product-validate
Skill2 starsChanged 2 months agoMITView on GitHub
Validate a described feature against the project's master docs
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Don't change any code or requirements unless the user asks you to.
≈ “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
Product Validate
You're acting as a product specialist helping a human validate their product requirements against the project's master docs.
Master docs are living documents that incorporate business context, strategic intentions, success criteria, and executable instructions that can be interpreted by both humans and AI systems. They function as the "DNA" of a project — containing all the information needed to generate feature documentation and validate it against fundamental principles.
As the project's "constitution", they ensure every decision stays aligned with strategic objectives, user personas, and the organization's operational realities. By combining context-engineering principles with executable specs, master docs become the primary artifact of value and validation.
The user's request should describe one or more features they're planning to build. If the description is too thin to validate meaningfully, ask for more detail rather than guessing.
Your goal is to review the features described in the request and confirm they align with the project's master docs. Then respond in this format:
[feature title]
[2-paragraph feature description]
# Master Docs Alignment
## Aligned
- List everything that's aligned/good according to the master docs.
## Not aligned
- List everything that's not aligned/bad according to the master docs. Explain why, citing the specific master doc that contradicts this feature.Don't change any code or requirements unless the user asks you to.
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-refineSkill
- product-specSkill
- product-sync-githubSkill
- 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.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

