Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
Passed 12 of 17 test cases with the skill, and 9 of 17 without it.
and 3 more in the full report
4 fixed11 passed either way6 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to run an architectural friction analysis on our repository `/src/payment_gateway`. Note that this repository currently lacks `CONTEXT.md` and has no `docs/adr/` folder. How should you handle these missing documentation files before proceeding with the architectural review?
| Checked | Without skill | With skill |
|---|---|---|
| Proceeds silently with codebase exploration when CONTEXT.md is missing. | Missed | Passed |
| Refrains from suggesting upfront creation of missing CONTEXT.md files. | Missed | Passed |
The instructions your model reads when the skill loads.
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in LANGUAGE.md.
Key principles (see LANGUAGE.md for the full list):
This skill is informed by the project's domain model — CONTEXT.md and any docs/adr/. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate. See CONTEXT-FORMAT.md and ADR-FORMAT.md.
Read existing documentation first:
CONTEXT.md (or CONTEXT-MAP.md + each CONTEXT.md in a multi-context repo)docs/adr/ (and any context-scoped docs/adr/ directories)If any of these files don't exist, proceed silently — don't flag their absence or suggest creating them upfront.
Then use the Agent tool with subagent_type=Explore to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
test cases passed, vs 9 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.