Agent skill

Parallel PR

by team-mirai in team-mirai/mirai-gikai

複数の独立PRをチーム×worktreeで並列作成する。タスク一覧を受け取り、worktree準備→チーム組成→エージェント起動→CI確認→クリーンアップまで一気に実行する。

AGPL-3.0Auto-check passedDevelopment

Install Parallel PR

skills CLI
$ npx skills add team-mirai/mirai-gikai --skill parallel-pr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install team-mirai/mirai-gikai parallel-pr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/team-mirai/mirai-gikai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/parallel-pr .claude/skills/parallel-pr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
parallel-pr
GitHub stars
212
Token cost
~767 tokens
SKILL.md length
71 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
AGPL-3.0

At a glance

複数の独立PRをチーム×worktreeで並列作成する。タスク一覧を受け取り、worktree準備→チーム組成→エージェント起動→CI確認→クリーンアップまで一気に実行する。

  • Works in 6 steps: タスク整理 → worktree準備 → チーム組成&エージェント起動 → …
  • Tasks that involve Git worktrees
  • SKILL.md covers 前提条件, ワークフロー and 注意事項
  • Calls git, pnpm and gh

What it does

Parallel PR is an agent skill from team-mirai/mirai-gikai. 複数の独立PRをチーム×worktreeで並列作成する。タスク一覧を受け取り、worktree準備→チーム組成→エージェント起動→CI確認→クリーンアップまで一気に実行する。

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Git worktrees. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Git worktrees

Example prompts

  • “/parallel-pr”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. タスク整理
  2. worktree準備
  3. チーム組成&エージェント起動
  4. 完了待ち&CI確認
  5. クリーンアップ
  6. ユーザーに結果報告

What it can do on your machine

Read from SKILL.md and the folder at commit 00b649b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • pnpm
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, pnpm and gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Parallel PR loads about 767 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 71 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~767

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from team-mirai/mirai-gikai at commit 00b649b, republished under its AGPL-3.0 licence (© team-mirai). 71 words, ~767 tokens.

Download SKILL.mdSave it as .claude/skills/parallel-pr/SKILL.md (or your agent's skills folder).
name
parallel-pr
description
複数の独立PRをチーム×worktreeで並列作成する。タスク一覧を受け取り、worktree準備→チーム組成→エージェント起動→CI確認→クリーンアップまで一気に実行する。

Parallel PR

複数の独立したPRを、git worktree + エージェントチームで並列に作成するスキル。

前提条件

  • ユーザーからPR一覧(ブランチ名、対象ファイル、作業内容)が提供されていること
  • 提供されていなければ、まずプランモードで一覧を設計し承認を得る

ワークフロー

Phase 1: タスク整理

ユーザーの指示からPR一覧を整理する:

| # | ブランチ名 | 作業内容 | 対象ファイル |
|---|-----------|---------|-------------|
| 1 | feat/xxx  | ...     | src/...     |

PRの数に応じてエージェント数を決める(目安: 4-5が上限)。 1エージェントに1-2 PRを割り当てる。

Phase 2: worktree準備

エージェントごとにworktreeを作成する:

bash
# {team} はチーム名の略称(例: test4, refactor2)
# {x} はエージェント識別子(a, b, c, d...)
git worktree add ../mirai-gikai-{team}-{x} -b {team}-{x}-base
mkdir -p ../mirai-gikai-{team}-{x}/.claude
cp .claude/settings.local.json ../mirai-gikai-{team}-{x}/.claude/

依存パッケージのインストール(全worktreeをバックグラウンドで並列実行):

bash
cd ../mirai-gikai-{team}-{x} && pnpm install --frozen-lockfile
Phase 3: チーム組成&エージェント起動
  1. TeamCreate でチームを作成
  2. TaskCreate で各エージェントのタスクを作成(owner設定、in_progress)
  3. Task で各エージェントをバックグラウンドで起動:
Task(
  subagent_type: "general-purpose",
  team_name: "{チーム名}",
  name: "agent-{x}",
  mode: "bypassPermissions",
  run_in_background: true,
  prompt: 下記テンプレート参照
)
エージェントプロンプトテンプレート
あなはworktree-workerです。以下の手順で作業してください。

## 作業環境
- worktreeパス: {絶対パス}
- 全コマンドはこのworktreeディレクトリ内で実行すること

## 担当PR一覧
### PR 1
- ブランチ名: {branch}
- 作業内容: {description}
- 対象ファイル: {files}

### PR 2 (あれば)
- ...

## 作業手順
1. `git checkout -b {branch} develop` でブランチ作成
2. 対象ファイルを読んで理解
3. 実装・修正
4. push前のローカル検証(CIと同じコマンドを全て実行し、全て通過すること):
   - `pnpm lint:fix` でフォーマット修正
   - `pnpm lint` でlintチェック通過を確認
   - `pnpm typecheck` で型チェック通過を確認
   - `pnpm test` でテスト通過を確認
5. エラーがあれば修正して再度ステップ4を実行
6. コミット(Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>)
7. `git push -u origin {branch}`
8. `gh pr create --base develop --title "{title}" --body "..."`
9. 次のPRがあれば `git checkout -b {next-branch} develop` で次へ
10. 全完了後、リーダーにメッセージで報告(PR番号・URL)
Phase 4: 完了待ち&CI確認

エージェントからの完了メッセージを待つ。全エージェント完了後:

bash
# 全PRのCI状態を一括確認
for pr in {PR番号リスト}; do
  echo "=== PR #$pr ==="
  gh pr checks $pr
done
bash
# 全PRのコメントを確認(CodeRabbitやレビューアからのフィードバック)
for pr in {PR番号リスト}; do
  echo "=== PR #$pr comments ==="
  gh pr view $pr --comments
done

CI失敗時の対応:

  • TypeScript型エラー: worktreeで直接修正してpush
  • Biomeエラー: worktreeで pnpm lint:fix して再push
  • テスト失敗: worktreeで修正して再push

PRコメント対応:

  • CodeRabbitの指摘: 重要な指摘はworktreeで修正してpush
  • 軽微な指摘(nitpick等): マージ後に対応するか、必要に応じて対応
Phase 5: クリーンアップ
bash
# 全エージェントにシャットダウン要求
SendMessage(type: "shutdown_request", recipient: "agent-{x}")

# worktree削除
git worktree remove ../mirai-gikai-{team}-{x}
git branch -D {team}-{x}-base

# チーム削除
TeamDelete
Phase 6: ユーザーに結果報告

作成したPR一覧をまとめて報告:

| # | PR | タイトル | CI |
|---|-----|---------|-----|
| 1 | #XX | feat: ... | Passed |

注意事項

  • エージェント数は4-5が実用的上限(APIレート制限、CI負荷)
  • CIのflaky testに注意 → 失敗時はログ確認してから再実行
  • worktreeパスは ../mirai-gikai-{name} 形式
  • settings.local.json のコピーは必須(権限設定のため)

© team-mirai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/parallel-pr of team-mirai/mirai-gikai.

Open the folder on GitHubat commit 00b649b

Compare with similar skills

Parallel PR next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Parallel PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Parallel PR this skillteam-mirai/mirai-gikai212—~767Automated safety check: PassAGPL-3.0
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Finishing A Development Branchfarm-fe/farm5.6k34 repos~1.8kAutomated safety check: PassMIT
Git Worktree Cleanuplobehub/lobehub83k—~2.8kAutomated safety check: PassCustom licence
Keep Codex Fastvibeforge1111/keep-codex-fast1.6k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…

    5.6k GitHub starsUsed in 34 repos~1.8k tokens
    DevelopmentAuto-check passed
  • Git Worktree Cleanup

    lobehub/lobehub

    Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.

    83k GitHub stars~2.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Keep Codex Fast

    vibeforge1111/keep-codex-fast

    A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.

    1.6k GitHub stars~3.1k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Pre-Release PR Triage

    jamiepine/voicebox

    Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.

    57k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from team-mirai/mirai-gikai

All 10 skills in this repo
  • Agent Browser

    team-mirai/mirai-gikai

    agent-browser CLIを使ったブラウザ操作のガイド。Webページの操作、スクレイピング、スクリーンショット取得などブラウザ自動化が必要なときに参照する。「ブラウザで開いて」「Webページを操作して」「スクリーンショットを撮って」と言われたらこのスキルを使う。

    212 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Land

    team-mirai/mirai-gikai

    PR をランディングする。コンフリクトを監視・解決し、チェックを待ち、グリーンに なったら squash-merge する。land、merge、PR を完了まで導くことを依頼された ときに使用する。

    212 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Linear

    team-mirai/mirai-gikai

    Linear と対話するためのスキル。Linear MCP サーバー(mcplinear ツール)を 優先的に使用し、MCP でカバーされない生の GraphQL 操作(イントロスペクション、 ファイルアップロードなど)は lineargraphql クライアントツールにフォールバックする。

    212 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Linear

    team-mirai/mirai-gikai

    Linearタスクのステータス管理(In Progress / In Review への自動遷移). An agent skill from team-mirai/mirai-gikai.

    212 GitHub stars~407 tokensUpdated yesterday
    Auto-check passed
  • PR Screenshot

    team-mirai/mirai-gikai

    UI変更を含むPRで、agent-browserでスクリーンショットを撮影し、R2にアップロードしてPR本文に貼り付ける

    212 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check: notes
  • Push

    team-mirai/mirai-gikai

    現在のブランチの変更を origin に push し、対応する pull request を作成 または更新する。push、更新の公開、pull request の作成を依頼されたときに使用する。

    212 GitHub stars~724 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Parallel PR

What does Parallel PR do?

複数の独立PRをチーム×worktreeで並列作成する。タスク一覧を受け取り、worktree準備→チーム組成→エージェント起動→CI確認→クリーンアップまで一気に実行する。. Parallel PR is an agent skill from team-mirai/mirai-gikai.

When should I use Parallel PR?

Parallel PR fits situations like: tasks that involve Git worktrees.

How do I install Parallel PR in Claude Code?

Run `npx skills add team-mirai/mirai-gikai --skill parallel-pr -a claude-code`. Or copy the skill folder (.claude/skills/parallel-pr in team-mirai/mirai-gikai) into .claude/skills/parallel-pr in your project. Claude Code loads it when a task matches its description.

How do I install Parallel PR in Codex?

Run `npx skills add team-mirai/mirai-gikai --skill parallel-pr -a codex`. Or copy the skill folder (.claude/skills/parallel-pr in team-mirai/mirai-gikai) into .agents/skills/parallel-pr in your project. Codex loads it when a task matches its description.

Can I use Parallel PR in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add team-mirai/mirai-gikai --skill parallel-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/parallel-pr, .gemini/skills/parallel-pr, .github/skills/parallel-pr and .opencode/skills/parallel-pr in your project.

What does Parallel PR need to run?

Going by SKILL.md and its folder, Parallel PR needs the command-line tools its instructions call (git, pnpm and gh).

Does Parallel PR access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Parallel PR safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Parallel PR use?

Parallel PR is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Parallel PR use?

About 767 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Parallel PR?

Skills that share tags, products or a category with Parallel PR: Finishing a Development Branch (obra/superpowers, 296k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Parallel PR?

team-mirai (a GitHub organization) maintains it in team-mirai/mirai-gikai, which has 212 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

Source: team-mirai/mirai-gikai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.