[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78298B6FVPFGHQHZZHABFYG":3,"skill-same:01M78298B6FVPFGHQHZZHABFYG":48},{"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":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M78298B6FVPFGHQHZZHABFYG","agentation-self-driving",null,"Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to \"critique this page,\" \"add design annotations,\" \"review the UI,\" \"self-driving mode,\" \"auto-annotate,\" or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fskills_sh\u002Fs\u002Fskills-sh_benjitaylor_agentation_agentation-self-driving\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agentation-self-driving\ndescription: Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to \"critique this page,\" \"add design annotations,\" \"review the UI,\" \"self-driving mode,\" \"auto-annotate,\" or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.\nallowed-tools: Bash(agent-browser:*)\n---\n\n# Agentation Self-Driving Mode\n\nAutonomously critique a web page by adding design annotations via the Agentation toolbar — in a visible headed browser so the user can watch the agent work in real time, like watching a self-driving car navigate.\n\n## Launch — Always Headed\n\nThe browser MUST be visible. Never run headless. The user watches you scan, hover, click, and annotate.\n\n**Preflight**: Verify `agent-browser` is available before anything else:\n\n```bash\ncommand -v agent-browser >\u002Fdev\u002Fnull || { echo \"ERROR: agent-browser not found. Install the agent-browser skill first.\"; exit 1; }\n```\n\n**Launch**: Try opening directly first. Only close an existing session if the open command fails with a stale session error — this avoids killing a browser someone else is using:\n\n```bash\n# Try to open. If it fails (stale session), close first then retry.\nagent-browser --headed open \u003Curl> 2>&1 || { agent-browser close 2>\u002Fdev\u002Fnull; agent-browser --headed open \u003Curl>; }\n```\n\nThen verify the Agentation toolbar is present and expand it:\n\n```bash\n# 1. Check toolbar exists on the page (data-feedback-toolbar is the root marker)\nagent-browser eval \"document.querySelector('[data-feedback-toolbar]') ? 'toolbar found' : 'NOT FOUND'\"\n# If \"NOT FOUND\": Agentation is not installed on this page — stop and tell the user\n\n# 2. Expand ONLY if collapsed (clicking when already expanded collapses it)\nagent-browser eval \"document.querySelector('[data-feedback-toolbar][class*=expanded]') ? 'already expanded' : (document.querySelector('[class*=toggleContent]')?.click(), 'expanding')\"\n\n# 3. Verify: take a snapshot and look for toolbar controls\nagent-browser snapshot -i\n# If expanded: you'll see \"Block page interactions\" checkbox, color buttons (Purple, Blue, etc.)\n# If collapsed: you'll only see the small toggle button — retry step 2\n```\n\n\"Block page interactions\" must be checked (default: on).\n\n> **eval quoting rule**: Always use `[class*=toggleContent]` (no quotes around the attribute value) in eval strings. Do not use double-bang in eval because bash treats it as history expansion. Do not use backslash-escaped inner quotes either, as they break unpredictably across shells.\n\n## Critical: How to Create Annotations\n\n**Standard element clicks (`click @ref`) do NOT trigger annotation dialogs.** The Agentation overlay intercepts pointer events at the coordinate level. Use coordinate-based mouse events — this also makes the interaction visible in the browser as the cursor moves across the page.\n\n> **`@ref` compatibility**: Only `click`, `fill`, `type`, `hover`, `focus`, `check`, `select`, `drag` support `@ref` syntax. The commands `scrollintoview`, `get box`, and `eval` do NOT — they expect CSS selectors. Use `eval` with `querySelector` for scrolling and position lookup.\n\n```bash\n# 1. Take interactive snapshot — identify target element and build a CSS selector\nagent-browser snapshot -i\n# Example: snapshot shows  heading \"Point at bugs.\" [ref=e10]\n# Derive a CSS selector: 'h1', or more specific: 'h1:first-of-type'\n\n# 2. Scroll the element into view via eval (NOT scrollintoview @ref — that breaks)\nagent-browser eval \"document.querySelector('h1').scrollIntoView({block:'center'})\"\n\n# 3. Get its bounding box via eval (NOT get box @ref — that also breaks)\nagent-browser eval \"((r) => r.x+','+r.y+','+r.width+','+r.height)(document.querySelector('h1').getBoundingClientRect())\"\n# Returns: \"383,245,200,40\"  (parse these as x,y,width,height)\n\n# 4. Move cursor to element center, then click\n#    centerX = x + width\u002F2,  centerY = y + height\u002F2\nagent-browser mouse move \u003CcenterX> \u003CcenterY>\nagent-browser mouse down left\nagent-browser mouse up left\n\n# 5. Get the annotation dialog refs — read the FULL snapshot output\n#    Dialog refs appear at the BOTTOM of the list, don't truncate with head\u002Ftail\nagent-browser snapshot -i\n# Look for: textbox \"What should change?\" and \"Cancel\" \u002F \"Add\" buttons\n\n# 6. Type critique — fill and click DO support @ref\nagent-browser fill @\u003CtextboxRef> \"Your critique here\"\n\n# 7. Submit (Add button enables after text is filled)\nagent-browser click @\u003CaddRef>\n```\n\nIf no dialog appears after clicking, the toolbar may have collapsed. Re-expand (only if collapsed) and retry:\n\n```bash\nagent-browser eval \"document.querySelector('[data-feedback-toolbar][class*=expanded]') ? 'ok' : (document.querySelector('[class*=toggleContent]')?.click(), 'expanded')\"\n```\n\n### Building CSS selectors from snapshots\n\nThe snapshot shows element roles, names, and refs. Map them to CSS selectors:\n\n| Snapshot line | CSS selector |\n|--------------|-------------|\n| `heading \"Point at bugs.\" [ref=e10]` | `h1` or `h1:first-of-type` |\n| `button \"npm install agentation Copy\" [ref=e15]` | `button:has(code)` or by text content via eval |\n| `link \"Star on GitHub\" [ref=e28]` | `a[href*=github]` |\n| `paragraph (long text...) [ref=e20]` | Target by section: `section:nth-of-type(2) p` |\n\nWhen in doubt, use a broader selector and verify with eval:\n```bash\nagent-browser eval \"document.querySelector('h2').textContent\"\n```\n\n## The Loop\n\nWork top-to-bottom through the page. For each annotation:\n\n1. Scroll to the target area via eval (`scrollIntoView`)\n2. Pick a specific element — heading, paragraph, button, section container\n3. Get its bounding box via eval (`getBoundingClientRect`)\n4. Execute the coordinate-click sequence (`mouse move` → `mouse down` → `mouse up`)\n5. Read the **full** snapshot output to find dialog refs at the bottom\n6. Write the critique (`fill @ref`) and submit (`click @ref`)\n7. Verify the annotation was added (see below)\n8. Move to the next area\n\n### Verifying annotations\n\nAfter submitting each annotation, confirm the count increased:\n\n```bash\nagent-browser eval \"document.querySelectorAll('[data-annotation-marker]').length\"\n# Should return the expected count (1 after first, 2 after second, etc.)\n```\n\nIf the count didn't increase, the submission failed silently — re-snapshot and check if the dialog is still open.\n\nAim for 5-8 annotations per page unless told otherwise.\n\n## What to Critique\n\n| Area | What to look for |\n|------|-----------------|\n| **Hero \u002F above the fold** | Headline hierarchy, CTA placement, visual grouping |\n| **Navigation** | Label styling, category grouping, visual weight |\n| **Demo \u002F illustrations** | Clarity, depth, animation readability |\n| **Content sections** | Spacing rhythm, callout treatments, typography hierarchy |\n| **Key taglines** | Whether resonant lines get enough visual emphasis |\n| **CTAs and footer** | Conversion weight, visual separation, final actions |\n\n## Critique Style\n\n2-3 sentences max per annotation:\n\n- **Specific and actionable**: \"Stack the install command below the subheading at 16px\" not \"fix the layout\"\n- **1-2 concrete alternatives**: Reference CSS values, layout patterns, or design systems\n- **Name the principle**: Visual hierarchy, Gestalt grouping, whitespace, emphasis, conversion design\n- **Reference comparable products**: \"Like how Stripe\u002FLinear\u002FVercel handles this\"\n\nBad: \"This section needs work\"\nGood: \"This bullet list reads like docs, not a showcase. Use a 3-column card grid with icons — similar to Stripe's guidelines pattern. Creates visual rhythm and scannability.\"\n\n## Install\n\nThe skill must be symlinked into `~\u002F.claude\u002Fskills\u002F` for Claude Code to discover it:\n\n```bash\nln -s \"$(pwd)\u002Fskills\u002Fagentation-self-driving\" ~\u002F.claude\u002Fskills\u002Fagentation-self-driving\n```\n\nRestart Claude Code after installing. Verify with `\u002Fagentation-self-driving` — if it loads the skill instructions, the symlink is working.\n\n## Troubleshooting\n\n- **\"Browser not launched. Call launch first.\"**: Stale session from a previous run — run `agent-browser close 2>\u002Fdev\u002Fnull` then retry the `--headed open` command\n- **Toolbar not found on page**: Agentation isn't installed — run `\u002Fagentation` to set it up first\n- **No dialog after clicking**: Toolbar collapsed — re-expand with the state-aware eval (check `[class*=expanded]` first), retry\n- **Wrong element targeted**: Click Cancel, scroll to intended element, retry with correct coordinates\n- **Add button stays disabled**: Text wasn't filled — re-snapshot and fill the textbox\n- **Page navigated**: \"Block page interactions\" is off — enable via toolbar settings\n- **Annotation count didn't increase**: Submission failed — dialog may still be open, re-snapshot and check\n- **Interrupted mid-run (Ctrl+C)**: The browser stays open with whatever state it was in. Run `agent-browser close` to clean up before starting a new session\n\n## agent-browser Pitfalls\n\nThese will silently break the workflow if you're not aware of them:\n\n| Pitfall | What happens | Fix |\n|---------|-------------|-----|\n| `scrollintoview @ref` | Crashes: \"Unsupported token @ref while parsing css selector\" | Use `eval \"document.querySelector('sel').scrollIntoView({block:'center'})\"` |\n| `get box @ref` | Same crash — `get box` parses refs as CSS selectors | Use `eval \"((r)=>r.x+','+r.y+','+r.width+','+r.height)(document.querySelector('sel').getBoundingClientRect())\"` |\n| `eval` with double-bang | Bash expands double-bang as history substitution before the command runs | Use `expr !== null` or `expr ? true : false` instead |\n| `eval` with backslash-escaped quotes | Escaped inner quotes break across shells | Drop the quotes: `[class*=toggleContent]` works for simple values without spaces |\n| `snapshot -i \\| head -50` | Annotation dialog refs (`textbox \"What should change?\"`, `Add`, `Cancel`) appear at the BOTTOM of the snapshot | Always read the **full** snapshot output — never truncate |\n| `click @ref` on overlay elements | The click goes through to the real DOM, bypassing the Agentation overlay | Use `mouse move` → `mouse down left` → `mouse up left` for coordinate-based clicks that the overlay intercepts |\n| `--headed open` fails with \"Browser not launched\" | Stale sessions from previous runs block new launches | Run `agent-browser close 2>\u002Fdev\u002Fnull` then retry the open command |\n\n**Rule of thumb**: `@ref` works for interaction commands (`click`, `fill`, `type`, `hover`). For everything else (`eval`, `get`, `scrollintoview`), use CSS selectors via `querySelector` in an eval.\n\n## Two-Session Workflow (Full Self-Driving)\n\nWith MCP connected (toolbar shows \"MCP Connected\"), annotations auto-send to any listening agent. This enables:\n\n- **Session 1** (this skill): Watches the page, adds critique annotations in the visible browser\n- **Session 2**: Runs `agentation_watch_annotations` in a loop, receives annotations, edits code to address each one\n\nThe user watches Session 1 drive through the page in the browser while Session 2 fixes issues in the codebase — fully autonomous design review and implementation.\n","# Agentation Self-Driving Mode\n\nAutonomously critique a web page by adding design annotations via the Agentation toolbar — in a visible headed browser so the user can watch the agent work in real time, like watching a self-driving car navigate.\n\n## Launch — Always Headed\n\nThe browser MUST be visible. Never run headless. The user watches you scan, hover, click, and annotate.\n\n**Preflight**: Verify `agent-browser` is available before anything else:\n\n```bash\ncommand -v agent-browser >\u002Fdev\u002Fnull || { echo \"ERROR: agent-browser not found. Install the agent-browser skill first.\"; exit 1; }\n```\n\n**Launch**: Try opening directly first. Only close an existing session if the open command fails with a stale session error — this avoids killing a browser someone else is using:\n\n```bash\n# Try to open. If it fails (stale session), close first then retry.\nagent-browser --headed open \u003Curl> 2>&1 || { agent-browser close 2>\u002Fdev\u002Fnull; agent-browser --headed open \u003Curl>; }\n```\n\nThen verify the Agentation toolbar is present and expand it:\n\n```bash\n# 1. Check toolbar exists on the page (data-feedback-toolbar is the root marker)\nagent-browser eval \"document.querySelector('[data-feedback-toolbar]') ? 'toolbar found' : 'NOT FOUND'\"\n# If \"NOT FOUND\": Agentation is not installed on this page — stop and tell the user\n\n# 2. Expand ONLY if collapsed (clicking when already expanded collapses it)\nagent-browser eval \"document.querySelector('[data-feedback-toolbar][class*=expanded]') ? 'already expanded' : (document.querySelector('[class*=toggleContent]')?.click(), 'expanding')\"\n\n# 3. Verify: take a snapshot and look for toolbar controls\nagent-browser snapshot -i\n# If expanded: you'll see \"Block page interactions\" checkbox, color buttons (Purple, Blue, etc.)\n# If collapsed: you'll only see the small toggle button — retry step 2\n```\n\n\"Block page interactions\" must be checked (default: on).\n\n> **eval quoting rule**: Always use `[class*=toggleContent]` (no quotes around the attribute value) in eval strings. Do not use double-bang in eval because bash treats it as history expansion. Do not use backslash-escaped inner quotes either, as they break unpredictably across shells.\n\n## Critical: How to Create Annotations\n\n**Standard element clicks (`click @ref`) do NOT trigger annotation dialogs.** The Agentation overlay intercepts pointer events at the coordinate level. Use coordinate-based mouse events — this also makes the interaction visible in the browser as the cursor moves across the page.\n\n> **`@ref` compatibility**: Only `click`, `fill`, `type`, `hover`, `focus`, `check`, `select`, `drag` support `@ref` syntax. The commands `scrollintoview`, `get box`, and `eval` do NOT — they expect CSS selectors. Use `eval` with `querySelector` for scrolling and position lookup.\n\n```bash\n# 1. Take interactive snapshot — identify target element and build a CSS selector\nagent-browser snapshot -i\n# Example: snapshot shows  heading \"Point at bugs.\" [ref=e10]\n# Derive a CSS selector: 'h1', or more specific: 'h1:first-of-type'\n\n# 2. Scroll the element into view via eval (NOT scrollintoview @ref — that breaks)\nagent-browser eval \"document.querySelector('h1').scrollIntoView({block:'center'})\"\n\n# 3. Get its bounding box via eval (NOT get box @ref — that also breaks)\nagent-browser eval \"((r) => r.x+','+r.y+','+r.width+','+r.height)(document.querySelector('h1').getBoundingClientRect())\"\n# Returns: \"383,245,200,40\"  (parse these as x,y,width,height)\n\n# 4. Move cursor to element center, then click\n#    centerX = x + width\u002F2,  centerY = y + height\u002F2\nagent-browser mouse move \u003CcenterX> \u003CcenterY>\nagent-browser mouse down left\nagent-browser mouse up left\n\n# 5. Get the annotation dialog refs — read the FULL snapshot output\n#    Dialog refs appear at the BOTTOM of the list, don't truncate with head\u002Ftail\nagent-browser snapshot -i\n# Look for: textbox \"What should change?\" and \"Cancel\" \u002F \"Add\" buttons\n\n# 6. Type critique — fill and click DO support @ref\nagent-browser fill @\u003CtextboxRef> \"Your critique here\"\n\n# 7. Submit (Add button enables after text is filled)\nagent-browser click @\u003CaddRef>\n```\n\nIf no dialog appears after clicking, the toolbar may have collapsed. Re-expand (only if collapsed) and retry:\n\n```bash\nagent-browser eval \"document.querySelector('[data-feedback-toolbar][class*=expanded]') ? 'ok' : (document.querySelector('[class*=toggleContent]')?.click(), 'expanded')\"\n```\n\n### Building CSS selectors from snapshots\n\nThe snapshot shows element roles, names, and refs. Map them to CSS selectors:\n\n| Snapshot line | CSS selector |\n|--------------|-------------|\n| `heading \"Point at bugs.\" [ref=e10]` | `h1` or `h1:first-of-type` |\n| `button \"npm install agentation Copy\" [ref=e15]` | `button:has(code)` or by text content via eval |\n| `link \"Star on GitHub\" [ref=e28]` | `a[href*=github]` |\n| `paragraph (long text...) [ref=e20]` | Target by section: `section:nth-of-type(2) p` |\n\nWhen in doubt, use a broader selector and verify with eval:\n```bash\nagent-browser eval \"document.querySelector('h2').textContent\"\n```\n\n## The Loop\n\nWork top-to-bottom through the page. For each annotation:\n\n1. Scroll to the target area via eval (`scrollIntoView`)\n2. Pick a specific element — heading, paragraph, button, section container\n3. Get its bounding box via eval (`getBoundingClientRect`)\n4. Execute the coordinate-click sequence (`mouse move` → `mouse down` → `mouse up`)\n5. Read the **full** snapshot output to find dialog refs at the bottom\n6. Write the critique (`fill @ref`) and submit (`click @ref`)\n7. Verify the annotation was added (see below)\n8. Move to the next area\n\n### Verifying annotations\n\nAfter submitting each annotation, confirm the count increased:\n\n```bash\nagent-browser eval \"document.querySelectorAll('[data-annotation-marker]').length\"\n# Should return the expected count (1 after first, 2 after second, etc.)\n```\n\nIf the count didn't increase, the submission failed silently — re-snapshot and check if the dialog is still open.\n\nAim for 5-8 annotations per page unless told otherwise.\n\n## What to Critique\n\n| Area | What to look for |\n|------|-----------------|\n| **Hero \u002F above the fold** | Headline hierarchy, CTA placement, visual grouping |\n| **Navigation** | Label styling, category grouping, visual weight |\n| **Demo \u002F illustrations** | Clarity, depth, animation readability |\n| **Content sections** | Spacing rhythm, callout treatments, typography hierarchy |\n| **Key taglines** | Whether resonant lines get enough visual emphasis |\n| **CTAs and footer** | Conversion weight, visual separation, final actions |\n\n## Critique Style\n\n2-3 sentences max per annotation:\n\n- **Specific and actionable**: \"Stack the install command below the subheading at 16px\" not \"fix the layout\"\n- **1-2 concrete alternatives**: Reference CSS values, layout patterns, or design systems\n- **Name the principle**: Visual hierarchy, Gestalt grouping, whitespace, emphasis, conversion design\n- **Reference comparable products**: \"Like how Stripe\u002FLinear\u002FVercel handles this\"\n\nBad: \"This section needs work\"\nGood: \"This bullet list reads like docs, not a showcase. Use a 3-column card grid with icons — similar to Stripe's guidelines pattern. Creates visual rhythm and scannability.\"\n\n## Install\n\nThe skill must be symlinked into `~\u002F.claude\u002Fskills\u002F` for Claude Code to discover it:\n\n```bash\nln -s \"$(pwd)\u002Fskills\u002Fagentation-self-driving\" ~\u002F.claude\u002Fskills\u002Fagentation-self-driving\n```\n\nRestart Claude Code after installing. Verify with `\u002Fagentation-self-driving` — if it loads the skill instructions, the symlink is working.\n\n## Troubleshooting\n\n- **\"Browser not launched. Call launch first.\"**: Stale session from a previous run — run `agent-browser close 2>\u002Fdev\u002Fnull` then retry the `--headed open` command\n- **Toolbar not found on page**: Agentation isn't installed — run `\u002Fagentation` to set it up first\n- **No dialog after clicking**: Toolbar collapsed — re-expand with the state-aware eval (check `[class*=expanded]` first), retry\n- **Wrong element targeted**: Click Cancel, scroll to intended element, retry with correct coordinates\n- **Add button stays disabled**: Text wasn't filled — re-snapshot and fill the textbox\n- **Page navigated**: \"Block page interactions\" is off — enable via toolbar settings\n- **Annotation count didn't increase**: Submission failed — dialog may still be open, re-snapshot and check\n- **Interrupted mid-run (Ctrl+C)**: The browser stays open with whatever state it was in. Run `agent-browser close` to clean up before starting a new session\n\n## agent-browser Pitfalls\n\nThese will silently break the workflow if you're not aware of them:\n\n| Pitfall | What happens | Fix |\n|---------|-------------|-----|\n| `scrollintoview @ref` | Crashes: \"Unsupported token @ref while parsing css selector\" | Use `eval \"document.querySelector('sel').scrollIntoView({block:'center'})\"` |\n| `get box @ref` | Same crash — `get box` parses refs as CSS selectors | Use `eval \"((r)=>r.x+','+r.y+','+r.width+','+r.height)(document.querySelector('sel').getBoundingClientRect())\"` |\n| `eval` with double-bang | Bash expands double-bang as history substitution before the command runs | Use `expr !== null` or `expr ? true : false` instead |\n| `eval` with backslash-escaped quotes | Escaped inner quotes break across shells | Drop the quotes: `[class*=toggleContent]` works for simple values without spaces |\n| `snapshot -i \\| head -50` | Annotation dialog refs (`textbox \"What should change?\"`, `Add`, `Cancel`) appear at the BOTTOM of the snapshot | Always read the **full** snapshot output — never truncate |\n| `click @ref` on overlay elements | The click goes through to the real DOM, bypassing the Agentation overlay | Use `mouse move` → `mouse down left` → `mouse up left` for coordinate-based clicks that the overlay intercepts |\n| `--headed open` fails with \"Browser not launched\" | Stale sessions from previous runs block new launches | Run `agent-browser close 2>\u002Fdev\u002Fnull` then retry the open command |\n\n**Rule of thumb**: `@ref` works for interaction commands (`click`, `fill`, `type`, `hover`). For everything else (`eval`, `get`, `scrollintoview`), use CSS selectors via `querySelector` in an eval.\n\n## Two-Session Workflow (Full Self-Driving)\n\nWith MCP connected (toolbar shows \"MCP Connected\"), annotations auto-send to any listening agent. This enables:\n\n- **Session 1** (this skill): Watches the page, adds critique annotations in the visible browser\n- **Session 2**: Runs `agentation_watch_annotations` in a loop, receives annotations, edits code to address each one\n\nThe user watches Session 1 drive through the page in the browser while Session 2 fixes issues in the codebase — fully autonomous design review and implementation.\n",{"name":5,"description":7,"allowed-tools":24},"Bash(agent-browser:*)","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fskills_sh\u002Fs\u002Fskills-sh_benjitaylor_agentation_agentation-self-driving",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agentation-self-driving",{"tool":40,"command":41},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agentation-self-driving",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agentation-self-driving","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fskills_sh\u002Fs\u002Fskills-sh_benjitaylor_agentation_agentation-self-driving\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]