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

Turns a user request for a coding task into a single actionable plan with atomic steps, following a workflow of scanning context, minimal interaction, and a fixed markdown template…

SKILL 1 file

SKILL.md
Download 
---
name: antigravity-awesome-skills-concise-planning
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 for coding task
  • 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. Use verb-first phrasing for steps.
  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 action items
  • at most 3 open questions
  • include Scope In/Out and Validation

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.
  • Limit open questions to at most 3.

FAILURE MODES

  • May produce non-atomic steps.
  • May exceed the 1-2 question limit.

CAVEATS

Dependencies
  • README.md
  • docs
  • relevant code files
Missing context
  • How the user request and project context (files) are supplied to the model.
Ambiguities
  • The 'When to Use' section references an 'overview' that is not present in the prompt.
  • 'execute the workflow or actions described in the overview' is unclear and self-referential.

QUALITY

OVERALL
0.74
CLARITY
0.75
SPECIFICITY
0.82
REUSABILITY
0.78
COMPLETENESS
0.68

IMPROVEMENT SUGGESTIONS

  • Replace the vague 'When to Use' paragraph with a concise, self-contained trigger condition.
  • Add an explicit 'Input' section describing the expected format of the user request and available files.

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