codebase-understanding
Skill6 starsChanged 39 days agoMITView on GitHub
Build a reliable mental model of an unfamiliar repository before making changes. Use when entering a new codebase, investigating architecture, or when the user asks where a feature belongs.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- OneDro1d/onedroid-docstheir own version, first seen Sep 18, 2026
- Wukung1010/claude_code_booktheir own version, first seen Apr 21, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Wukung1010/claude_code_book★ 1same name
- OneDro1d/onedroid-docs★ 0same name
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 repository36 other files it gives its agents.
- bioinformatics-planningSkill
- biology-literature-analysisSkill
- biology-paper-analysisSkill
- chemistry-research-analysisSkill
- skill-authorSkill
- codebase-explorerSkill
- code-reviewSkill
- debug-systematicallySkill
- implementation-plannerSkill
- implementation-reviewSkill
- ledger-tasks-yyloSkill
- test-and-verifySkill
- algorithm-learningSkill
- system-design-basicsSkill
- defensive-security-reviewSkill
- threat-modelingSkill
- data-analysisSkill
- tutorSkill
- experiment-analysisSkill
- model-evaluationSkill
- numerical-methodsSkill
- mathematics-problem-solverSkill
- proof-solvingSkill
- physics-research-analysisSkill
- data-cleaningSkill
- data-visualizationSkill
- evidence-checkerSkill
- evidence-comparisonSkill
- experimental-planningSkill
- literature-synthesizerSkill
- reproducibility-auditSkill
- research-questionSkill
- source-verificationSkill
- api-designSkill
- frontend-planningSkill
- technical-editorSkill
The file
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 16
Search for existing implementations before proposing new ones.
- Distinctive: line 22
Read targeted files before broad exploration.
- Distinctive: line 23
Do not invent architecture that is not supported by repository evidence.
- Distinctive: line 24
Prefer existing abstractions over introducing parallel ones.
- Distinctive: line 26
If the change crosses multiple layers, state the dependency order.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Codebase Understanding
Build understanding before proposing edits. Prefer evidence from the repository over assumptions.
Process
- Identify entry points, package/build files, configuration, tests, and documentation.
- Map the relevant directory structure.
- Trace the execution path for the requested feature or bug.
- Identify important data models, interfaces, dependencies, and integration boundaries.
- Search for existing implementations before proposing new ones.
- Record constraints, conventions, and likely regression points.
- Summarize the model in a compact form before changing code.
Rules
- Read targeted files before broad exploration.
- Do not invent architecture that is not supported by repository evidence.
- Prefer existing abstractions over introducing parallel ones.
- Distinguish observed facts from hypotheses.
- If the change crosses multiple layers, state the dependency order.
Output
Return:
- Repository map
- Relevant execution/data flow
- Existing patterns to reuse
- Constraints and risks
- Proposed change locations
- Verification plan
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.