project-code-standards
Skill1 starsChanged 3 months agoMITView on GitHub
<project> language and code conventions. Use when writing or reviewing any code in this repository — naming, tunables, data access, error handling, component patterns, and the stack-constraint checklist.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- KiWi233333/JiwuChattheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- KiWi233333/JiwuChat★ 749same 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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- code-commenterSkill
- project-architectureSkill
- subagent-driven-developmentSkill
The file
Files
<project> code standards
Stub — fill this in. Everything a gate already enforces (formatting, lint, import order) belongs in the gate, not here. This file carries what a reviewer would otherwise have to say out loud on every PR. Rename to
<project>-code-standardsand update.claude/skills/README.md.
Stack constraints
| Constraint | Version / choice | What breaks if it is quietly changed |
<…> | <…> | <…> |
Naming
<The conventions that are not obvious from the language: what a file, a type, a test, and a public
contract are each called, with one example of each.>
Data access
<The query-count rule, with the shape that violates it.><What a write returns, and why nothing reads back.><What a bulk write owns that the ORM would otherwise have done.>
Types
<The banned shapes in a signature you own, and the two or three real exceptions.><Where a record / sealed type / projection replaces a loose map.>
Errors
<The error model: the type, the status mapping, what a client can bind to, what is logged where.>
Tunables
<Where configuration lives, how a new tunable is declared, and what its default must be so the day it
ships nothing behaves differently.>
Tests
<The slice to reach for first, and when to escalate.>- Prove a new test bites — remove the behaviour it names, watch it fail, restore it.
Review checklist
- Deprecated APIs: none introduced; current replacement named for any found.
- Comments: non-obvious why only, once (
code-commenter). - Contracts regenerated in this PR.
- Every punt has a target in
DEFERRED.md.
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.