initial-software-design-analysis
Skill15 starsChanged 5 months agoCC0-1.0View on GitHub
Produces a first-pass architecture and design review covering structure, maintainability, and scalability. Use when onboarding to or assessing the design of a codebase.
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 14
If no target path is given above, review the entire codebase.
- Distinctive: line 29
Create an architecture diagram showing:
- Distinctive: line 54
Prefer minimal, drop-in fix snippets over prose.
- Distinctive: line 56
Do not invent files or functions that aren’t present.
- Distinctive: line 58
Write this into a markdown file and place it in the audits/ folder.
≈ “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
Target: $ARGUMENTS
If no target path is given above, review the entire codebase.
Initial Software Design Analysis:
Analyze the project architecture and identify:
Evaluate:
- Is there clear separation of concerns?
- Which architectural pattern is used (MVC, Layered, Microservices)?
- Are there any God objects or modules doing too much?
- Is the dependency flow clean (no circular dependencies)?
- Rate the modularity (1-10) with justification
Create an architecture diagram showing:
- Layer dependencies
- Data flow
- External service integrations
- Potential bottlenecks
Identify anti-patterns:
- Spaghetti code
- Copy-paste programming
- God classes/modules
- Tight coupling
- Missing abstractions
Provide:
A structured finding report
A scale of 1/10 on how important each finding is
Remediation: precise code-level fix or config change (snippets welcome) if possible
Constraints & style:
Be concrete and cite exact code locations and identifiers.
Prefer minimal, drop-in fix snippets over prose.
Do not invent files or functions that aren’t present; if context is missing, mark as Unable to verify and say what code would prove it.
Write this into a markdown file and place it in the audits/ folder.
In this repository21 other files it gives its agents.
- api-and-infrastructureSkill
- authentication-flow-reviewSkill
- authorization-implementationSkill
- business-logic-vulnerabilitiesSkill
- code-duplication-detectionSkill
- code-quality-metrics-standardsSkill
- comprehensive-security-reportSkill
- database-securitySkill
- design-pattern-implementationSkill
- error-handling-resilienceSkill
- exception-flow-analysisSkill
- file-handling-business-logicSkill
- initial-security-analysisSkill
- input-validationSkill
- logging-monitoringSkill
- readability-and-namingSkill
- resilience-fault-toleranceSkill
- secrets-management-auditSkill
- session-cookie-securitySkill
- solid-principlesSkill
- testing-implementationSkill
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.