[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ED6QBJSWEDWK02SAR4V09G":3,"skill-same:01M7ED6QBJSWEDWK02SAR4V09G":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7ED6QBJSWEDWK02SAR4V09G","attention-span",null,"ADHD-friendly output styles and attention-kind conciseness rules for AI agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, Copilot). Provides Attention-kind, Spartan, and Rundown output styles for scannable, token-efficient agent communication.","sanjeevafk\u002Fagent-skills","sanjeevafk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F230678117?v=4","01M7C540EFY46ETG1NNWKS5X3Q","Sanjeev","01M7C540F366J5C1D587BMKH9Q",0,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: attention-span\ndescription: ADHD-friendly output styles and attention-kind conciseness rules for AI agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, Copilot). Provides Attention-kind, Spartan, and Rundown output styles for scannable, token-efficient agent communication.\nlicense: AGPL-3.0\nmetadata:\n  origin: alexgreensh\u002Fattention-span\n  version: 0.6.0\ntools: Read, Write, Edit, Bash, Grep, Glob\n---\n\n# Attention Span Skill\n\nA collection of ADHD-friendly output styles and conciseness guidelines for AI coding agents that optimize for reader scannability and attention retention without compromising engineering quality.\n\n## When to Activate\n\n- Asking an agent to format responses for maximum scannability and plain-English clarity\n- Configuring or switching agent output styles (`Attention-kind`, `Spartan`, `Rundown`)\n- Reducing token verbosity and eliminating AI fluff\u002Fpreambles in agent responses\n- Setting up global or project-level output style rules across AI agents (Claude Code, Codex, Antigravity CLI, Cursor, Windsurf, Copilot)\n\n## Available Output Styles\n\n| Style | Description | Ideal For |\n|---|---|---|\n| **Attention-kind** | ADHD-friendly, front-loaded answers, heavy bolding, arrow markers (`→`), spaced out blocks | General pair programming, deep focus, preventing wall-of-text fatigue |\n| **Spartan** | Zero-warmth, blunt, imperative, maximum signal-to-noise ratio | Heads-down work, rapid execution, quick technical answers |\n| **Rundown** | Briefing style with TL;DR, status checklist (`✅`\u002F`🟡`\u002F`⬜`), action items tagged with emoji | Standups, status updates, progress reports |\n\n---\n\n## Core Guidelines & Principles\n\n### 1. Attention-Kind Principles\n- **Lead with the bottom line in line 1.** The first sentence contains the direct answer.\n- **Say the least that fully answers.** Eliminate preambles (\"Great question!\", \"Sure thing!\"), restating questions, or closing restatements.\n- **Build for scanning:**\n  - Mark key points with `**→ Lead-in.**` on a new line with blank lines between paragraphs.\n  - **Bold the main takeaway and key terms\u002Fnumbers** so skimming only the bold text yields the complete answer.\n- **Preserve critical details:** Never cut a warning, caveat, exact threshold, or scoped condition to save words.\n- **Depth requests suspend brevity:** If the user asks to \"explain deeply\", \"walk me through it\", or \"give full context\", brevity constraints are suspended for that turn.\n\n### 2. Spartan Principles\n- **Imperative & direct:** Strip all warmth, transitions, and conversational fluff.\n- **Deliverable purity:** When asked for code, a commit message, or a document, return *only* the requested artifact without wrapping text.\n- **One idea per paragraph block.**\n\n### 3. Rundown Principles\n- **Open with `TL;DR:`** carrying the complete summary.\n- **State checklist:** `☑️ Done`, `🟡 In Progress`, `⬜ Not Started`.\n- **Group next choices under `Your move:`** with relevant emoji markers.\n- **Never invent status:** Report only verified facts.\n\n---\n\n## Multi-Agent Configuration\n\n### Claude Code\nOutput styles can be selected via `\u002Fstyle`:\n```bash\n# Global output styles directory\nmkdir -p ~\u002F.claude\u002Foutput-styles ~\u002F.claude\u002Fcommands\ncp output-styles\u002F*.md ~\u002F.claude\u002Foutput-styles\u002F\ncp commands\u002Fstyle.md ~\u002F.claude\u002Fcommands\u002F\n```\nTo set as default in `~\u002F.claude\u002Fsettings.json`:\n```json\n{\n  \"outputStyle\": \"Attention-kind\"\n}\n```\n\n### Codex\nAppend the body of the desired output style to `~\u002F.codex\u002FAGENTS.md` (idempotent block):\n```markdown\n\u003C!-- attention-span:start -->\n[Attention-kind instructions body]\n\u003C!-- attention-span:end -->\n```\n\n### Antigravity CLI (agy)\nAppend the style body to `GEMINI.md` in the current project or home directory:\n```markdown\n\u003C!-- attention-span:start -->\n[Attention-kind instructions body]\n\u003C!-- attention-span:end -->\n```\n\n### Windsurf \u002F Devin \u002F Cursor\nFor Windsurf\u002FDevin global memories:\n`~\u002F.codeium\u002Fwindsurf\u002Fmemories\u002Fattention-kind.md`\nFor Cursor global rules:\n`~\u002F.cursor\u002Frules\u002Fattention-kind.mdc` or `~\u002F.cursor\u002Frules\u002F`\n\n---\n\n## Repository & Links\n\n- Source Repository: [github.com\u002Falexgreensh\u002Fattention-span](https:\u002F\u002Fgithub.com\u002Falexgreensh\u002Fattention-span)\n- License: AGPL-3.0\n","# Attention Span Skill\n\nA collection of ADHD-friendly output styles and conciseness guidelines for AI coding agents that optimize for reader scannability and attention retention without compromising engineering quality.\n\n## When to Activate\n\n- Asking an agent to format responses for maximum scannability and plain-English clarity\n- Configuring or switching agent output styles (`Attention-kind`, `Spartan`, `Rundown`)\n- Reducing token verbosity and eliminating AI fluff\u002Fpreambles in agent responses\n- Setting up global or project-level output style rules across AI agents (Claude Code, Codex, Antigravity CLI, Cursor, Windsurf, Copilot)\n\n## Available Output Styles\n\n| Style | Description | Ideal For |\n|---|---|---|\n| **Attention-kind** | ADHD-friendly, front-loaded answers, heavy bolding, arrow markers (`→`), spaced out blocks | General pair programming, deep focus, preventing wall-of-text fatigue |\n| **Spartan** | Zero-warmth, blunt, imperative, maximum signal-to-noise ratio | Heads-down work, rapid execution, quick technical answers |\n| **Rundown** | Briefing style with TL;DR, status checklist (`✅`\u002F`🟡`\u002F`⬜`), action items tagged with emoji | Standups, status updates, progress reports |\n\n---\n\n## Core Guidelines & Principles\n\n### 1. Attention-Kind Principles\n- **Lead with the bottom line in line 1.** The first sentence contains the direct answer.\n- **Say the least that fully answers.** Eliminate preambles (\"Great question!\", \"Sure thing!\"), restating questions, or closing restatements.\n- **Build for scanning:**\n  - Mark key points with `**→ Lead-in.**` on a new line with blank lines between paragraphs.\n  - **Bold the main takeaway and key terms\u002Fnumbers** so skimming only the bold text yields the complete answer.\n- **Preserve critical details:** Never cut a warning, caveat, exact threshold, or scoped condition to save words.\n- **Depth requests suspend brevity:** If the user asks to \"explain deeply\", \"walk me through it\", or \"give full context\", brevity constraints are suspended for that turn.\n\n### 2. Spartan Principles\n- **Imperative & direct:** Strip all warmth, transitions, and conversational fluff.\n- **Deliverable purity:** When asked for code, a commit message, or a document, return *only* the requested artifact without wrapping text.\n- **One idea per paragraph block.**\n\n### 3. Rundown Principles\n- **Open with `TL;DR:`** carrying the complete summary.\n- **State checklist:** `☑️ Done`, `🟡 In Progress`, `⬜ Not Started`.\n- **Group next choices under `Your move:`** with relevant emoji markers.\n- **Never invent status:** Report only verified facts.\n\n---\n\n## Multi-Agent Configuration\n\n### Claude Code\nOutput styles can be selected via `\u002Fstyle`:\n```bash\n# Global output styles directory\nmkdir -p ~\u002F.claude\u002Foutput-styles ~\u002F.claude\u002Fcommands\ncp output-styles\u002F*.md ~\u002F.claude\u002Foutput-styles\u002F\ncp commands\u002Fstyle.md ~\u002F.claude\u002Fcommands\u002F\n```\nTo set as default in `~\u002F.claude\u002Fsettings.json`:\n```json\n{\n  \"outputStyle\": \"Attention-kind\"\n}\n```\n\n### Codex\nAppend the body of the desired output style to `~\u002F.codex\u002FAGENTS.md` (idempotent block):\n```markdown\n\u003C!-- attention-span:start -->\n[Attention-kind instructions body]\n\u003C!-- attention-span:end -->\n```\n\n### Antigravity CLI (agy)\nAppend the style body to `GEMINI.md` in the current project or home directory:\n```markdown\n\u003C!-- attention-span:start -->\n[Attention-kind instructions body]\n\u003C!-- attention-span:end -->\n```\n\n### Windsurf \u002F Devin \u002F Cursor\nFor Windsurf\u002FDevin global memories:\n`~\u002F.codeium\u002Fwindsurf\u002Fmemories\u002Fattention-kind.md`\nFor Cursor global rules:\n`~\u002F.cursor\u002Frules\u002Fattention-kind.mdc` or `~\u002F.cursor\u002Frules\u002F`\n\n---\n\n## Repository & Links\n\n- Source Repository: [github.com\u002Falexgreensh\u002Fattention-span](https:\u002F\u002Fgithub.com\u002Falexgreensh\u002Fattention-span)\n- License: AGPL-3.0\n",{"name":5,"tools":25,"license":15,"metadata":26,"description":7},"Read, Write, Edit, Bash, Grep, Glob",{"origin":27,"version":28},"alexgreensh\u002Fattention-span","0.6.0","main","4e084e84eb42fc53e144c89c0f7f48b39c8a4b0f","skills\u002Fattention-span",1,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002Fsanjeevafk","First make it work. Then make it right. Then make it fast.","2026-11-14 13:36:16",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add sanjeevafk\u002Fagent-skills --skill attention-span",{"tool":43,"command":44},"bunx","bunx skills add sanjeevafk\u002Fagent-skills --skill attention-span",{"tool":46,"command":47},"pnpm","pnpm dlx skills add sanjeevafk\u002Fagent-skills --skill attention-span","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002FSKILL.md",true,[51,57,61,65,69,73],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"commands\u002Fstyle.md","REFERENCE","参考文档",4130,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002Fcommands\u002Fstyle.md",{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":16},"LICENSE","许可证",34523,{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"output-styles\u002Fattention-kind.md",7035,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002Foutput-styles\u002Fattention-kind.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"output-styles\u002Frundown.md",2520,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002Foutput-styles\u002Frundown.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"output-styles\u002Fspartan.md",3293,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002Foutput-styles\u002Fspartan.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"README.md",18768,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fattention-span\u002FREADME.md",[78,86,94,103,111,118],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":20},"01M7EFHX67M3KKXT1BXVPA5ADT","zarr-python","Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I\u002FO, S3\u002FGCS via fsspec, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","MIT","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":20},"01M7EFFQGM51TZBGRENXY50ZYM","whiteboard-diagrams","Create accurate, simple, hand-drawn whiteboard diagrams from a user's process, system, architecture, learning workflow, comparison, or causal explanation. Use when the user asks for a scribbly whiteboard visual, educational workflow graphic, hand-drawn explainer, or diagram like the bundled reference; ask one focused clarification question when the subject or relationships are missing, then generate and visually verify the final image.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":20},"01M7EFF1CSQNTDMHFK4ZGY6NYK","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":98,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":20},"01M7EFE8106X6C28FT8PA74427","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":20},"01M7EFCSNZM9G7ZHS6F127Q71X","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":20},"01M7EFCE7EZMKPRYDDNKBQ9EEH","vercel-deploy","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FSKILL.md",[],[]]