sanjay3290/ai-skills

grok-build

Orchestrate coding work by delegating well-specified implementation tasks to xAI's Grok Build CLI (grok) running headlessly, while the coding assistant plans, writes the task specs, reviews every diff, and owns the result.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/sanjay3290/ai-skills --skill grok-build

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

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 GrokKeep with the orchestrator
Plan tasks with clear acceptance criteriaAmbiguous requirements, architecture decisions
Boilerplate, scaffolding, CRUDDeep cross-file debugging
Mechanical refactorsSecurity-sensitive code
Test writing from clear specsAnything touching production infrastructure
UI components from mockups/specsTasks where writing the spec ≈ doing the work

When in doubt, keep it with the orchestrator.

Session preflight (once, before the first dispatch)

  1. grok update --check --json — if updateAvailable is true, run grok update and

confirm with grok --version.

  1. grok models — if it errors or reports logged out, STOP and ask the user to run

grok login.

Per-task loop (sequential — the default)

  1. 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 "${TMPDIR:-/tmp}/grok-specs", then write task.md there.
  • Windows (PowerShell): New-Item -ItemType Directory -Force "$env:TEMP\grok-specs",

then write task.md there.

  1. 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 in git status, they're usually just un-gitignored, not your concern. Never dispatch on a dirty source tree.

  1. Dispatch.

POSIX:

bash
   grok --prompt-file <task-file> \
     --output-format json \
     --always-approve \
     --max-turns 30 \
     --cwd <repo>

Windows (PowerShell) — backtick line-continuation:

powershell
   grok --prompt-file <task-file> `
     --output-format json `
     --always-approve `
     --max-turns 30 `
     --cwd <repo>

Parse the JSON output and save sessionId. (--always-approve is required for headless runs — --permission-mode acceptEdits silently cancels edits with no interactive approver. See references/cli.md.) For a high-stakes task, add --check so Grok self-verifies before you review; skip it otherwise (it ~doubles latency).

  1. 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 -fd` for new files), do the task yourself, and tell the user Grok couldn't complete it.

Task spec template

markdown
# 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

FailureAction
stopReason: "Cancelled", empty text, no diffMissing --always-approve — retry with it
CLI error / timeoutRetry once; then do the task yourself and note the fallback
Auth expiredStop; ask the user to run grok login
2 fix-up rounds exhaustedRevert Grok's diff; the orchestrator finishes the task
Dirty tree at dispatchRefuse; commit/stash first

Models

Default grok-4.5. Add -m grok-composer-2.5-fast only for trivial mechanical tasks.

同じリポジトリから

関連する Skills

すべての Skills
sanjay3290
コミュニティ

deep-research

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 minutes but produces detailed, cited reports. Costs $2-5 per task.

1時間の導入数
1
GitHub Stars
454
更新日
11月2日
sanjay3290
コミュニティ

elevenlabs

Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.

1時間の導入数
1
GitHub Stars
454
更新日
11月2日
sanjay3290
コミュニティ

gmail

Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail labels. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.

1時間の導入数
1
GitHub Stars
454
更新日
11月2日
sanjay3290
コミュニティ

google-drive

Interact with Google Drive - search files, find folders, list contents, download files, upload files, create folders, move, copy, rename, and trash files. Use when user asks to: search Google Drive, find a file/folder, list Drive contents, download or upload files, create folders, move files, or organize Drive content. Lightweight integration with standalone OAuth authentication supporting full read/write access.

1時間の導入数
1
GitHub Stars
454
更新日
11月2日