CtrlK
BlogDocsLog inGet started
Tessl Logo

mcclowes/ai-aware-code-structure

Use when deciding how to organise code in an AI-assisted codebase — whether to split or merge a file, where to draw module boundaries, how big a file should get, whether to separate logic from rendering/styles/data, whether to use barrel/index re-export files, or where types and test files should live. Triggers on "should I split this file", "this file is getting too big", "separate concerns", "where should this code live", "are barrel files worth it", "central types file or co-locate", "colocate tests or a tests folder", reviewing or refactoring file/module organisation, structuring a new component or feature, or any architecture decision where part of the audience is an AI coding agent. Apply this whenever someone is choosing how to lay code out across files and an LLM will be reading or editing it, even if they only say "refactor this" or "clean up the structure" without mentioning AI.

83

1.54x
Quality

87%

Does it follow best practices?

Impact

82%

1.54x

Average score across 9 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

criteria.jsonevals/scenario-8/

{
  "context": "A 550-line helpers.ts holds several unrelated concerns and the user invokes 'big files are fine for agents' to justify leaving it. The criteria check whether the answer recommends splitting on clean concern boundaries and corrects the misapplied defense.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Recommends splitting",
      "description": "Clearly recommends splitting the file and does NOT advise keeping it as one file",
      "max_score": 8
    },
    {
      "name": "Justified by concerns and/or ceiling",
      "description": "Justifies the split by multiple independent concerns AND/OR exceeding the ~300-line ceiling, not blind line count",
      "max_score": 6
    },
    {
      "name": "Clean boundaries (isolation test)",
      "description": "Notes each group (dates/currency/validation/etc.) can be understood in isolation, so the boundaries are clean",
      "max_score": 6
    },
    {
      "name": "Corrects misapplied defense",
      "description": "Corrects the 'big files are fine for agents' reasoning — that defense is for one cohesive concern, not a grab-bag",
      "max_score": 8
    }
  ]
}

README.md

SKILL.md

tile.json