improve-codebase-architecture
Skill0 starsChanged 25 days agoMITView on GitHub
Review a codebase for worthwhile architectural simplifications and deeper modules. Use when the user asks for an architecture review or targeted design improvement.
195 other projects use a version of this.
Adopted by
Most recently taken up by
- chrysogonus/power-agentstheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
- miklschmidt/archboardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use migrate-to-shoehorn, writing-beats and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
simo97Skillmigrate-to-shoehorn
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
Also in 73 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 68 projects that use this
simo97Skillrequest-refactor-plan
Use this skill when user wants to create a refactor plan.
Also in 43 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 8 projects that use this
LesaniSkillwriting-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.
Also in 65 projects that use this
- +2 more from simo97
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- mattpocock/skills★ 309ksame name
- danny-avila/LibreChat★ 47ksame name
- LibreChat-AI/LibreChat★ 47ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- windmill-labs/windmill★ 18ksame name
- GreyDGL/PentestGPT★ 16ksame name
- humanlayer/humanlayer★ 13ksame name
- sanity-io/sanity★ 6.4ksame name
- ArcReel/ArcReel★ 6.3ksame name
185 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- codebase-designSkill
- uv-pythonSkill
- bw-loginSkill
- project-iconSkill
- recover-mouse-inputSkill
- wizardSkill
- dispatching-parallel-agentsSkill
- handoffSkill
- hill-climbSkill
- opcSkill
- opnSkill
- personal-skillsSkill
- reassign-pmSkill
- repo-lessonsSkill
- trialSkill
- unstuckSkill
- woSkill
- sampleSkill
- find-docsSkill
- liteparseSkill
- tco-searchSkill
- browse-xSkill
- frontend-designSkill
- playwrightSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 184 edited versions we read keep these.
4
Distinctive
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 12
Use the requested subsystem or pain point.
- Distinctive: line 22
Default to a concise inline report with the strongest recommendation first.
- Distinctive: line 28
Ask about decisions that materially change scope, behavior, or an irreversible commitment.
- Distinctive: line 30
Use the repository's existing delivery and ownership rules.
“Common” is measured: kept by at least 6 in 10 of the 184 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Improve Codebase Architecture
Find changes that make real work easier: less knowledge required by callers, fewer places to change together, and behavior that is easier to test. This skill is standalone; no other skill or preliminary setup is required.
Focus the review
Use the requested subsystem or pain point. For a broad review, recent changes and concrete maintenance friction are useful starting points. Read architecture notes, domain terminology, and decisions only where they affect the area under review. Preserve established terminology and justified tradeoffs.
A deep module exposes a small, understandable interface while hiding substantial implementation detail. Its interface includes ordering constraints, errors, and configuration, not just method signatures. A useful simplification reduces what callers must know rather than merely moving complexity elsewhere.
Look for behavior scattered across tightly coupled files, abstractions that only forward calls, implementation details exposed to callers, and tests that cannot exercise the actual behavior through a stable interface. Keep additional boundaries only when real variation or a concrete testing need justifies them. Size or file count alone is not a defect.
Present useful candidates
For each worthwhile candidate, identify the source paths, observed friction, proposed change, preserved behavior, tradeoffs, and a proportionate way to verify it. Distinguish evidenced problems from speculative opportunities. A finding-free review is valid.
Default to a concise inline report with the strongest recommendation first. Use a diagram or HTML artifact only when it materially clarifies the design or the user asks for one. Avoid imposing a presentation framework or remote dependencies.
Follow the user's requested outcome
A review request authorizes findings, not implementation. For an implementation request, continue through the scoped change, relevant checks, and repairs until the requested behavior is verified. Do not stop merely because a first version exists. Report checks that could not run without claiming completion.
Ask about decisions that materially change scope, behavior, or an irreversible commitment. Choose routine implementation details from the available evidence. Interviews, glossary changes, and architectural decision records are optional tools, not mandatory phases; use them only when they resolve a real ambiguity or are requested.
Use the repository's existing delivery and ownership rules. This skill does not grant publication, merge, delegation, or destructive-cleanup authority.
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.

