markdown reports. Supports unattended cron/scheduled execution with date-stamped idempotent output."
babat-red-project
by Redurbabat
Project rules and workflows for BABAT RED, a multi-space personal OS with Finance, Learning, Documents, Wardrobe, AI, Health, Dashboard, Settings, shared components, services, and utilities. Use when changing BABAT RED architecture, spaces, UI, Graphify artifacts, animation systems, or AI-agent workflows.
ai-media-generator
by Hao0321
為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞，並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0 pro、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen-4.5 / Aleph、Google Veo 3.1、Ideogram 3、Nano Banana Pro、Stable Diffusion 3.5（⚠️ OpenAI Sora 2 已於 2026-04-26 停運，API 撐到 2026-09-24，預設改推 Runway/Veo/Kling）。只要使用者提到「AI 生圖」「AI 影片」「AI 音樂」「做 MV」「做 storyboard」「寫 prompt 給 XXX」「我想用 Kling/Suno/Midjourney/Runway/Veo...」「幫我操作 OiiOii / 即夢 / 可靈」「txt2img / img2video / 文生圖 / 文生影片 / 圖生影片」「角色一致性」「多鏡頭分鏡」「運鏡」「結果有瑕疵 / 不夠精緻 / 怎麼修」，或任何跟上述平台或影像/影片/音樂生成工作流相關的任務，都要用這個 skill。即使他們沒講明平台，只要任務是要餵給某個生成模型的 prompt，就用這個 skill 幫他們選對的平台、寫對的格式。
hako
by masakirocorp
"Control hako from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running hako instance over a local unix socket. Use when running inside hako (HAKO_ENV=1)."
spotter
by engguh01
Use this skill whenever the user gives a short or vague vibe-coding instruction that references existing UI elements, components, pages, or behavior inside an existing codebase (e.g. "ubah button di header", "samain style sama halaman login", "fix the navbar spacing"). This skill enforces a scoping-first workflow — run scripts/scoper.py to get a short list of relevant file paths BEFORE reading any file contents, instead of scanning or reading the whole project. Do not use this for brand-new files/features with no existing reference, or for tasks that already specify exact file paths.
landing-premium
by lucasmartinsgyn62-lab
Use this skill whenever building or redesigning a landing page, hero section, or marketing site — especially for clinics, dental practices, SaaS products, or service businesses. Helps avoid the generic "AI-generated" look (cream background + serif headline + terracotta accent, OR dark background + single neon accent, OR templated bento grids) by forcing deliberate, subject-specific design decisions.
bybit-trading
by bybit-exchange
Bybit AI Trading Skill — Trade on Bybit using natural language. Covers spot, derivatives, earn, and more. Works with Claude, ChatGPT, OpenClaw, and any AI assistant.
powder
by misty-step
Use when an agent needs to inspect, claim, update, request input for, or complete work cards in a Powder instance. Powder is the self-hostable, agent-first work board: a durable card store with run sessions, activity, audit events, relations, optional proof, and human-in-loop states.
novel-master
by bbroot
出版级中文长篇小说全流程创作技能包。当用户要求写小说、创作故事、分章节写作、连续剧情、章节悬念、长篇小说时触发。覆盖从世界观设定、人物塑造、大纲规划、分章撰写到伏笔管理、质量控制的全链路。
music-creation-engine
by mage0535
Deployable music generation workflow for AI agents, with CLI, API, agent adapters, and configurable integrations.
mo-graphify-obsidian-memory
by M4F-S
Graph-based knowledge memory system using Obsidian markdown vault files with wiki-links and graph visualizations. Triggered by graphify my knowledge, obsidian memory, unified memory, save to memory, remember this, knowledge graph, memory vault, prospective memory, memory search, consolidate memory, semantic search, graph traversal, salience scoring, admission control, MCP server.
executing-hard-tasks
by wsbm393
Use when a task spans multiple steps, files, or unknowns — before planning the order of work, whenever about to report completion or success in any wording, and when picking the next action after a result, failure, or surprise. Also under deadline pressure, or when resuming work built on questionable foundations.
Vector Accuracy Studio Skill
by Panikkos88
Compare against research/test-logo-vectormagic-fill-only.svg and exported local samples.
forter-agentic-readiness-audit
by forter
Audit a website against the Forter Agentic Readiness Guide. Loads the 25 weighted rubrics in audit/, probes the target site (and optional source code), scores each guideline Pass/Partial/Fail/N/A with sub-check granularity, and produces a prioritized fix report. Use when a user asks "score my site against the agentic readiness guide", "audit https://… for agent readiness", or "what do I need to fix to be agent-ready".