[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"category-skills-ja-devtools":3},{"items":4,"total":418,"page":419,"pageSize":420},[5,32,49,66,83,100,117,134,150,167,184,200,217,234,251,268,285,302,319,334,351,367,384,401],{"slug":6,"name":7,"title":7,"skillCategorySlug":8,"summary":9,"description":10,"skillCategoryName":11,"sourceUrl":12,"downloadUrl":13,"cliCommand":14,"authorName":-1,"version":-1,"license":-1,"stars":15,"trendScore":16,"qualityScore":16,"recommendedTools":17,"recommendedToolNames":17,"supportedClients":18,"clients":21,"tags":29,"installHint":14,"useCases":30,"updatedAt":31},"bradautomates-claude-video","bradautomates\u002Fclaude-video","devtools","Give Claude the ability to watch any video. \u002Fwatch downloads, extracts frames, transcribes, hands it all to Claude.","Claude Code (recommended — auto-updates via marketplace):\n\nCodex, Cursor, Copilot, Gemini CLI, or any of 50+ Agent Skills hosts:\n\n(-g installs globally for your user, available across all projects. Drop it to scope per-project.)\n\nMore install options (claude.ai web, manual) in the Install section below.\n\nZero config to start — yt-dlp and ffmpeg install on first run via brew on macOS (Linux\u002FWindows print exact commands). Captions cover most public videos for free. Whisper API key is only needed when a video has no captions.\n\nClaude can read a webpage, run a script, browse a repo. What it can't do, out of the box, is watch a video. You paste a YouTube link and it has to either guess from the title or pull a transcript that's missing 90% of what's on screen.","Developer tools","https:\u002F\u002Fgithub.com\u002Fbradautomates\u002Fclaude-video","https:\u002F\u002Fgithub.com\u002Fbradautomates\u002Fclaude-video\u002Farchive\u002FHEAD.zip","npx skillfish add bradautomates\u002Fclaude-video",4752,99,[],[19,20],"claude-desktop","cursor",[22,26],{"slug":19,"name":23,"summary":24,"count":25},"Claude Desktop","ローカル MCP 設定に対応するデスクトップクライアント。",0,{"slug":20,"name":27,"summary":28,"count":25},"Cursor","開発者向け MCP サーバーとよく使われる AI コードエディタ。",[8],[],"2026-08-30T08:29:27.202887",{"slug":33,"name":34,"title":34,"skillCategorySlug":8,"summary":35,"description":36,"skillCategoryName":11,"sourceUrl":37,"downloadUrl":38,"cliCommand":39,"authorName":-1,"version":-1,"license":-1,"stars":40,"trendScore":16,"qualityScore":16,"recommendedTools":41,"recommendedToolNames":41,"supportedClients":42,"clients":43,"tags":46,"installHint":39,"useCases":47,"updatedAt":48},"shareai-lab-kode-cli","shareai-lab\u002Fkode-cli","Kode CLI — Design for post-human workflows. One unit agent for every human & computer task.",": npm + optionalDependencies distribution (all platforms). Kode prefers the per-platform native binary package (@shareai-lab\u002Fkode-bin-*) with Node.js as a fallback; standalone binaries are also published on GitHub Releases. See docs\u002Fbinary-distribution.md.\n\nKode supports the AGENTS.md standard: a simple, open format for guiding coding agents, used by 60k+ open-source projects.\n\n- ✅ - Native support for the OpenAI-initiated standard format - ✅ - Reads .claude directories and CLAUDE.md when present (see docs\u002Fcompatibility.md) - ✅ - Advanced agent delegation and task orchestration - ✅ - Works with 20+ AI models and providers\n\nUse # Your documentation request to generate and maintain your AGENTS.md file automatically, while preserving compatibility with existing .claude workflows.\n\n- Kode reads project instructions by walking from the Git repo root → current working directory. - In each directory, it prefers AGENTS.override.md over AGENTS.md (at most one file per directory).","https:\u002F\u002Fgithub.com\u002Fshareai-lab\u002Fkode-cli","https:\u002F\u002Fgithub.com\u002Fshareai-lab\u002Fkode-cli\u002Farchive\u002FHEAD.zip","npx skillfish add shareai-lab\u002Fkode-cli",5162,[],[19,20],[44,45],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:30:15.086216",{"slug":50,"name":51,"title":51,"skillCategorySlug":8,"summary":52,"description":53,"skillCategoryName":11,"sourceUrl":54,"downloadUrl":55,"cliCommand":56,"authorName":-1,"version":-1,"license":-1,"stars":57,"trendScore":16,"qualityScore":16,"recommendedTools":58,"recommendedToolNames":58,"supportedClients":59,"clients":60,"tags":63,"installHint":56,"useCases":64,"updatedAt":65},"wanshuiyin-auto-claude-code-research-in-sleep","wanshuiyin\u002Fauto-claude-code-research-in-sleep","ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation.","💡 *Use ARIS as a skill-based workflow in Claude Code \u002F Codex CLI \u002F Cursor \u002F Trae \u002F Antigravity \u002F GitHub Copilot CLI \u002F OpenClaw, or get the full experience with the standalone CLI — enjoy any way you like!*\n\n🌱 ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.\n\n🤖 Read AGENT_GUIDE.md instead — structured for LLM consumption, not human browsing.\n\n🛡️ It catalogs — and checks a submission for them , producing a deterministic, reviewer-ready integrity report. *Self-consistency + fabrication forensics, an AI-text detector.*\n\nThe field has put up with unreliable autoresearch long enough — Anti-Autoresearch is the read that finally catches it.\n\n🎬 — hand it a rough story and get back a movie told in still frames, checked scene by scene (the reference run has 19 scenes).","https:\u002F\u002Fgithub.com\u002Fwanshuiyin\u002Fauto-claude-code-research-in-sleep","https:\u002F\u002Fgithub.com\u002Fwanshuiyin\u002Fauto-claude-code-research-in-sleep\u002Farchive\u002FHEAD.zip","npx skillfish add wanshuiyin\u002Fauto-claude-code-research-in-sleep",13028,[],[19,20],[61,62],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:28:16.672532",{"slug":67,"name":68,"title":68,"skillCategorySlug":8,"summary":69,"description":70,"skillCategoryName":11,"sourceUrl":71,"downloadUrl":72,"cliCommand":73,"authorName":-1,"version":-1,"license":-1,"stars":74,"trendScore":16,"qualityScore":16,"recommendedTools":75,"recommendedToolNames":75,"supportedClients":76,"clients":77,"tags":80,"installHint":73,"useCases":81,"updatedAt":82},"nicobailon-visual-explainer","nicobailon\u002Fvisual-explainer","Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps","Ask your agent to explain a system architecture, review a diff, or compare requirements against a plan. Instead of ASCII art and box-drawing tables, it generates a self-contained HTML page and opens it in your browser.\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F55ebc81b-8732-40f6-a4b1-7c3781aa96ec\n\nEvery coding agent defaults to ASCII art when you ask for a diagram. Box-drawing characters, monospace alignment hacks, text arrows. It works for trivial cases, but anything beyond a 3-box flowchart turns into an unreadable mess.\n\nTables are worse. Ask the agent to compare 15 requirements against a plan and you get a wall of pipes and dashes that wraps and breaks in the terminal. The data is there but it's painful to read.\n\nThis skill fixes that. Real typography, dark\u002Flight themes, interactive Mermaid diagrams with zoom and pan. No build step, no dependencies beyond a browser.\n\nNote: Claude Code plugins namespace commands as \u002Fvisual-explainer:command-name.","https:\u002F\u002Fgithub.com\u002Fnicobailon\u002Fvisual-explainer","https:\u002F\u002Fgithub.com\u002Fnicobailon\u002Fvisual-explainer\u002Farchive\u002FHEAD.zip","npx skillfish add nicobailon\u002Fvisual-explainer",9179,[],[19,20],[78,79],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:28:24.930973",{"slug":84,"name":85,"title":85,"skillCategorySlug":8,"summary":86,"description":87,"skillCategoryName":11,"sourceUrl":88,"downloadUrl":89,"cliCommand":90,"authorName":-1,"version":-1,"license":-1,"stars":91,"trendScore":16,"qualityScore":16,"recommendedTools":92,"recommendedToolNames":92,"supportedClients":93,"clients":94,"tags":97,"installHint":90,"useCases":98,"updatedAt":99},"teng-lin-notebooklm-py","teng-lin\u002Fnotebooklm-py","Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents...","Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw.\n\n: https:\u002F\u002Fgithub.com\u002Fteng-lin\u002Fnotebooklm-py\n\nThis library uses that can change without notice. - - This is a community project - - Google can change internal endpoints anytime - - Heavy usage may be throttled Best for prototypes, research, and personal projects. See Troubleshooting for debugging tips.\n\n🤖 - Integrate NotebookLM into Claude Code, Codex, and other LLM agents. Ships with a root NotebookLM skill for GitHub and npx skills add discovery, local notebooklm skill install support for Claude Code and .agents skill directories, and repo-level Codex guidance in AGENTS.md.\n\n📚 - Bulk-import sources (URLs, PDFs, YouTube, Google Drive), run web\u002FDrive research queries with auto-import, and extract insights programmatically. Build repeatable research pipelines.","https:\u002F\u002Fgithub.com\u002Fteng-lin\u002Fnotebooklm-py","https:\u002F\u002Fgithub.com\u002Fteng-lin\u002Fnotebooklm-py\u002Farchive\u002FHEAD.zip","npx skillfish add teng-lin\u002Fnotebooklm-py",17229,[],[19,20],[95,96],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T04:42:39.845366",{"slug":101,"name":102,"title":102,"skillCategorySlug":8,"summary":103,"description":104,"skillCategoryName":11,"sourceUrl":105,"downloadUrl":106,"cliCommand":107,"authorName":-1,"version":-1,"license":-1,"stars":108,"trendScore":16,"qualityScore":16,"recommendedTools":109,"recommendedToolNames":109,"supportedClients":110,"clients":111,"tags":114,"installHint":107,"useCases":115,"updatedAt":116},"twostraws-swiftui-agent-skill","twostraws\u002Fswiftui-agent-skill","SwiftUI agent skill for Claude Code, Codex, and other AI tools.","SwiftUI Agent Skill for AI Coding Assistants\n\nAn agent skill that helps AI coding assistants write smarter, simpler, and more modern SwiftUI, including guidance on API usage, design, performance, and accessibility. Covers navigation, layout, animations, state management, VoiceOver, deprecated API, and more, targeting the mistakes LLMs actually make.\n\n- SwiftData Pro - Swift Concurrency Pro - Swift Testing Pro\n\nFind more agent skills for Swift and Apple platform development at Swift Agent Skills.\n\nThe skill builds upon my existing AGENTS.md file, meaning that you can bring years of knowledge and practical experience into your coding agent of choice in just a few minutes. It uses the Agent Skills format, so it works smoothly with Claude Code, Codex, Gemini, Cursor, and more.\n\nYou can install this skill into Claude Code, Codex, Gemini, Cursor, and more by using npx:\n\nIf you get the error npx: command not found, it means you don’t currently have Node installed.","https:\u002F\u002Fgithub.com\u002Ftwostraws\u002Fswiftui-agent-skill","https:\u002F\u002Fgithub.com\u002Ftwostraws\u002Fswiftui-agent-skill\u002Farchive\u002FHEAD.zip","npx skillfish add twostraws\u002Fswiftui-agent-skill",4275,[],[19,20],[112,113],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:29:52.73205",{"slug":118,"name":119,"title":119,"skillCategorySlug":8,"summary":120,"description":121,"skillCategoryName":11,"sourceUrl":122,"downloadUrl":123,"cliCommand":124,"authorName":-1,"version":-1,"license":-1,"stars":125,"trendScore":16,"qualityScore":16,"recommendedTools":126,"recommendedToolNames":126,"supportedClients":127,"clients":128,"tags":131,"installHint":124,"useCases":132,"updatedAt":133},"charmbracelet-crush","charmbracelet\u002Fcrush","Glamourous agentic coding for all 💘","Your new coding bestie, now available in your favourite terminal. Your tools, your code, and your workflows, wired into your LLM of choice. 终端里的编程新搭档， 无缝接入你的工具、代码与工作流，全面兼容主流 LLM 模型。\n\n- choose from a wide range of LLMs or add your own via OpenAI- or Anthropic-compatible APIs - switch LLMs mid-session while preserving context - maintain multiple work sessions and contexts per project - Crush uses LSPs for additional context, just like you do - add capabilities via MCPs (http, stdio, and sse) - first-class support in every terminal on macOS, Linux, Windows (PowerShell and WSL), Android, FreeBSD, OpenBSD, and NetBSD - built on the Charm ecosystem, powering 25k+ applications, from leading open source projects to business-critical infrastructure\n\nCrush is available via the official Charm NUR in nur.repos.charmbracelet.crush, which is the most up-to-date way to get Crush in Nix.\n\nYou can also try out Crush via the NUR with nix-shell:\n\nCrush provides NixOS and Home Manager modules via NUR.","https:\u002F\u002Fgithub.com\u002Fcharmbracelet\u002Fcrush","https:\u002F\u002Fgithub.com\u002Fcharmbracelet\u002Fcrush\u002Farchive\u002FHEAD.zip","npx skillfish add charmbracelet\u002Fcrush",26101,[],[19,20],[129,130],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T04:42:19.392736",{"slug":135,"name":136,"title":136,"skillCategorySlug":8,"summary":137,"description":137,"skillCategoryName":11,"sourceUrl":138,"downloadUrl":139,"cliCommand":140,"authorName":-1,"version":-1,"license":-1,"stars":141,"trendScore":16,"qualityScore":16,"recommendedTools":142,"recommendedToolNames":142,"supportedClients":143,"clients":144,"tags":147,"installHint":140,"useCases":148,"updatedAt":149},"superagent-ai-grok-cli","superagent-ai\u002Fgrok-cli","This project is community-built, open-source, and \"Grok\" is a trademark of xAI Corp. This tool uses the publicly available Grok API.","https:\u002F\u002Fgithub.com\u002Fsuperagent-ai\u002Fgrok-cli","https:\u002F\u002Fgithub.com\u002Fsuperagent-ai\u002Fgrok-cli\u002Farchive\u002FHEAD.zip","npx skillfish add superagent-ai\u002Fgrok-cli",3262,[],[19,20],[145,146],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-07-14T01:53:52.888712",{"slug":151,"name":152,"title":152,"skillCategorySlug":8,"summary":153,"description":154,"skillCategoryName":11,"sourceUrl":155,"downloadUrl":156,"cliCommand":157,"authorName":-1,"version":-1,"license":-1,"stars":158,"trendScore":16,"qualityScore":16,"recommendedTools":159,"recommendedToolNames":159,"supportedClients":160,"clients":161,"tags":164,"installHint":157,"useCases":165,"updatedAt":166},"mistralai-mistral-vibe","mistralai\u002Fmistral-vibe","Minimal CLI coding agent by Mistral","Mistral Vibe is a command-line coding assistant powered by Mistral's models. It provides a conversational interface to your codebase, allowing you to use natural language to explore, modify, and interact with your projects through a powerful set of tools.\n\nMistral Vibe works on Windows, but we officially support and target UNIX environments.\n\n- : A conversational AI agent that understands your requests and breaks down complex tasks. - : A suite of tools for file manipulation, code searching, version control, and command execution, right from the chat prompt. - Read, write, and patch files (read, write_file, edit). - Execute shell commands (bash), with an experimental managed PTY mode for polling and stdin helpers. - Recursively search code with grep (with ripgrep support). - Manage a todo list to track the agent's work. - Ask interactive questions to gather user input (ask_user_question). - Delegate tasks to subagents for parallel work (task).","https:\u002F\u002Fgithub.com\u002Fmistralai\u002Fmistral-vibe","https:\u002F\u002Fgithub.com\u002Fmistralai\u002Fmistral-vibe\u002Farchive\u002FHEAD.zip","npx skillfish add mistralai\u002Fmistral-vibe",4653,[],[19,20],[162,163],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:31:21.074788",{"slug":168,"name":169,"title":169,"skillCategorySlug":8,"summary":170,"description":171,"skillCategoryName":11,"sourceUrl":172,"downloadUrl":173,"cliCommand":174,"authorName":-1,"version":-1,"license":-1,"stars":175,"trendScore":16,"qualityScore":16,"recommendedTools":176,"recommendedToolNames":176,"supportedClients":177,"clients":178,"tags":181,"installHint":174,"useCases":182,"updatedAt":183},"eugeniughelbur-obsidian-second-brain","eugeniughelbur\u002Fobsidian-second-brain","Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and people every session.","An evolution of Karpathy's LLM Wiki pattern : a vault that rewrites itself. Every source updates existing pages instead of just appending new ones. Contradictions reconcile automatically. Your vault compounds while you sleep. Powered by OKM - Open Knowledge Metabolism : every stored fact is timeless, dated, or a pointer - so your knowledge base never fills with facts that used to be true. 44 commands · auto-synthesis · thinking tools that argue with you live research from X, the web, and YouTube · 4 scheduled agents · 4 role presets write-time AI-first validator · \u002Fcreate-command interview flow · multilingual trigger schema Demos · OKM · See it in action · All commands · Install · Presets · Discussions\n\nOne \u002Fobsidian-save - five cross-linked notes. Real footage, synthetic vault. More demos →\n\nv0.","https:\u002F\u002Fgithub.com\u002Feugeniughelbur\u002Fobsidian-second-brain","https:\u002F\u002Fgithub.com\u002Feugeniughelbur\u002Fobsidian-second-brain\u002Farchive\u002FHEAD.zip","npx skillfish add eugeniughelbur\u002Fobsidian-second-brain",3195,[],[19,20],[179,180],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:31:33.296796",{"slug":185,"name":186,"title":186,"skillCategorySlug":8,"summary":187,"description":187,"skillCategoryName":11,"sourceUrl":188,"downloadUrl":189,"cliCommand":190,"authorName":-1,"version":-1,"license":-1,"stars":191,"trendScore":16,"qualityScore":16,"recommendedTools":192,"recommendedToolNames":192,"supportedClients":193,"clients":194,"tags":197,"installHint":190,"useCases":198,"updatedAt":199},"alvinunreal-oh-my-opencode-slim","alvinunreal\u002Foh-my-opencode-slim","Seven divine beings emerged from the dawn of code, each an immortal master of their craft, awaiting your command to forge order from chaos and build what was once thought impossible.","https:\u002F\u002Fgithub.com\u002Falvinunreal\u002Foh-my-opencode-slim","https:\u002F\u002Fgithub.com\u002Falvinunreal\u002Foh-my-opencode-slim\u002Farchive\u002FHEAD.zip","npx skillfish add alvinunreal\u002Foh-my-opencode-slim",7678,[],[19,20],[195,196],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-04T06:11:44.710987",{"slug":201,"name":202,"title":202,"skillCategorySlug":8,"summary":203,"description":204,"skillCategoryName":11,"sourceUrl":205,"downloadUrl":206,"cliCommand":207,"authorName":-1,"version":-1,"license":-1,"stars":208,"trendScore":16,"qualityScore":16,"recommendedTools":209,"recommendedToolNames":209,"supportedClients":210,"clients":211,"tags":214,"installHint":207,"useCases":215,"updatedAt":216},"vectifyai-openkb","vectifyai\u002Fopenkb","OpenKB: Open LLM Knowledge Base","Scale to long documents  •  Reasoning-based retrieval  •  Native multi-modality  •  No Vector DB\n\n- Google Open Knowledge Format (OKF): Wiki pages follow the Google OKF specification for knowledge sharing. - Entity Pages: People, orgs, places, and products as dedicated wiki pages, auto-extracted and kept in sync.\n\nis an open-source system (in CLI) that compiles raw documents into a structured, interlinked wiki-style knowledge base using LLMs, powered by 's vectorless, reasoning-based retrieval for long documents.\n\nThe idea is based on a concept described by Andrej Karpathy: LLMs generate summaries, concept pages, and cross-references, all maintained automatically. Knowledge compounds over time instead of being re-derived on every query.\n\nTraditional RAG rediscovers knowledge from scratch on every query. Nothing accumulates. OpenKB compiles knowledge once into a persistent wiki, then keeps it current.","https:\u002F\u002Fgithub.com\u002Fvectifyai\u002Fopenkb","https:\u002F\u002Fgithub.com\u002Fvectifyai\u002Fopenkb\u002Farchive\u002FHEAD.zip","npx skillfish add vectifyai\u002Fopenkb",2936,[],[19,20],[212,213],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:30:17.310966",{"slug":218,"name":219,"title":219,"skillCategorySlug":8,"summary":220,"description":221,"skillCategoryName":11,"sourceUrl":222,"downloadUrl":223,"cliCommand":224,"authorName":-1,"version":-1,"license":-1,"stars":225,"trendScore":16,"qualityScore":16,"recommendedTools":226,"recommendedToolNames":226,"supportedClients":227,"clients":228,"tags":231,"installHint":224,"useCases":232,"updatedAt":233},"composio-community-awesome-codex-skills","composio-community\u002Fawesome-codex-skills","A curated list of practical Codex skills for automating workflows across the Codex CLI and API.","A curated list of practical Codex skills for automating workflows across the Codex CLI and API.\n\nCodex can send emails, create issues, post to Slack, and take actions across 1000+ apps. See how →\n\nThe installer fetches the skill and places it in $CODEX_HOME\u002Fskills\u002F . Restart Codex to pick up new skills.\n\n1. Copy the desired skill folder (e.g., .\u002Fspreadsheet-formula-helper) into $CODEX_HOME\u002Fskills\u002F (defaults to ~\u002F.codex\u002Fskills\u002F). 2. Restart Codex so it loads the new metadata. 3. In your next session, describe the task or mention the skill name; Codex will trigger matching skills based on their description frontmatter.\n\nCodex skills are modular instruction bundles that tell Codex how to execute a task the way you want it done. Each skill lives in its own folder with a SKILL.md that includes metadata (name + description) and step-by-step guidance. Codex reads the metadata to decide when to trigger a skill and loads the body only after it fires, keeping context lean.","https:\u002F\u002Fgithub.com\u002Fcomposio-community\u002Fawesome-codex-skills","https:\u002F\u002Fgithub.com\u002Fcomposio-community\u002Fawesome-codex-skills\u002Farchive\u002FHEAD.zip","npx skillfish add composio-community\u002Fawesome-codex-skills",14973,[],[19,20],[229,230],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T04:42:14.204408",{"slug":235,"name":236,"title":236,"skillCategorySlug":8,"summary":237,"description":238,"skillCategoryName":11,"sourceUrl":239,"downloadUrl":240,"cliCommand":241,"authorName":-1,"version":-1,"license":-1,"stars":242,"trendScore":16,"qualityScore":16,"recommendedTools":243,"recommendedToolNames":243,"supportedClients":244,"clients":245,"tags":248,"installHint":241,"useCases":249,"updatedAt":250},"ogulcancelik-herdr","ogulcancelik\u002Fherdr","the runtime your coding agents live on","herdr.dev · install · quick start · supported agents · docs · socket api · sponsor\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F043ec09f-4bdd-41d5-aee0-8fda6b83e267\n\nrun your agents where they already run; your machine, a server, anywhere you can ssh. each one gets its own real terminal, not an app's imitation of one, so even full-screen TUIs render right. click, drag, and split panes into workspaces and tabs, and watch each agent go blocked, working, done. close the laptop and nothing dies; reattach from another terminal, or from your phone over ssh. one local rust binary, not an app: no gui, no electron, no mac-only wrapper, no account, no telemetry. (if you've used tmux: it's that, rebuilt for agents.)\n\n- you see each agent's own screen, not an app's imitation of one, so even full-screen TUIs render right. - the sidebar rolls every agent up to 🔴 blocked, 🟡 working, 🔵 done, or 🟢 idle, so you always know who needs you. zero config, no hooks required.","https:\u002F\u002Fgithub.com\u002Fogulcancelik\u002Fherdr","https:\u002F\u002Fgithub.com\u002Fogulcancelik\u002Fherdr\u002Farchive\u002FHEAD.zip","npx skillfish add ogulcancelik\u002Fherdr",13223,[],[19,20],[246,247],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:29:17.012248",{"slug":252,"name":253,"title":253,"skillCategorySlug":8,"summary":254,"description":255,"skillCategoryName":11,"sourceUrl":256,"downloadUrl":257,"cliCommand":258,"authorName":-1,"version":-1,"license":-1,"stars":259,"trendScore":16,"qualityScore":16,"recommendedTools":260,"recommendedToolNames":260,"supportedClients":261,"clients":262,"tags":265,"installHint":258,"useCases":266,"updatedAt":267},"diegosouzapw-awesome-omni-skill","diegosouzapw\u002Fawesome-omni-skill","Repositorio Publico, agregador de skills","The largest curated collection of SKILL.md-compatible agent skills for Claude Code, Gemini CLI, Cursor, Copilot, and more. Auto-synced from OmniSkill Registry.\n\nVisit the OmniSkill Registry for search, filters, and one-click install commands.\n\nSee CATALOG.md for the complete alphabetical listing of all 10,000 skills.\n\nThis repo is automatically synced from OmniSkill Registry every 6 hours via GitHub Actions.\n\nEach skill directory contains: - SKILL.md — The original skill file from the source repository - metadata.json — Rich metadata including quality score, stars, install commands, and source links\n\nThis repository is an . All skills are sourced from their original repositories. Links to source repos are preserved in each metadata.json. All credit goes to the original authors.\n\nIndividual skills retain their original licenses. This aggregation layer is MIT licensed.","https:\u002F\u002Fgithub.com\u002Fdiegosouzapw\u002Fawesome-omni-skill","https:\u002F\u002Fgithub.com\u002Fdiegosouzapw\u002Fawesome-omni-skill\u002Farchive\u002FHEAD.zip","npx skillfish add diegosouzapw\u002Fawesome-omni-skill",53,[],[19,20],[263,264],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T04:41:46.245546",{"slug":269,"name":270,"title":270,"skillCategorySlug":8,"summary":271,"description":272,"skillCategoryName":11,"sourceUrl":273,"downloadUrl":274,"cliCommand":275,"authorName":-1,"version":-1,"license":-1,"stars":276,"trendScore":16,"qualityScore":16,"recommendedTools":277,"recommendedToolNames":277,"supportedClients":278,"clients":279,"tags":282,"installHint":275,"useCases":283,"updatedAt":284},"rich-harris-degit","rich-harris\u002Fdegit","Straightforward project scaffolding","makes copies of git repositories. When you run degit some-user\u002Fsome-repo, it will find the latest commit on https:\u002F\u002Fgithub.com\u002Fsome-user\u002Fsome-repo and download the associated tar file to the platform-appropriate cache directory if it doesn't already exist locally. On Linux\u002FBSD this follows XDG_CACHE_HOME when set and otherwise uses ~\u002F.cache\u002Fdegit; on macOS it uses ~\u002FLibrary\u002FCaches\u002Fdegit; on Windows it uses %LOCALAPPDATA%\\degit. (This is much quicker than using git clone, because you're not downloading the entire git history.) degit resolves refs through an internal git backend, downloads tar snapshots by default, and falls back to SSH cloning when tarball fetches or extraction fail. Public HTTPS sources do not need a local git binary on your PATH, but SSH\u002Fprivate repositories still do.\n\n- Node.js or later (see engines in package.json) - Bun when developing this repository (see packageManager in package.","https:\u002F\u002Fgithub.com\u002Frich-harris\u002Fdegit","https:\u002F\u002Fgithub.com\u002Frich-harris\u002Fdegit\u002Farchive\u002FHEAD.zip","npx skillfish add rich-harris\u002Fdegit",7907,[],[19,20],[280,281],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:30:46.274199",{"slug":286,"name":287,"title":287,"skillCategorySlug":8,"summary":288,"description":289,"skillCategoryName":11,"sourceUrl":290,"downloadUrl":291,"cliCommand":292,"authorName":-1,"version":-1,"license":-1,"stars":293,"trendScore":16,"qualityScore":16,"recommendedTools":294,"recommendedToolNames":294,"supportedClients":295,"clients":296,"tags":299,"installHint":292,"useCases":300,"updatedAt":301},"rohitg00-ai-engineering-from-scratch","rohitg00\u002Fai-engineering-from-scratch","Learn it. Build it. Ship it for others.","This curriculum closes that gap. 503 lessons. 20 phases. ~320 hours. Python, TypeScript, Rust, Julia. Every lesson ships a reusable artifact: a prompt, a skill, an agent, an MCP server. Free, open source, MIT. You don't just learn AI. You build it. End-to-end. By hand.\n\n150,639 readers  ·  241,669 page views in the last 30 days  ·  as of 2026-06-07\n\nMost AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it.\n\nThis curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop.","https:\u002F\u002Fgithub.com\u002Frohitg00\u002Fai-engineering-from-scratch","https:\u002F\u002Fgithub.com\u002Frohitg00\u002Fai-engineering-from-scratch\u002Farchive\u002FHEAD.zip","npx skillfish add rohitg00\u002Fai-engineering-from-scratch",37409,[],[19,20],[297,298],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T04:42:34.08289",{"slug":303,"name":304,"title":304,"skillCategorySlug":8,"summary":305,"description":306,"skillCategoryName":11,"sourceUrl":307,"downloadUrl":308,"cliCommand":309,"authorName":-1,"version":-1,"license":-1,"stars":310,"trendScore":16,"qualityScore":16,"recommendedTools":311,"recommendedToolNames":311,"supportedClients":312,"clients":313,"tags":316,"installHint":309,"useCases":317,"updatedAt":318},"avdlee-swiftui-agent-skill","avdlee\u002Fswiftui-agent-skill","Add expert SwiftUI Best Practices guidance to your AI coding tool (Agent Skills open format).","Expert guidance for any AI coding tool that supports the Agent Skills open format — SwiftUI state management, view composition, performance, and iOS 26+ Liquid Glass adoption.\n\nThis repository distills practical SwiftUI best practices into actionable, concise references for agents and code review workflows.\n\n- Teams adopting modern SwiftUI APIs who want quick, correct defaults - Developers reviewing or refactoring SwiftUI views and data flow - Anyone shipping performant lists, scrolling, sheets, and navigation in SwiftUI\n\n- Swift Concurrency Expert - Core Data Expert - Swift Testing Expert - Xcode Build Optimization Agent Skill - Xcode Simulator AI Control Agent Skill\n\nInstall this skill with a single command:\n\nFor more information, visit the skills.sh platform page.","https:\u002F\u002Fgithub.com\u002Favdlee\u002Fswiftui-agent-skill","https:\u002F\u002Fgithub.com\u002Favdlee\u002Fswiftui-agent-skill\u002Farchive\u002FHEAD.zip","npx skillfish add avdlee\u002Fswiftui-agent-skill",3189,[],[19,20],[314,315],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:27:59.920097",{"slug":320,"name":321,"title":321,"skillCategorySlug":8,"summary":220,"description":220,"skillCategoryName":11,"sourceUrl":322,"downloadUrl":323,"cliCommand":324,"authorName":-1,"version":-1,"license":-1,"stars":325,"trendScore":16,"qualityScore":16,"recommendedTools":326,"recommendedToolNames":326,"supportedClients":327,"clients":328,"tags":331,"installHint":324,"useCases":332,"updatedAt":333},"composiohq-awesome-codex-skills","composiohq\u002Fawesome-codex-skills","https:\u002F\u002Fgithub.com\u002Fcomposiohq\u002Fawesome-codex-skills","https:\u002F\u002Fgithub.com\u002Fcomposiohq\u002Fawesome-codex-skills\u002Farchive\u002FHEAD.zip","npx skillfish add composiohq\u002Fawesome-codex-skills",14453,[],[19,20],[329,330],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T01:41:09.707942",{"slug":335,"name":336,"title":336,"skillCategorySlug":8,"summary":337,"description":338,"skillCategoryName":11,"sourceUrl":339,"downloadUrl":340,"cliCommand":341,"authorName":-1,"version":-1,"license":-1,"stars":342,"trendScore":16,"qualityScore":16,"recommendedTools":343,"recommendedToolNames":343,"supportedClients":344,"clients":345,"tags":348,"installHint":341,"useCases":349,"updatedAt":350},"google-research-timesfm","google-research\u002Ftimesfm","TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.","TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.\n\n* Paper: A decoder-only foundation model for time-series forecasting, ICML 2024. * All checkpoints: TimesFM Hugging Face Collection. * Google Research blog. * TimesFM in Google 1P Products: * BigQuery ML: Enterprise level SQL queries for scalability and reliability. * Google Sheets: For your daily spreadsheet. * Vertex Model Garden: Dockerized endpoint for agentic calling.\n\nThis open version is not an officially supported Google product.\n\n- 1.0 and 2.0: relevant code archived in the sub directory v1. You can pip install timesfm==1.3.0 to install an older version of this package to load them.\n\nUpdated PyPI to timesfm=2.0.2. See Install.\n\nAdded fine-tuning example using HuggingFace Transformers + PEFT (LoRA) — see timesfm-forecasting\u002Fexamples\u002Ffinetuning\u002F. Also added unit tests (tests\u002F) and incorporated several community fixes.","https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Ftimesfm","https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Ftimesfm\u002Farchive\u002FHEAD.zip","npx skillfish add google-research\u002Ftimesfm",26628,[],[19,20],[346,347],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:29:26.003525",{"slug":352,"name":353,"title":353,"skillCategorySlug":8,"summary":354,"description":354,"skillCategoryName":11,"sourceUrl":355,"downloadUrl":356,"cliCommand":357,"authorName":-1,"version":-1,"license":-1,"stars":358,"trendScore":16,"qualityScore":16,"recommendedTools":359,"recommendedToolNames":359,"supportedClients":360,"clients":361,"tags":364,"installHint":357,"useCases":365,"updatedAt":366},"kkkkhazix-khazix-skills","kkkkhazix\u002Fkhazix-skills","I am khazix, a digital life form, founder of Xushi Media, striving to share some interesting AI insights, and may we always remain curious about the world.","https:\u002F\u002Fgithub.com\u002Fkkkkhazix\u002Fkhazix-skills","https:\u002F\u002Fgithub.com\u002Fkkkkhazix\u002Fkhazix-skills\u002Farchive\u002FHEAD.zip","npx skillfish add kkkkhazix\u002Fkhazix-skills",16318,[],[19,20],[362,363],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T01:38:27.368515",{"slug":368,"name":369,"title":369,"skillCategorySlug":8,"summary":370,"description":371,"skillCategoryName":11,"sourceUrl":372,"downloadUrl":373,"cliCommand":374,"authorName":-1,"version":-1,"license":-1,"stars":375,"trendScore":16,"qualityScore":16,"recommendedTools":376,"recommendedToolNames":376,"supportedClients":377,"clients":378,"tags":381,"installHint":374,"useCases":382,"updatedAt":383},"run-llama-liteparse","run-llama\u002Fliteparse","A fast, helpful, and open-source document parser","Looking for LiteParse V1? Follow this link to the old code\n\nLiteParse is a standalone OSS PDF parsing tool focused exclusively on parsing. It provides high-quality spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. Everything runs locally on your machine.\n\nFor complex documents (dense tables, multi-column layouts, charts, handwritten text, or scanned PDFs), you'll get significantly better results with LlamaParse, our cloud-based document parser built for production document pipelines. LlamaParse handles the hard stuff so your models see clean, structured data and markdown.","https:\u002F\u002Fgithub.com\u002Frun-llama\u002Fliteparse","https:\u002F\u002Fgithub.com\u002Frun-llama\u002Fliteparse\u002Farchive\u002FHEAD.zip","npx skillfish add run-llama\u002Fliteparse",11474,[],[19,20],[379,380],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:28:40.625271",{"slug":385,"name":386,"title":386,"skillCategorySlug":8,"summary":387,"description":388,"skillCategoryName":11,"sourceUrl":389,"downloadUrl":390,"cliCommand":391,"authorName":-1,"version":-1,"license":-1,"stars":392,"trendScore":16,"qualityScore":16,"recommendedTools":393,"recommendedToolNames":393,"supportedClients":394,"clients":395,"tags":398,"installHint":391,"useCases":399,"updatedAt":400},"kyegomez-swarms","kyegomez\u002Fswarms","The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https:\u002F\u002Fswarms.ai","Swarms Website   •   Documentation   •   Swarms Marketplace\n\nSwarms, The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework\n\nSwarms is the most reliable, scalable, and adaptive multi-agent orchestration framework available today. We provide a comprehensive suite of production-ready, prebuilt multi-agent architectures, including sequential, concurrent, and hierarchical systems. Additionally, Swarms offers backward compatibility with leading agent frameworks and interoperability with protocols such as MCP, x402, skills, and much more.\n\nuv is a fast Python package installer and resolver, written in Rust.\n\nLearn more about the environment configuration here\n\nAn is the fundamental building block of a swarm—an autonomous entity powered by an LLM + Tools + Memory.","https:\u002F\u002Fgithub.com\u002Fkyegomez\u002Fswarms","https:\u002F\u002Fgithub.com\u002Fkyegomez\u002Fswarms\u002Farchive\u002FHEAD.zip","npx skillfish add kyegomez\u002Fswarms",6944,[],[19,20],[396,397],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:30:51.542106",{"slug":402,"name":403,"title":403,"skillCategorySlug":8,"summary":404,"description":405,"skillCategoryName":11,"sourceUrl":406,"downloadUrl":407,"cliCommand":408,"authorName":-1,"version":-1,"license":-1,"stars":409,"trendScore":16,"qualityScore":16,"recommendedTools":410,"recommendedToolNames":410,"supportedClients":411,"clients":412,"tags":415,"installHint":408,"useCases":416,"updatedAt":417},"ai-boost-awesome-harness-engineering","ai-boost\u002Fawesome-harness-engineering","Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.","Awesome Harness Engineering Curated resources, patterns, and templates for building reliable AI agent harnesses. Deutsch | English | Español | Français | 日本語 | 한국어 | Português | Русский | 中文\n\nis the discipline of designing the scaffolding — context delivery, tool interfaces, planning artifacts, verification loops, memory systems, and sandboxes — that surrounds an AI agent and determines whether it succeeds or fails on real tasks.\n\nThis list focuses on the harness, not the model. Every component here exists because the model can't do it alone — and the best harnesses are designed knowing those components will become unnecessary as models improve.\n\nCanonical essays that define what harness engineering is and why it matters.\n\n- Harness Engineering — OpenAI's framing of harness engineering as a discipline: how to design the scaffolding that lets Codex and similar agents operate reliably in an agent-first world.","https:\u002F\u002Fgithub.com\u002Fai-boost\u002Fawesome-harness-engineering","https:\u002F\u002Fgithub.com\u002Fai-boost\u002Fawesome-harness-engineering\u002Farchive\u002FHEAD.zip","npx skillfish add ai-boost\u002Fawesome-harness-engineering",3067,[],[19,20],[413,414],{"slug":19,"name":23,"summary":24,"count":25},{"slug":20,"name":27,"summary":28,"count":25},[8],[],"2026-08-30T08:30:42.670046",3897,1,24]