review-functional-design
Skill8 starsChanged 2 months agoMITView on GitHub
Review an existing functional design against its modeling Spec and canonical quality Rule before technical design begins. Evaluative atomic skill; outputs findings without rewriting.
In this repository77 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- archive-milestoneSkill
- assess-product-opportunitySkill
- automate-testsSkill
- bump-versionSkill
- capture-work-itemsSkill
- commit-workSkill
- competitive-researchSkill
- consume-nats-messageSkill
- decontextualize-textSkill
- deep-researchSkill
- define-docs-normsSkill
- define-missionSkill
- define-north-starSkill
- define-roadmapSkill
- define-strategic-pillarsSkill
- define-visionSkill
- deliver-featureSkill
- design-strategic-goalsSkill
- eli5Skill
- establish-delivery-workflowSkill
- execute-delivery-workflowSkill
- generate-agent-entrySkill
- generate-github-workflowSkill
- generate-standard-readmeSkill
- inspect-artifact-stateSkill
- integrate-branchesSkill
- manage-secretSkill
- map-item-dependenciesSkill
- market-researchSkill
- orchestrate-code-reviewSkill
- orchestrate-governance-stepSkill
- orchestrate-repair-loopSkill
- orchestrate-repair-requirements-loopSkill
- orchestrate-roadmap-planningSkill
- plan-milestonesSkill
- plan-nextSkill
- policy-researchSkill
- ponytailSkill
- prepare-presales-responseSkill
- prepare-version-notesSkill
- prioritize-backlogSkill
- product-opportunity-analysisSkill
- promote-roadmap-itemsSkill
- publish-nats-messageSkill
- record-milestone-achievementSkill
- redeploy-localSkill
- refine-skill-designSkill
- review-architectureSkill
- review-codebaseSkill
- review-diffSkill
- review-dotnetSkill
- review-error-surfacingSkill
- review-goSkill
- review-implementation-alignmentSkill
- review-javaSkill
- review-observabilitySkill
- review-orm-usageSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
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 26
After functional design is drafted and before technical design
- Distinctive: line 27
After business workflow, state or permission changes
- Distinctive: line 28
Before accepting a functional design imported from another system
- Distinctive: line 33
Verify artifact identity, approved parent, required sections and all conditional sections, including UI and interaction flow, against the …
- Distinctive: line 34
Check workflow closure, exception behavior, business boundaries and acceptance traceability without introducing technical implementation …
- Distinctive: line 44
Do not rewrite the design or requirement.
- Distinctive: line 45
Do not demand database, API or deployment detail in this layer.
- Distinctive: line 46
Do not restate business rules that should be cited from the requirement.
- Distinctive: line 59
If two roles have different operation permissions and no permission matrix exists, emit the matching conditional-section finding.
- Distinctive: line 63
If the input is an ADR-authorized refactor with no user-visible behavior, stop and redirect to technical design.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Skill: Review Functional Design
Purpose
Evaluate an existing functional design against functional-design-modeling and functional-design-quality. This is a pre-coding business-behavior gate, not an architecture review and not a meta-skill.
Core objective
Determine whether business modules, workflows, states, permissions, exceptions and acceptance criteria are complete and traceable enough for technical design.
Scope boundaries
This Skill reviews one functional-design artifact and its requirement references. It does not create the design, make technical choices, review implementation or aggregate other Skills.
Use cases
- After functional design is drafted and before technical design
- After business workflow, state or permission changes
- Before accepting a functional design imported from another system
Behavior
- Load the active modeling Spec and quality Rule.
- Verify artifact identity, approved parent, required sections and all conditional sections, including UI and interaction flow, against the loaded Spec and Rule. A sufficient existing design needs no external reference. Use the UI design decisions guide for reference evidence and handoff context.
- Check workflow closure, exception behavior, business boundaries and acceptance traceability without introducing technical implementation detail.
- Emit one finding per violation with category
functional-design-qualityand a precise section or flow/state location. - Report zero findings as ready for technical design, without invoking it.
Input and output
Input is one existing functional-design path or full content. Output follows findings-list.
Restrictions
- Do not rewrite the design or requirement.
- Do not demand database, API or deployment detail in this layer.
- Do not restate business rules that should be cited from the requirement.
Self-Check
- Both canonical assets were loaded.
- Conditional state, permission and UI sections were evaluated, including legitimate UI skip reasons.
- Every finding is grounded and uses category
functional-design-quality. - No technical-design criterion was introduced.
Examples
Example 1: approval roles differ
If two roles have different operation permissions and no permission matrix exists, emit the matching conditional-section finding.
Example 2: purely technical refactor
If the input is an ADR-authorized refactor with no user-visible behavior, stop and redirect to technical design; a functional design is not required.
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.