Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Concise Coding Task Planner

agent planning skill risk: low

Concise Coding Task Planner

Transforms a user request for a coding task into a single actionable plan with approach, scope, 6-10 atomic verb-first action items, and validation steps, after scanning context an…

SKILL 1 file

SKILL.md
Download 
---
name: antigravity-awesome-skills-concise-planning-0c27c6e9
description: "Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist."
---
# Concise Planning

## Goal

Turn a user request into a **single, actionable plan** with atomic steps.

## Workflow

### 1. Scan Context

- Read `README.md`, docs, and relevant code files.
- Identify constraints (language, frameworks, tests).

### 2. Minimal Interaction

- Ask **at most 1–2 questions** and only if truly blocking.
- Make reasonable assumptions for non-blocking unknowns.

### 3. Generate Plan

Use the following structure:

- **Approach**: 1-3 sentences on what and why.
- **Scope**: Bullet points for "In" and "Out".
- **Action Items**: A list of 6-10 atomic, ordered tasks (Verb-first).
- **Validation**: At least one item for testing.

## Plan Template

```markdown
# Plan

<High-level approach>

## Scope

- In:
- Out:

## Action Items

[ ] <Step 1: Discovery>
[ ] <Step 2: Implementation>
[ ] <Step 3: Implementation>
[ ] <Step 4: Validation/Testing>
[ ] <Step 5: Rollout/Commit>

## Open Questions

- <Question 1 (max 3)>
```

## Checklist Guidelines

- **Atomic**: Each step should be a single logical unit of work.
- **Verb-first**: "Add...", "Refactor...", "Verify...".
- **Concrete**: Name specific files or modules when possible.

## When to Use
This skill is applicable to execute the workflow or actions described in the overview.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

REQUIRED CONTEXT

  • user request
  • README.md
  • docs
  • relevant code files

ROLES & RULES

  1. Read README.md, docs, and relevant code files.
  2. Identify constraints (language, frameworks, tests).
  3. Ask at most 1–2 questions and only if truly blocking.
  4. Make reasonable assumptions for non-blocking unknowns.
  5. Use the following structure for the plan.
  6. Each step should be a single logical unit of work.
  7. Each step should be verb-first.
  8. Name specific files or modules when possible.
  9. Use this skill only when the task clearly matches the scope described above.
  10. Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  11. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

EXPECTED OUTPUT

Format
markdown
Schema
markdown_sections · Plan, Scope, Action Items, Open Questions
Constraints
  • use exact Plan Template structure
  • 6-10 atomic verb-first tasks
  • at most 1-2 clarifying questions if blocking
  • include Approach, Scope, Action Items, Validation, Open Questions

SUCCESS CRITERIA

  • Turn a user request into a single, actionable plan with atomic steps.
  • Produce 6-10 atomic, ordered, verb-first tasks.
  • Include at least one validation/testing item.
  • Ask at most 1-2 questions only if blocking.

FAILURE MODES

  • May produce non-atomic or non-ordered steps.
  • May exceed the question limit.
  • May omit required template sections.

CAVEATS

Dependencies
  • README.md
  • docs
  • relevant code files
Missing context
  • How the user request and codebase context are supplied to the prompt.
  • Whether the prompt expects an existing project or can handle green-field tasks.
Ambiguities
  • Workflow step 1 assumes README.md and docs exist without specifying fallback behavior.
  • Template uses <High-level approach> while instructions say 'Approach: 1-3 sentences' (minor mismatch).
  • Does not specify how or when the 1-2 clarifying questions should be output.

QUALITY

OVERALL
0.79
CLARITY
0.82
SPECIFICITY
0.78
REUSABILITY
0.75
COMPLETENESS
0.80

IMPROVEMENT SUGGESTIONS

  • Add an explicit 'Input' section describing the expected user message and any attached files.
  • Align the Plan Template heading with the 'Approach' instruction for consistency.
  • Add a short rule for what to output when critical files (README, docs) are absent.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT