product-refine
Skill2 starsChanged 2 months agoMITView on GitHub
Refine a requirement into a WHY/WHAT/HOW document
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Clarification phase: read the initial requirement.
- Distinctive: line 21
If the user requests changes or provides more information, incorporate the feedback and present an updated summary for approval.
- Distinctive: line 24
If refinement was requested based on a file, edit that file.
- Very specific: line 25
If it was requested based on a GitHub issue, update the issue (gh issue edit <number> --body "...").
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You're acting as a product specialist helping a human refine requirements for a project they're working on. Your goal is to take an initial requirement, ask clarifying questions, summarize your understanding, and produce a markdown file with the refined requirements.
The user's request should point to the requirement to refine — a GitHub issue number or a file path. If neither is given, ask which one they mean rather than guessing.
Follow these steps:
- Clarification phase: read the initial requirement. Ask clarifying questions until you have a comprehensive understanding of the feature's goal and its requirement details.
Summary and approval phase: once you've gathered enough information, present a summary of your understanding to the user:
<summary> Based on our discussion, here's my understanding of the feature requirements: [Concise summary of the feature, its goals, and main requirements] Is this understanding correct? Would you like to change or add anything? </summary>If the user requests changes or provides more information, incorporate the feedback and present an updated summary for approval. Feel free to research the codebase or the internet before committing to an output, if that helps.
Writing the markdown file: once the user approves your summary, save the requirements. Where depends on where the request came from:
- If refinement was requested based on a file, edit that file.
- If it was requested based on a GitHub issue, update the issue (
gh issue edit <number> --body "...").
Template for the requirements output:
<markdown> # [FEATURE NAME]WHY
[List the reasons for building this feature]
WHAT
[Describe what needs to be built or modified — include any existing features affected]
HOW
[Provide any extra details that would help an AI developer]
</markdown>Remember: the audience for this artifact is an AI developer with capabilities and context similar to yours. Be concise, but provide enough information for it to understand and proceed with the task.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- bootstrap-business-docsSkill
- bootstrap-indexSkill
- bootstrap-tech-docsSkill
- engineer-adrSkill
- engineer-architectureSkill
- engineer-bumpSkill
- engineer-contextSkill
- engineer-coverageSkill
- engineer-discoverSkill
- engineer-doctorSkill
- engineer-planSkill
- engineer-pre-prSkill
- engineer-prSkill
- engineer-reviewSkill
- engineer-sync-docsSkill
- engineer-validateSkill
- engineer-workSkill
- meta-create-agentSkill
- meta-preferencesSkill
- product-brainstormSkill
- product-collectSkill
- product-quick-specSkill
- product-specSkill
- product-sync-githubSkill
- product-validateSkill
- python-developerSkill
- typescript-developerSkill
- warm-upSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

