Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Conversation Context PRD Synthesizer

agent planning skill risk: medium

Conversation Context PRD Synthesizer

Synthesizes a PRD from the current conversation context and codebase without interviewing the user, following a defined process and template, then publishes it to the project issue…

  • External action: high

SKILL 1 file

SKILL.md
---
name: to-prd
description: "Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context."
---
This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know.

The issue tracker and triage label vocabulary should have been provided to you — run `/setup-matt-pocock-skills` if not.

## Process

1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the PRD, and respect any ADRs in the area you're touching.

2. Sketch out the major modules you will need to build or modify to complete the implementation. Actively look for opportunities to extract deep modules that can be tested in isolation.

A deep module (as opposed to a shallow module) is one which encapsulates a lot of functionality in a simple, testable interface which rarely changes.

Check with the user that these modules match their expectations. Check with the user which modules they want tests written for.

3. Write the PRD using the template below, then publish it to the project issue tracker. Apply the `ready-for-agent` triage label - no need for additional triage.

<prd-template>

## Problem Statement

The problem that the user is facing, from the user's perspective.

## Solution

The solution to the problem, from the user's perspective.

## User Stories

A LONG, numbered list of user stories. Each user story should be in the format of:

1. As an <actor>, I want a <feature>, so that <benefit>

<user-story-example>
1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending
</user-story-example>

This list of user stories should be extremely extensive and cover all aspects of the feature.

## Implementation Decisions

A list of implementation decisions that were made. This can include:

- The modules that will be built/modified
- The interfaces of those modules that will be modified
- Technical clarifications from the developer
- Architectural decisions
- Schema changes
- API contracts
- Specific interactions

Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.

Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.

## Testing Decisions

A list of testing decisions that were made. Include:

- A description of what makes a good test (only test external behavior, not implementation details)
- Which modules will be tested
- Prior art for the tests (i.e. similar types of tests in the codebase)

## Out of Scope

A description of the things that are out of scope for this PRD.

## Further Notes

Any further notes about the feature.

</prd-template>

REQUIRED CONTEXT

  • current conversation context
  • codebase understanding
  • project issue tracker
  • triage label vocabulary

ROLES & RULES

  1. Do NOT interview the user — just synthesize what you already know.
  2. Use the project's domain glossary vocabulary throughout the PRD.
  3. Respect any ADRs in the area you're touching.
  4. Check with the user that these modules match their expectations.
  5. Check with the user which modules they want tests written for.
  6. Do NOT include specific file paths or code snippets.
  7. Apply the `ready-for-agent` triage label - no need for additional triage.

EXPECTED OUTPUT

Format
structured_report
Schema
markdown_sections · Problem Statement, Solution, User Stories, Implementation Decisions, Testing Decisions, Out of Scope, Further Notes
Constraints
  • use provided prd-template sections exactly
  • apply ready-for-agent triage label after publishing
  • do not include file paths or code snippets unless encoding a precise decision from a prototype

SUCCESS CRITERIA

  • Synthesize PRD solely from current conversation context and codebase understanding
  • Use domain glossary and respect ADRs
  • Identify deep modules and check expectations with user
  • Follow the exact PRD template structure
  • Publish to issue tracker with ready-for-agent label

FAILURE MODES

  • May include specific file paths or code snippets despite the rule
  • May produce incomplete user stories list

EXAMPLES

Includes one example of a correctly formatted user story.

CAVEATS

Dependencies
  • Requires current conversation context
  • Requires codebase understanding
  • Requires issue tracker and triage label vocabulary (run /setup-matt-pocock-skills if missing)
Missing context
  • Confirmation that /setup-matt-pocock-skills has already been run (issue tracker details and triage labels)
Ambiguities
  • Step 2 instructs to 'Check with the user' about modules, which conflicts with the explicit rule 'Do NOT interview the user — just synthesize what you already know.'

QUALITY

OVERALL
0.79
CLARITY
0.82
SPECIFICITY
0.88
REUSABILITY
0.78
COMPLETENESS
0.72

IMPROVEMENT SUGGESTIONS

  • Remove or reconcile the 'Check with the user' sentences in step 2 so they align with the 'Do NOT interview the user' directive.
  • Add a short note at the top clarifying whether the skill should ever ask clarifying questions or must remain fully autonomous.

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