How do I install the Batch skill?

Run npx skillmds@latest add ww-w-ai/batch in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Batch safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Batch?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Batch free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

ww-w-ai (@ww-w-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Batch by ww-w-ai — Agent Skill

Name: Batch
Author: ww-w-ai

Batch

Process multiple features or tasks in parallel. Batch execution of PDCA commands across features. Triggers: batch, parallel, bulk, multiple features, 배치, 병렬, 대량 처리, バッチ, 並列, 一括処理, 批量, 并行, 批处理, lote, paralelo, procesamiento masivo, lot, parallèle, traitement en masse, Stapel, parallel, Massenverarbeitung, batch, parallelo, elaborazione di massa

ww-w-ai a1d403b 2.6 KB Updated Sep 17, 2026

File contents

Batch Skill

Process multiple features or tasks in parallel. Execute PDCA commands across multiple features in a single invocation.

Usage

/batch plan user-auth payment-system notification
/batch design user-auth payment-system
/batch analyze user-auth payment-system notification search
/batch report user-auth payment-system

Execution Model

Parse: Extract the command and feature list from arguments
Validate: Check that each feature has prerequisites for the requested command
Execute: Process each feature sequentially, tracking progress via Task Tracker
Report: Output a summary table showing status for each feature

Progress Tracking

Each feature creates a Task Tracker entry:

Task subject: [Batch {command}] {feature}
Status updates as each feature completes
Final summary shows pass/fail per feature

Error Handling

Fail-forward: If one feature fails, remaining features still execute
Error log: Failed features are collected and reported at the end
Retry option: Use --retry-failed to re-run only the failed features

/batch --retry-failed analyze user-auth payment-system

Output Format

Batch Execution Summary
----------------------------------------------
Command: plan
Features: 4 total | 3 success | 1 failed
----------------------------------------------
  user-auth        [OK]   docs/01-plan/features/user-auth.plan.md
  payment-system   [OK]   docs/01-plan/features/payment-system.plan.md
  notification     [OK]   docs/01-plan/features/notification.plan.md
  search           [FAIL] Missing prerequisite: project scope undefined
----------------------------------------------

Feature Discovery

If no features are specified, batch will auto-discover features from:

.pdca-status.json primary and secondary features
docs/01-plan/features/*.plan.md existing plan files
docs/02-design/features/*.design.md existing design files

/batch analyze          # auto-discovers all features
/batch report --all     # explicitly process all known features

Combination with Other Skills

Batch works with any PDCA subcommand and can be combined with loop:

/loop 1h batch analyze user-auth payment-system

---name: batchdescription: Process multiple features or tasks in parallel. Batch execution of PDCA commands across features. Triggers: batch, parallel, bulk, multiple features, 배치, 병렬, 대량 처리, バッチ, 並列, 一括処理, 批量, 并行, 批处理, lote, paralelo, procesamiento masivo, lot, parallèle, traitement en masse, Stapel, parallel, Massenverarbeitung, batch, parallelo, elaborazione di massa---# Batch Skill> Process multiple features or tasks in parallel. Execute PDCA commands across multiple features in a single invocation.## Usage```/batch plan user-auth payment-system notification/batch design user-auth payment-system/batch analyze user-auth payment-system notification search/batch report user-auth payment-system```## Execution Model1. **Parse**: Extract the command and feature list from arguments2. **Validate**: Check that each feature has prerequisites for the requested command3. **Execute**: Process each feature sequentially, tracking progress via Task Tracker4. **Report**: Output a summary table showing status for each feature## Progress TrackingEach feature creates a Task Tracker entry:- Task subject: `[Batch {command}] {feature}`- Status updates as each feature completes- Final summary shows pass/fail per feature## Error Handling- **Fail-forward**: If one feature fails, remaining features still execute- **Error log**: Failed features are collected and reported at the end- **Retry option**: Use `--retry-failed` to re-run only the failed features```/batch --retry-failed analyze user-auth payment-system```## Output Format```Batch Execution Summary----------------------------------------------Command: planFeatures: 4 total | 3 success | 1 failed---------------------------------------------- user-auth [OK] docs/01-plan/features/user-auth.plan.md payment-system [OK] docs/01-plan/features/payment-system.plan.md notification [OK] docs/01-plan/features/notification.plan.md search [FAIL] Missing prerequisite: project scope undefined----------------------------------------------```## Feature DiscoveryIf no features are specified, batch will auto-discover features from:1. `.pdca-status.json` primary and secondary features2. `docs/01-plan/features/*.plan.md` existing plan files3. `docs/02-design/features/*.design.md` existing design files```/batch analyze # auto-discovers all features/batch report --all # explicitly process all known features```## Combination with Other SkillsBatch works with any PDCA subcommand and can be combined with loop:```/loop 1h batch analyze user-auth payment-system```

Frequently asked questions