OpenAI Create Plan Skill

OpenAI Create Plan Skill

Defines a read-only agent skill that turns a coding request into one concise, actionable plan in the final message.

Skill files1 file
SKILL.md74 lines
1
---
2
name: create-plan
3
description: Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.
4
metadata:
5
short-description: Create a plan
6
---
7
8
# Create Plan
9
10
## Goal
11
12
Turn a user prompt into a **single, actionable plan** delivered in the final assistant message.
13
14
## Minimal workflow
15
16
Throughout the entire workflow, operate in read-only mode. Do not write or update files.
17
18
1. **Scan context quickly**
19
- Read `README.md` and any obvious docs (`docs/`, `CONTRIBUTING.md`, `ARCHITECTURE.md`).
20
- Skim relevant files (the ones most likely touched).
21
- Identify constraints (language, frameworks, CI/test commands, deployment shape).
22
23
2. **Ask follow-ups only if blocking**
24
- Ask **at most 1–2 questions**.
25
- Only ask if you cannot responsibly plan without the answer; prefer multiple-choice.
26
- If unsure but not blocked, make a reasonable assumption and proceed.
27
28
3. **Create a plan using the template below**
29
- Start with **1 short paragraph** describing the intent and approach.
30
- Clearly call out what is **in scope** and what is **not in scope** in short.
31
- Then provide a **small checklist** of action items (default 6–10 items).
32
- Each checklist item should be a concrete action and, when helpful, mention files/commands.
33
- **Make items atomic and ordered**: discovery → changes → tests → rollout.
34
- **Verb-first**: “Add…”, “Refactor…”, “Verify…”, “Ship…”.
35
- Include at least one item for **tests/validation** and one for **edge cases/risk** when applicable.
36
- If there are unknowns, include a tiny **Open questions** section (max 3).
37
38
4. **Do not preface the plan with meta explanations; output only the plan as per template**
39
40
## Plan template (follow exactly)
41
42
```markdown
43
# Plan
44
45
<1–3 sentences: what we’re doing, why, and the high-level approach.>
46
47
## Scope
48
- In:
49
- Out:
50
51
## Action items
52
[ ] <Step 1>
53
[ ] <Step 2>
54
[ ] <Step 3>
55
[ ] <Step 4>
56
[ ] <Step 5>
57
[ ] <Step 6>
58
59
## Open questions
60
- <Question 1>
61
- <Question 2>
62
- <Question 3>
63
```
64
65
## Checklist item guidance
66
Good checklist items:
67
- Point to likely files/modules: src/..., app/..., services/...
68
- Name concrete validation: “Run npm test”, “Add unit tests for X”
69
- Include safe rollout when relevant: feature flag, migration plan, rollback note
70
71
Avoid:
72
- Vague steps (“handle backend”, “do auth”)
73
- Too many micro-steps
74
- Writing code snippets (keep the plan implementation-agnostic)
@OpenSourceBuffGuy

I find openly licensed prompts and post them here.

0 followers · 2,873 prompts

More by @OpenSourceBuffGuy

See all
Ethereum Developer prompt image

Ethereum Developer

Asks the AI to act as an experienced Ethereum developer who writes a Solidity smart contract for an on-chain messenger with public reads and owner-only writes.

act-as, crypto, coding

1 view
Linux Terminal prompt image

Linux Terminal

Makes the AI act as a Linux terminal that replies to each typed command with only its output inside one code block.

simulator, linux, coding

5 views
English Translator and Improver prompt image

English Translator and Improver

Turns the AI into an English translator and editor that detects the input language and returns only an improved, more literary English version.

act-as, translation, rewriting, proofreading

2 views

Reviews

Loading reviews…

Discussion

Loading comments…