关于
The grok-build skill orchestrates coding by delegating well-specified implementation tasks to xAI's Grok Build CLI, which executes them headlessly. The assistant plans, writes the task specifications, reviews every diff, and owns the final result. Use it when the user explicitly requests to delegate work to Grok, such as for executing a Markdown implementation plan task-by-task.
快速安装
Claude Code
推荐npx skills add sanjay3290/ai-skills -a claude-code/plugin add https://github.com/sanjay3290/ai-skillsgit clone https://github.com/sanjay3290/ai-skills.git ~/.claude/skills/grok-build在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Grok Build Orchestration
The coding assistant is the orchestrator: it plans, writes self-contained task specs,
dispatches them to Grok Build headlessly, reviews every diff, and owns the final result.
Grok is the fast, cheap executor. Full CLI details and verified behaviors: references/cli.md.
When to delegate vs keep with the orchestrator
| Delegate to Grok | Keep with the orchestrator |
|---|---|
| Plan tasks with clear acceptance criteria | Ambiguous requirements, architecture decisions |
| Boilerplate, scaffolding, CRUD | Deep cross-file debugging |
| Mechanical refactors | Security-sensitive code |
| Test writing from clear specs | Anything touching production infrastructure |
| UI components from mockups/specs | Tasks where writing the spec ≈ doing the work |
When in doubt, keep it with the orchestrator.
Session preflight (once, before the first dispatch)
grok update --check --json— ifupdateAvailableis true, rungrok updateand confirm withgrok --version.grok models— if it errors or reports logged out, STOP and ask the user to rungrok login.
Per-task loop (sequential — the default)
-
Spec. Write a self-contained task file (template below) to a temp directory OUTSIDE the target repo — the harness scratchpad if one is available, else the OS temp dir. Never write it inside the target repo. Grok has zero conversation context: no one-liner prompts, ever.
- POSIX:
mkdir -p "${TMPDIR:-/tmp}/grok-specs", then writetask.mdthere. - Windows (PowerShell):
New-Item -ItemType Directory -Force "$env:TEMP\grok-specs", then writetask.mdthere.
- POSIX:
-
Clean state. No uncommitted source changes — commit or stash first, so the post-run diff is exactly Grok's work. Ignore build artifacts (
__pycache__,dist/, etc.); if they show ingit status, they're usually just un-gitignored, not your concern. Never dispatch on a dirty source tree. -
Dispatch.
POSIX:
grok --prompt-file <task-file> \ --output-format json \ --always-approve \ --max-turns 30 \ --cwd <repo>Windows (PowerShell) — backtick line-continuation:
grok --prompt-file <task-file> ` --output-format json ` --always-approve ` --max-turns 30 ` --cwd <repo>Parse the JSON output and save
sessionId. (--always-approveis required for headless runs —--permission-mode acceptEditssilently cancels edits with no interactive approver. Seereferences/cli.md.) For a high-stakes task, add--checkso Grok self-verifies before you review; skip it otherwise (it ~doubles latency). -
Review gate — non-negotiable.
- Read the diff yourself (
git diff -- <files from the spec>to skip artifact noise): does it do the task, only the task, and match repo conventions? - Run the acceptance commands from the spec.
- Pass → commit with a clear message following the repo's convention → next task.
- Fail → fix-up:
grok --resume <sessionId> -p "<specific feedback>" --always-approve --output-format json. Max 2 fix-up rounds. Still failing → revert Grok's changes (git checkout -- .;git clean -fdfor new files), do the task yourself, and tell the user Grok couldn't complete it.
- Read the diff yourself (
Task spec template
# Task: <one-line title>
## Context
- Repo: <path> — <one line on what the project is>
- Conventions: <test runner, formatter, a good example file to imitate>
## Files
- Modify: <path>
- Create: <path>
## Task
<precise description of the change>
## Constraints
- Do not modify any files other than those listed above.
- <other constraints>
## Acceptance criteria
- `<exact command>` <expected result>
Executing a Markdown implementation plan
- One plan task per dispatch, in order.
- Check off the plan's task checkboxes (
- [ ]→- [x]) as each task lands and passes the review gate. - If the plan explicitly marks tasks as independent, see Parallel dispatch below; otherwise stay sequential.
Parallel dispatch (opt-in exception, not the default)
Only when a plan explicitly marks tasks independent: dispatch each with
--worktree=<task-slug>, run concurrently, then review and merge one worktree at a
time through the same review gate. Merge conflicts usually eat the savings — prefer
sequential.
Failure handling
| Failure | Action |
|---|---|
stopReason: "Cancelled", empty text, no diff | Missing --always-approve — retry with it |
| CLI error / timeout | Retry once; then do the task yourself and note the fallback |
| Auth expired | Stop; ask the user to run grok login |
| 2 fix-up rounds exhausted | Revert Grok's diff; the orchestrator finishes the task |
| Dirty tree at dispatch | Refuse; commit/stash first |
Models
Default grok-4.5. Add -m grok-composer-2.5-fast only for trivial mechanical tasks.
GitHub 仓库
Frequently asked questions
What is the grok-build skill?
grok-build is a Claude Skill by sanjay3290. Skills package instructions and resources that Claude loads on demand, so Claude can perform grok-build-related tasks without extra prompting.
How do I install grok-build?
Use the install commands on this page: add grok-build to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does grok-build belong to?
grok-build is in the Meta category, tagged ai and design.
Is grok-build free to use?
Yes. grok-build is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
