メニュー
This command should be used to generate an implementation plan with task breakdown, dependencies, and complexity estimates. Fourth stage of the Kimchi planning pipeline. Produces .kimchi/PLAN.md.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | kimchi:generate |
| description | This command should be used to generate an implementation plan with task breakdown, dependencies, and complexity estimates. Fourth stage of the Kimchi planning pipeline. Produces .kimchi/PLAN.md. |
<command_purpose> Create a task breakdown from requirements and research, with dependencies, complexity estimates, and traceability to requirements. </command_purpose>
Read .kimchi/CONTEXT.md, .kimchi/REQUIREMENTS.md, and .kimchi/RESEARCH.md. If any are missing, tell the user which prerequisite to run.
For each v1 requirement, identify the implementation tasks needed:
Build a dependency graph:
| Complexity | Characteristics |
|---|---|
| S (Small) | Single file, clear pattern to follow, < 100 lines |
| M (Medium) | Multiple files, some decisions required, 100-300 lines |
| L (Large) | Architectural decisions, new patterns, > 300 lines. Consider splitting. |
If any task is L, consider splitting it into smaller tasks.
Write to .kimchi/PLAN.md:
# Plan: [Feature Name]
**Generated:** [today's date]
**Source:** .kimchi/CONTEXT.md, .kimchi/REQUIREMENTS.md, .kimchi/RESEARCH.md
## Task Overview
| ID | Task | Complexity | Depends On | Requirements |
|----|------|------------|------------|--------------|
| 001 | [Task title] | S | - | [REQ-ID] |
| 002 | [Task title] | M | - | [REQ-ID] |
| 003 | [Task title] | M | 002 | [REQ-ID] |
## Dependency Graph
[ASCII dependency graph showing parallel and sequential tasks]
## Task Details
### Task 001: [Title]
**Complexity:** S
**Requirements:** [REQ-ID]
**Depends On:** None
[Description of what this task does]
**Deliverables:**
- [What files/changes will be produced]
**Context Needed:**
- [What existing code the agent needs to see]
---
### Task 002: [Title]
**Complexity:** M
**Requirements:** [REQ-ID]
**Depends On:** None
[Description]
**Deliverables:**
- [List]
**Context Needed:**
- [List]
---
[... additional tasks ...]
## Execution Strategy
**Parallel groups (tasks with no interdependencies):**
- Wave 1: [tasks that can start immediately]
- Wave 2: [tasks that depend on Wave 1]
- Wave 3: [tasks that depend on Wave 2]
**Integration tests:** Final task after all others complete
Report: "Plan generated. Saved to .kimchi/PLAN.md"
Suggest: "Run /kimchi:review for multi-persona critique, or /kimchi:refine to skip review."
Convert the kimchi plugin into OpenCode and Codex compatible formats using the bundled converter CLI. Requires bun runtime.
This command should be used to run the Kimchi planning pipeline through refinement, transforming a vague idea into a draft plan ready for cross-model analysis. Orchestrates 6 stages: clarify, requirements, research, generate, review, refine. Use --full-auto to also run beads + validate after manual revise/synthesize.
Use when executing a bead task. Detects orchestration mode (ACFS or GasTown) from .beads/manifest.yaml and enforces the appropriate execution discipline.
This command should be used to convert the final plan into standalone bead YAML task specifications for multi-agent execution. Ninth stage of the Kimchi planning pipeline. Produces .beads/ directory. Supports both ACFS and GasTown orchestration modes.
This command should be used to run the Kimchi self-improvement system. Observes execution outcomes, proposes incremental improvements to skills/validators/personas, validates against history, and applies with versioning.
This command should be used to clear the Kimchi working directory (.kimchi/) and start fresh. Preserves .beads/ directory. Use when starting a new planning session or recovering from a bad state.