home / skills / microck / ordinary-claude-skills / create-plan

create-plan skill

/skills_all/create-plan

This skill generates comprehensive implementation plans in Markdown, detailing objectives, tasks, verification criteria, risks, and alternatives for complex

This is most likely a fork of the create-plan skill from antinomyhq
npx playbooks add skill microck/ordinary-claude-skills --skill create-plan

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
4.0 KB
---
name: create-plan
description: Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. All plans MUST be validated using the included validation script. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.
---

# Create Implementation Plan

Generate comprehensive implementation plans that provide strategic guidance without making actual code changes.

## When to Use

- User explicitly requests a plan, roadmap, or implementation strategy
- Complex tasks requiring structured breakdown before implementation
- Need for risk assessment and alternative approach analysis
- Pre-implementation analysis of architectural decisions

## Planning Process

### 1. Initial Assessment

Research the codebase to understand:

- Project structure and organization
- Relevant files and components
- Existing patterns and conventions
- Potential challenges and risks

Use `search` and `read` tools to examine the codebase. Use `sage` if deeper research is required for the use-case. Explicitly cite sources using `filepath:line` format.

### 2. Create Strategic Plan

Generate a Markdown plan file in `plans/` directory with naming: `plans/{YYYY-MM-DD}-{task-name}-v{N}.md`

Example: `plans/2025-11-24-add-auth-v1.md`

### 3. Validate Plan

**MANDATORY:** Run the validation script to ensure the plan meets all requirements:

```bash
./.forge/skills/create-plan/validate-plan.sh plans/{YYYY-MM-DD}-{task-name}-v{N}.md
```

Fix any errors or warnings and re-validate until the plan passes all checks.

### 4. Plan Structure

```markdown
# [Task Name]

## Objective

[Clear statement of goal and expected outcomes]

## Implementation Plan

- [ ] 1. [First task with detailed description and rationale]
- [ ] 2. [Second task with detailed description and rationale]
- [ ] 3. [Third task with detailed description and rationale]

## Verification Criteria

- [Criterion 1: Specific, measurable outcome]
- [Criterion 2: Specific, measurable outcome]

## Potential Risks and Mitigations

1. **[Risk Description]**
   Mitigation: [Specific mitigation strategy]

2. **[Risk Description]**
   Mitigation: [Specific mitigation strategy]

## Alternative Approaches

1. [Alternative 1]: [Brief description and trade-offs]
2. [Alternative 2]: [Brief description and trade-offs]
```

## Critical Requirements

- **ALWAYS validate the plan** using `./.forge/skills/create-plan/validate-plan.sh` after creation
- **ALWAYS use checkbox format** (`- [ ]`) for ALL implementation tasks
- **NEVER use numbered lists** or plain bullet points in Implementation Plan section
- **NEVER write code, code snippets, or code examples** in the plan
- Include clear rationale for each task
- Provide specific, measurable verification criteria
- Document assumptions made for ambiguous requirements
- Focus on strategic "what" and "why", not tactical "how"
- Describe what needs to be done using natural language, not code

## Best Practices

- Make reasonable assumptions when requirements are ambiguous
- Use codebase patterns to infer best practices
- Provide multiple solution paths for complex challenges
- Balance thoroughness with actionability
- Create plans that can be executed step-by-step by implementation agents

## Boundaries

This is a **planning-only** skill:

- ✅ Research codebase and analyze structure
- ✅ Create strategic plans and documentation
- ✅ Assess risks and propose alternatives
- ✅ Describe implementations using natural language
- ❌ Make actual code changes
- ❌ Modify files or create implementations
- ❌ Run tests or build commands
- ❌ Write code, code snippets, or code examples in plans

If user requests implementation work, suggest switching to an implementation agent.

Overview

This skill generates detailed, validated implementation plans for complex tasks and features. It produces Markdown plans with clear objectives, step-by-step checkbox tasks, verification criteria, risk assessments, and alternative approaches.

How this skill works

I analyze the project structure and relevant components, then create a strategic plan file under the plans/ directory named with a date, task name, and version. Every plan uses checkbox-format tasks and includes measurable verification criteria, risks with mitigations, and alternatives. Plans must be validated with the provided validation script and updated until they pass.

When to use it

  • When you explicitly request a plan, roadmap, or implementation strategy for a feature or change.
  • Before implementing a complex feature that needs decomposition into actionable tasks.
  • When you need a documented risk assessment and trade-off analysis to inform decisions.
  • To prepare a hand-off document for implementation teams or agents that will execute the work.

Best practices

  • State clear assumptions for ambiguous requirements so implementers know constraints.
  • Use checkbox-style tasks for every implementation step to enable progress tracking.
  • Provide specific, measurable verification criteria for each major outcome.
  • Run the included validation script and fix all warnings/errors until the plan passes.

Example use cases

  • Designing an authentication feature: produce a stepwise plan, risks, and alternatives for token vs session approaches.
  • Breaking down a cross-service integration into ordered tasks, verification checks, and rollback mitigations.
  • Preparing a migration plan for a data model change with verification criteria and fallback options.
  • Creating a launch roadmap for a major product feature, including staged rollout tasks and risk mitigations.

FAQ

Do you make code changes or run builds?

No. This skill is strictly planning-focused and does not modify code, run tests, or build artifacts.

How is a plan validated?

Plans must be validated using the provided script: run the validate-plan.sh script against the generated plan file and address any errors or warnings until it passes.