一键导入
2-create-plan
Creates detailed implementation plans through an interactive, iterative process.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Creates detailed implementation plans through an interactive, iterative process.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when reviewing a PR in camunda/camunda that touches AGENTS.md, skills under .claude/skills/, the way the project uses ADRs, or the way the project uses architecture docs (not new ADRs or architecture docs themselves) — i.e., Agent-Ready initiative PRs
Use when Nico asks to write his daily stand-up, stand-up message, Geekbot reply, or to summarize yesterday's work for stand-up. Produces both "Yesterday" and "Today" sections in Nico's house style, organized by his current P1/P2/P3 epics with everything else under "Also". Posted in Slack
Use when user shares an error message, stack trace, or log snippet to investigate — or when investigating an incident that has a concrete error artifact (log line, exception, failed assertion). Skip when the incident has no error artifact, e.g. performance regressions, throughput/latency drops, capacity issues, or behavioral discrepancies without logs.
Refines an existing skill for effectiveness (does it achieve its goal?), efficiency (tokens spent doing so), and discoverability (does Claude trigger it when relevant?). Use when the user wants to optimize, refactor, audit, or tighten a skill, or invokes optimize-skill.
Produce a deterministic local reproducer for a bug described by the user. Use when the user shares an incident, bug report, or behavior description and wants to reproduce it locally. Output is a reproducer (test or script) for later root-cause analysis — RCA itself is out of scope.
Conducts a comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.
| name | 2_create_plan |
| description | Creates detailed implementation plans through an interactive, iterative process. |
You are tasked with creating detailed implementation plans through an interactive, iterative process. You should be skeptical, thorough, and work collaboratively with the user to produce high-quality technical specifications.
When this command is invoked, respond with:
I'll help you create a detailed implementation plan. Let me start by understanding what we're building.
Please provide:
1. The task description or requirements
2. Any relevant context, constraints, or specific requirements
3. Links to related research or previous implementations
I'll analyze this information and work with you to create a comprehensive plan.
Then wait for the user's input.
Read all mentioned files immediately and FULLY
Spawn initial research tasks to gather context:
Present informed understanding and focused questions: Based on research, present findings and ask only questions that require human judgment
Once aligned on approach:
Here's my proposed plan structure:
## Overview
[1-2 sentence summary]
## Implementation Phases:
1. [Phase name] - [what it accomplishes]
2. [Phase name] - [what it accomplishes]
3. [Phase name] - [what it accomplishes]
Does this phasing make sense?
Check existing plan files to determine next sequence number, then write the plan to thoughts/plans/NNN_{descriptive_name}.md where NNN is a 3-digit sequential number (001, 002, etc.):
# [Feature/Task Name] Implementation Plan
## Overview
[Brief description of what we're implementing and why]
## Current State Analysis
[What exists now, what's missing, key constraints discovered]
## Desired End State
[Specification of the desired end state and how to verify it]
## What We're NOT Doing
[Explicitly list out-of-scope items]
## Implementation Approach
[High-level strategy and reasoning]
## Phase 1: [Descriptive Name]
### Overview
[What this phase accomplishes]
### Changes Required:
#### 1. [Component/File Group]
**File**: `path/to/file.ext`
**Changes**: [Summary of changes]
```[language]
// Specific code to add/modify
```
npm testnpm run typechecknpm run lint[Similar structure...]
[Any performance implications or optimizations needed]
[If applicable, how to handle existing data/systems]
### Step 5: Review and Iterate
1. Save the plan and present location to user
2. Iterate based on feedback
3. Continue refining until satisfied
## Important Guidelines
1. **Be Skeptical**: Question vague requirements, identify issues early
2. **Be Interactive**: Get buy-in at each major step
3. **Be Thorough**: Include specific file paths and measurable success criteria
4. **Be Practical**: Focus on incremental, testable changes
5. **Track Progress**: Use TodoWrite throughout planning
6. **No Open Questions**: Resolve all questions before finalizing plan