[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A5KX16X17WCFJQMYFKA56N":3,"skill-same:01M7A5KX16X17WCFJQMYFKA56N":70},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M7A5KX16X17WCFJQMYFKA56N","grok-build",null,"Delegate well-specified implementation tasks to xAI's Grok Build CLI running headlessly while the orchestrating agent plans, writes task specs, reviews every diff, and owns the result.","MHassan0000\u002FSkills","MHassan0000","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F224296448?v=4","01M7A14DTC1EZCRN04582533RD","Muhammad Hassan Yousaf","01M7A14DV10KTW8NHQTJPD08X0",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fgrok-build\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: grok-build\ndescription: \"Delegate well-specified implementation tasks to xAI's Grok Build CLI running headlessly while the orchestrating agent plans, writes task specs, reviews every diff, and owns the result.\"\ncategory: agent-orchestration\nrisk: critical\nsource: https:\u002F\u002Fgithub.com\u002Fsanjay3290\u002Fai-skills\u002Ftree\u002Fmain\u002Fskills\u002Fgrok-build\nsource_repo: sanjay3290\u002Fai-skills\nsource_type: community\ndate_added: \"2026-07-09\"\nauthor: sanjay3290\ntags: [grok, delegation, code-generation, xai]\ntools: [claude, cursor, gemini]\nlicense: \"Apache-2.0\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fsanjay3290\u002Fai-skills\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Grok Build Orchestration\n\n## When to Use\n\n- Use when delegating a well-specified implementation task to xAI's Grok Build CLI running headlessly\n- Use when executing a Markdown implementation plan task-by-task with a diff review after each task\n- Use when the user says \"use grok\", \"grok build\", \"have grok implement\", or \"send to grok\"\n\nThe coding assistant is the orchestrator: it plans, writes self-contained task specs,\ndispatches them to Grok Build headlessly, reviews every diff, and owns the final result.\nGrok is the fast, cheap executor. Full CLI details and verified behaviors: `references\u002Fcli.md`.\n\n## Safety Gate\n\nBefore every dispatch, show the user the exact task specification that will be sent to xAI,\nthe target worktree, and the permission mode. Obtain explicit approval to disclose that text\nand to let Grok edit the scoped worktree. Never include secrets, proprietary source, customer\ndata, or credentials in a task specification. Do not run `grok update`, `--always-approve`,\nor a destructive recovery command without separate, explicit approval.\n\n## When to delegate vs keep with the orchestrator\n\n| Delegate to Grok | Keep with the orchestrator |\n|---|---|\n| Plan tasks with clear acceptance criteria | Ambiguous requirements, architecture decisions |\n| Boilerplate, scaffolding, CRUD | Deep cross-file debugging |\n| Mechanical refactors | Security-sensitive code |\n| Test writing from clear specs | Anything touching production infrastructure |\n| UI components from mockups\u002Fspecs | Tasks where writing the spec ≈ doing the work |\n\nWhen in doubt, keep it with the orchestrator.\n\n## Session preflight (once, before the first dispatch)\n\n1. `grok update --check --json` — if `updateAvailable` is true, tell the user. Run\n   `grok update` only after explicit approval, then confirm with `grok --version`.\n2. `grok models` — if it errors or reports logged out, STOP and ask the user to run\n   `grok login`.\n\n## Per-task loop (sequential — the default)\n\n1. **Spec.** Write a self-contained task file (template below) to a temp directory\n   OUTSIDE the target repo — the harness scratchpad if one is available, else the OS\n   temp dir. Never write it inside the target repo. Grok has zero conversation context:\n   no one-liner prompts, ever.\n   - POSIX: `mkdir -p \"${TMPDIR:-\u002Ftmp}\u002Fgrok-specs\"`, then write `task.md` there.\n   - Windows (PowerShell): `New-Item -ItemType Directory -Force \"$env:TEMP\\grok-specs\"`,\n     then write `task.md` there.\n2. **Clean state.** No uncommitted *source* changes — commit or stash first, so the\n   post-run diff is exactly Grok's work. Ignore build artifacts (`__pycache__`, `dist\u002F`,\n   etc.); if they show in `git status`, they're usually just un-gitignored, not your\n   concern. Never dispatch on a dirty source tree.\n3. **Dispatch.**\n\n   POSIX:\n\n   ```bash\n   grok --prompt-file \u003Ctask-file> \\\n     --output-format json \\\n     --always-approve \\\n     --max-turns 30 \\\n     --cwd \u003Crepo>\n   ```\n\n   Windows (PowerShell) — backtick line-continuation:\n\n   ```powershell\n   grok --prompt-file \u003Ctask-file> `\n     --output-format json `\n     --always-approve `\n     --max-turns 30 `\n     --cwd \u003Crepo>\n   ```\n\n   Parse the JSON output and save `sessionId`. (`--always-approve` is required for\n   headless runs — `--permission-mode acceptEdits` silently cancels edits with no\n   interactive approver. Use it only after the user explicitly approves Grok editing this\n   exact scoped worktree. See `references\u002Fcli.md`.) For a high-stakes task, add `--check`\n   so Grok self-verifies before you review; skip it otherwise (it ~doubles latency).\n4. **Review gate — non-negotiable.**\n   - Read the diff yourself (`git diff -- \u003Cfiles from the spec>` to skip artifact noise):\n     does it do the task, only the task, and match repo conventions?\n   - Run the acceptance commands from the spec.\n   - **Pass** → commit with a clear message following the repo's convention → next task.\n   - **Fail** → ask the user before a fix-up or any reset. Never run `git checkout -- .` or\n     `git clean -fd` automatically; preserve the diff for review and use a non-destructive\n     recovery plan unless the user explicitly authorizes otherwise.\n\n## Task spec template\n\n```markdown\n# Task: \u003Cone-line title>\n\n## Context\n- Repo: \u003Cpath> — \u003Cone line on what the project is>\n- Conventions: \u003Ctest runner, formatter, a good example file to imitate>\n\n## Files\n- Modify: \u003Cpath>\n- Create: \u003Cpath>\n\n## Task\n\u003Cprecise description of the change>\n\n## Constraints\n- Do not modify any files other than those listed above.\n- \u003Cother constraints>\n\n## Acceptance criteria\n- `\u003Cexact command>` \u003Cexpected result>\n```\n\n## Executing a Markdown implementation plan\n\n- One plan task per dispatch, in order.\n- Check off the plan's task checkboxes (`- [ ]` → `- [x]`) as each task lands and passes\n  the review gate.\n- If the plan explicitly marks tasks as independent, see Parallel dispatch below;\n  otherwise stay sequential.\n\n## Parallel dispatch (opt-in exception, not the default)\n\nOnly when a plan explicitly marks tasks independent: dispatch each with\n`--worktree=\u003Ctask-slug>`, run concurrently, then review and merge one worktree at a\ntime through the same review gate. Merge conflicts usually eat the savings — prefer\nsequential.\n\n## Failure handling\n\n| Failure | Action |\n|---|---|\n| `stopReason: \"Cancelled\"`, empty text, no diff | Missing `--always-approve` — retry with it |\n| CLI error \u002F timeout | Retry once; then do the task yourself and note the fallback |\n| Auth expired | Stop; ask the user to run `grok login` |\n| 2 fix-up rounds exhausted | Preserve the diff, ask the user for a recovery decision, then finish the task manually if authorized |\n| Dirty tree at dispatch | Refuse; commit\u002Fstash first |\n\n## Limitations\n\n- Grok receives the approved task specification; it is a third-party service and should not\n  receive secrets, proprietary material, personal data, or customer data.\n- `--always-approve` allows edits without an interactive approval prompt. It must be limited to\n  a clean, explicitly approved worktree and never substitutes for the orchestrator's review.\n- Model output can be incorrect, insecure, incomplete, or out of scope. Review the diff and\n  run the acceptance checks before accepting any change.\n- This skill does not authorize installations, updates, commits, pushes, deployments, or\n  destructive cleanup.\n\n## Models\n\nDefault `grok-4.5`. Add `-m grok-composer-2.5-fast` only for trivial mechanical tasks.\n","# Grok Build Orchestration\n\n## When to Use\n\n- Use when delegating a well-specified implementation task to xAI's Grok Build CLI running headlessly\n- Use when executing a Markdown implementation plan task-by-task with a diff review after each task\n- Use when the user says \"use grok\", \"grok build\", \"have grok implement\", or \"send to grok\"\n\nThe coding assistant is the orchestrator: it plans, writes self-contained task specs,\ndispatches them to Grok Build headlessly, reviews every diff, and owns the final result.\nGrok is the fast, cheap executor. Full CLI details and verified behaviors: `references\u002Fcli.md`.\n\n## Safety Gate\n\nBefore every dispatch, show the user the exact task specification that will be sent to xAI,\nthe target worktree, and the permission mode. Obtain explicit approval to disclose that text\nand to let Grok edit the scoped worktree. Never include secrets, proprietary source, customer\ndata, or credentials in a task specification. Do not run `grok update`, `--always-approve`,\nor a destructive recovery command without separate, explicit approval.\n\n## When to delegate vs keep with the orchestrator\n\n| Delegate to Grok | Keep with the orchestrator |\n|---|---|\n| Plan tasks with clear acceptance criteria | Ambiguous requirements, architecture decisions |\n| Boilerplate, scaffolding, CRUD | Deep cross-file debugging |\n| Mechanical refactors | Security-sensitive code |\n| Test writing from clear specs | Anything touching production infrastructure |\n| UI components from mockups\u002Fspecs | Tasks where writing the spec ≈ doing the work |\n\nWhen in doubt, keep it with the orchestrator.\n\n## Session preflight (once, before the first dispatch)\n\n1. `grok update --check --json` — if `updateAvailable` is true, tell the user. Run\n   `grok update` only after explicit approval, then confirm with `grok --version`.\n2. `grok models` — if it errors or reports logged out, STOP and ask the user to run\n   `grok login`.\n\n## Per-task loop (sequential — the default)\n\n1. **Spec.** Write a self-contained task file (template below) to a temp directory\n   OUTSIDE the target repo — the harness scratchpad if one is available, else the OS\n   temp dir. Never write it inside the target repo. Grok has zero conversation context:\n   no one-liner prompts, ever.\n   - POSIX: `mkdir -p \"${TMPDIR:-\u002Ftmp}\u002Fgrok-specs\"`, then write `task.md` there.\n   - Windows (PowerShell): `New-Item -ItemType Directory -Force \"$env:TEMP\\grok-specs\"`,\n     then write `task.md` there.\n2. **Clean state.** No uncommitted *source* changes — commit or stash first, so the\n   post-run diff is exactly Grok's work. Ignore build artifacts (`__pycache__`, `dist\u002F`,\n   etc.); if they show in `git status`, they're usually just un-gitignored, not your\n   concern. Never dispatch on a dirty source tree.\n3. **Dispatch.**\n\n   POSIX:\n\n   ```bash\n   grok --prompt-file \u003Ctask-file> \\\n     --output-format json \\\n     --always-approve \\\n     --max-turns 30 \\\n     --cwd \u003Crepo>\n   ```\n\n   Windows (PowerShell) — backtick line-continuation:\n\n   ```powershell\n   grok --prompt-file \u003Ctask-file> `\n     --output-format json `\n     --always-approve `\n     --max-turns 30 `\n     --cwd \u003Crepo>\n   ```\n\n   Parse the JSON output and save `sessionId`. (`--always-approve` is required for\n   headless runs — `--permission-mode acceptEdits` silently cancels edits with no\n   interactive approver. Use it only after the user explicitly approves Grok editing this\n   exact scoped worktree. See `references\u002Fcli.md`.) For a high-stakes task, add `--check`\n   so Grok self-verifies before you review; skip it otherwise (it ~doubles latency).\n4. **Review gate — non-negotiable.**\n   - Read the diff yourself (`git diff -- \u003Cfiles from the spec>` to skip artifact noise):\n     does it do the task, only the task, and match repo conventions?\n   - Run the acceptance commands from the spec.\n   - **Pass** → commit with a clear message following the repo's convention → next task.\n   - **Fail** → ask the user before a fix-up or any reset. Never run `git checkout -- .` or\n     `git clean -fd` automatically; preserve the diff for review and use a non-destructive\n     recovery plan unless the user explicitly authorizes otherwise.\n\n## Task spec template\n\n```markdown\n# Task: \u003Cone-line title>\n\n## Context\n- Repo: \u003Cpath> — \u003Cone line on what the project is>\n- Conventions: \u003Ctest runner, formatter, a good example file to imitate>\n\n## Files\n- Modify: \u003Cpath>\n- Create: \u003Cpath>\n\n## Task\n\u003Cprecise description of the change>\n\n## Constraints\n- Do not modify any files other than those listed above.\n- \u003Cother constraints>\n\n## Acceptance criteria\n- `\u003Cexact command>` \u003Cexpected result>\n```\n\n## Executing a Markdown implementation plan\n\n- One plan task per dispatch, in order.\n- Check off the plan's task checkboxes (`- [ ]` → `- [x]`) as each task lands and passes\n  the review gate.\n- If the plan explicitly marks tasks as independent, see Parallel dispatch below;\n  otherwise stay sequential.\n\n## Parallel dispatch (opt-in exception, not the default)\n\nOnly when a plan explicitly marks tasks independent: dispatch each with\n`--worktree=\u003Ctask-slug>`, run concurrently, then review and merge one worktree at a\ntime through the same review gate. Merge conflicts usually eat the savings — prefer\nsequential.\n\n## Failure handling\n\n| Failure | Action |\n|---|---|\n| `stopReason: \"Cancelled\"`, empty text, no diff | Missing `--always-approve` — retry with it |\n| CLI error \u002F timeout | Retry once; then do the task yourself and note the fallback |\n| Auth expired | Stop; ask the user to run `grok login` |\n| 2 fix-up rounds exhausted | Preserve the diff, ask the user for a recovery decision, then finish the task manually if authorized |\n| Dirty tree at dispatch | Refuse; commit\u002Fstash first |\n\n## Limitations\n\n- Grok receives the approved task specification; it is a third-party service and should not\n  receive secrets, proprietary material, personal data, or customer data.\n- `--always-approve` allows edits without an interactive approval prompt. It must be limited to\n  a clean, explicitly approved worktree and never substitutes for the orchestrator's review.\n- Model output can be incorrect, insecure, incomplete, or out of scope. Review the diff and\n  run the acceptance checks before accepting any change.\n- This skill does not authorize installations, updates, commits, pushes, deployments, or\n  destructive cleanup.\n\n## Models\n\nDefault `grok-4.5`. Add `-m grok-composer-2.5-fast` only for trivial mechanical tasks.\n",{"name":5,"risk":24,"tags":25,"tools":30,"author":34,"source":35,"license":15,"category":36,"date_added":37,"description":7,"source_repo":38,"source_type":39,"license_source":40},"critical",[26,27,28,29],"grok","delegation","code-generation","xai",[31,32,33],"claude","cursor","gemini","sanjay3290","https:\u002F\u002Fgithub.com\u002Fsanjay3290\u002Fai-skills\u002Ftree\u002Fmain\u002Fskills\u002Fgrok-build","agent-orchestration","2026-07-09","sanjay3290\u002Fai-skills","community","https:\u002F\u002Fgithub.com\u002Fsanjay3290\u002Fai-skills\u002Fblob\u002Fmain\u002FLICENSE","main","a4404a75dc81d6b7e58c5906b6aaffbcb5e84747","Claude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fgrok-build",0,"https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills","https:\u002F\u002Fgithub.com\u002FMHassan0000","https:\u002F\u002Fhassanyousaf.vercel.app","Full Stack Developer building web apps, SaaS, AI systems, and automations. Passionate about clean code, UI\u002FUX, backend systems, and turning ideas into products.","2026-08-07 20:42:05",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add MHassan0000\u002FSkills --skill grok-build",{"tool":56,"command":57},"bunx","bunx skills add MHassan0000\u002FSkills --skill grok-build",{"tool":59,"command":60},"pnpm","pnpm dlx skills add MHassan0000\u002FSkills --skill grok-build","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fgrok-build\u002FSKILL.md",true,[64],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fcli.md","REFERENCE","参考文档",4229,"https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fgrok-build\u002Freferences\u002Fcli.md",[71,79,86,93,101,109],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AGBX58S04DX8DKKME8N311","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","MIT","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fvercel-react-best-practices\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AGBREE890608Z7YDMAKH27","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fstop-slop\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":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AGAS972A2AN7Q5EW8HEAXK","ogilvy-copywriting","Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fogilvy\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7AGAF12803G5JPVMK79AYJB","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Ffrontend-design\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7AG88WWVWCGJY9WA9CH7EY4","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.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7AG7ZTNV7XQCWDQ9674FBYB","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\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[]]