agent planning skill risk: low

Concise Coding Task Planner

Instructs the model to convert a user coding request into a single actionable plan with atomic steps by scanning context, asking at most 1-2 questions, and outputting a fixed markd…

SKILL 1 file

SKILL.md

Download

---
name: 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

README.md
docs
relevant code files

OPTIONAL CONTEXT

language
frameworks
tests

ROLES & RULES

Ask at most 1–2 questions and only if truly blocking.
Make reasonable assumptions for non-blocking unknowns.
Each step should be a single logical unit of work.
Use verb-first phrasing for action items.
Name specific files or modules when possible.
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.

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 at least one validation/testing item

SUCCESS CRITERIA

Turn a user request into a single actionable plan with atomic steps.
Identify constraints from context.
Include at least one validation/testing item.

CAVEATS

Dependencies

README.md
docs
relevant code files

Missing context

The actual user request or coding task to be planned

Ambiguities

The 'When to Use' section refers to 'the overview' which is not present in the prompt.
'Scan Context' assumes existence of README.md and code files without specifying access method.

QUALITY

OVERALL: 0.80
CLARITY: 0.82
SPECIFICITY: 0.78
REUSABILITY: 0.85
COMPLETENESS: 0.75

IMPROVEMENT SUGGESTIONS

Replace the vague 'When to Use' sentence with explicit trigger conditions such as 'Apply when the user explicitly requests a plan for a coding task.'
Add a required input field at the top: 'User request: <the coding task description>'

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.