architecture-fit-check
Skill1 starsChanged 25 days agoMITView on GitHub
Tests solution architecture fitness when a design decision needs structured challenge before approval or build.
In this repository133 other files it gives its agents.
- templates/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- access-control-auditSkill
- ai-opportunity-scanSkill
- ai-policy-writerSkill
- annual-budget-builderSkill
- application-portfolio-mapSkill
- automation-backlogSkill
- benefits-realisationSkill
- board-paperSkill
- bottleneck-removalSkill
- break-even-modelSkill
- budget-variance-analystSkill
- business-continuity-plannerSkill
- business-valuationSkill
- capacity-planningSkill
- case-study-writerSkill
- cash-flow-forecastSkill
- change-adoptionSkill
- change-impactSkill
- channel-profitabilitySkill
- churn-cohort-analysisSkill
- client-handoverSkill
- client-kickoffSkill
- client-profitabilitySkill
- client-relationship-managerSkill
- closeout-packSkill
- compensation-bandsSkill
- competitor-mapperSkill
- contribution-marginSkill
- cost-structure-analystSkill
- crisis-communicationsSkill
- customer-insight-synthesiserSkill
- customer-interview-designerSkill
- customer-journey-mapSkill
- customer-segmenterSkill
- cyber-risk-assessmentSkill
- dashboard-requirements-plannerSkill
- data-lineage-mapperSkill
- data-quality-auditSkill
- decision-logSkill
- decision-memoSkill
- decision-rightsSkill
- delivery-model-selectorSkill
- demand-validatorSkill
- discount-governanceSkill
- discovery-call-facilitationSkill
- discovery-call-prepSkill
- discovery-question-designSkill
- discovery-synthesisSkill
- engagement-outcomesSkill
- evidence-synthesiserSkill
- executive-dashboardSkill
- executive-summarySkill
- fee-settingSkill
- financial-statement-diagnosticSkill
- fundraising-readinessSkill
- funnel-diagnosticSkill
- go-to-marketSkill
- governance-designerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use at design gates, before major commitments, or when an existing platform struggles with changing demand.
- Distinctive: line 20
Test fit across capacity, resilience, security, maintainability and interoperability.
- Distinctive: line 21
Run scenario checks for peak demand, component failure, recovery and future change.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Architecture Fit Check
When to use it
Use at design gates, before major commitments, or when an existing platform struggles with changing demand.
What Claude needs
client-context.mdfor business background- Business outcomes and functional requirements
- Architecture diagrams, interfaces and data flows
- Non-functional needs, constraints and design principles
Method
- Translate outcomes into measurable functional and non-functional requirements.
- Map components, trust boundaries, integrations, data stores and failure paths.
- Test fit across capacity, resilience, security, maintainability and interoperability.
- Run scenario checks for peak demand, component failure, recovery and future change.
- Record trade-offs and gaps in an architecture decision log.
- Recommend accept, amend, prototype or reject with conditions and evidence needs.
Output format
Provide a fit scorecard, scenario findings, gap register and decision record. Include conditions, owners and evidence required before the next gate.
Quality checks
- Requirements are testable and linked to business outcomes.
- Failure modes and operational support are examined.
- Trade-offs are explicit rather than hidden in an overall score.
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.

