validation-guard
Skill0 starsChanged 7 months agoMITView on GitHub
As a product quality guard, perform rigorous logical verification and risk assessment on product decisions, designs, and specifications.
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 19
Logical Closure: Do all User Stories have corresponding Acceptance Criteria (AC)?
≈ “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
Validation Guard: Product Quality Guard Procedures
Mimic unit testing in R&D to perform automated verification of product logic.
Checklist
- Desirability Check — Is research evidence from
docs/pmpowers/discovery/referenced? - Viability Check — Does this solution directly support the North Star Metric?
- Feasibility Check — Do current team resources allow for this? Are there major technical obstacles?
- Usability Check — Is the user path clear? Are exception handlings defined?
Logical Audit Standards
- Logical Closure: Do all User Stories have corresponding Acceptance Criteria (AC)?
- Edge Case Coverage: Are extreme cases (Edge Cases) defined?
- Resource Waste: Is there over-design for the sake of features?
Output Report
The guard must output a clear "Audit Report":
- Status: Pass / Fail
- Risks: Identified potential risk points.
- Action: Recommended improvement measures.
In this repository34 other files it gives its agents.
- agile-scrum-masterySkill
- artifact-provenanceSkill
- brainstormingSkill
- business-acumenSkill
- cross-functional-collaborationSkill
- customer-discoverySkill
- customer-empathySkill
- data-analysisSkill
- gtm-launch-managementSkill
- lean-experimentationSkill
- market-researchSkill
- metrics-definitionSkill
- negotiation-conflict-resolutionSkill
- north-star-metricSkill
- opportunity-mappingSkill
- outcome-ownershipSkill
- presentation-storytellingSkill
- prioritizationSkill
- problem-solvingSkill
- product-definitionSkill
- product-vision-strategySkill
- project-managementSkill
- prototypingSkill
- qa-quality-mindsetSkill
- roadmappingSkill
- spec-driven-designSkill
- stakeholder-managementSkill
- subagent-driven-discoverySkill
- technical-acumenSkill
- user-interviewingSkill
- using-pmpowersSkill
- ux-design-awarenessSkill
- writing-plansSkill
- written-communicationSkill
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.