project-conventions
Skill2 starsChanged 51 days agoMITView on GitHub
{{PROJECT_NAME}} project conventions, naming standards, project layout, commit format, and Definition of Done. Checked before starting code and before committing.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- frnkgns/Overgeared-Skillstheir own version, first seen Nov 8, 2026
- github/squadtheir own version, first seen Nov 8, 2026
- microsoft/github-vteam-industry-demostheir own version, first seen Oct 25, 2026
- g-cqd/skillstheir own version, first seen Oct 23, 2026
- vishalguptax/agent-engineering-kittheir own version, first seen Oct 11, 2026
- hyperledger-labs/splicetheir own version, first seen Oct 9, 2026
Used with
Projects with it also use e2e-template-testing, notification-routing 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.
GitHubSkille2e-template-testing
End-to-end validation of coordinator and agent template changes
Also in 3 projects that use this
GitHubSkillnotification-routing
Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding
Also in 3 projects that use this
Microsoft AzureSkillcoordinator-source-of-truth
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may read each one, and the precedence rules when they conflict. Squad coordinator loads this on demand when it needs to resolve a write conflict, decide where a piece of state belongs, or answer a 'who owns this file' question.
Also in 3 projects that use this
Microsoft AzureSkillcross-squad-communication
Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories
Also in 3 projects that use this
SentrySkillskill-creator
Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.
Also in 3 projects that use this
- +4 more from github
- +2 more from Azure
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- github/gh-aw★ 5.6ksame name
- github/squad★ 3.4ksame name
- Soju06/codex-lb★ 3.3ksame name
- nextcloud/notes-android★ 1.1ksame name
- hyperledger-labs/splice★ 122same name
- TangleML/tangle-ui★ 104same name
- Azure/apiops-cli★ 32same name
- choi138/toki★ 9same name
- frnkgns/Overgeared-Skills★ 7same name
- g-cqd/skills★ 2same name
7 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 repositoryOne other file it gives its agents.
- agent-coordinationSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
When an agent genuinely can't tell which files fall under its concern, it asks the user rather than guessing.
- Distinctive: line 45
If two or more of these paths are the same directory (single-repo/single-app project), ownership is decided by file pattern within that …
- Distinctive: line 52
If the contract changes, shared is updated first, then FE and BE adapt.
- Distinctive: line 55
All acceptance criteria checked and verified
- Very specific: line 59
Commit message includes the card ID (e.g.
“Common” is measured: kept by at least 6 in 10 of the 11 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
{{PROJECT_NAME}} Project Conventions
Project Layout
Ownership is by concern, not by directory. This kit deliberately does not record where things live — layouts differ per project and change over time, and a hardcoded path is a lie waiting to happen. Agents locate their areas by looking at the repo (graphify query if the graph exists, otherwise glob/grep), and the ownership boundaries below hold whatever the layout turns out to be — separate packages in a monorepo, or everything side by side in one src/.
When an agent genuinely can't tell which files fall under its concern, it asks the user rather than guessing. Guessing produces edits in another agent's territory, which is the one failure this ownership model exists to prevent.
- Package manager: {{PKG_MANAGER}}.
- Validation schemas live in exactly one shared module; frontend and backend both consume from there and neither re-declares them.
Card ID & Naming
Format: [MODULE-LAYER-SEQ]
Modules: {{MODULES}} (comma-separated, lowercase)
Layers: DB, BE, FE, INFRA, QA
Examples:
MODULE-ARCH-001= a module, architecture layer, 1st cardMODULE-BE-005= a module, backend layer, 5th cardMODULE-FE-002= a module, frontend layer, 2nd card
Commit format:
feat(MODULE-BE-003): short description
fix(MODULE-FE-001): short description
test(MODULE-DB-002): short descriptionOwnership Boundaries
| Area | Owner |
| Server-side code, OpenAPI, business rules | Backend agent |
| UI components, screens, client-side state | Frontend agent |
| Schema, migrations, seeds, auth infrastructure, CI | Data/Infra agent |
| Shared schema modules | Backend agent (FE consumes, changes go through BE) |
If two or more of these paths are the same directory (single-repo/single-app project), ownership is decided by file pattern within that directory rather than by the directory itself — see the Project Layout note above.
A BE card that needs a schema change adds a [SCHEMA-REQUEST] note to its description; the Data/Infra agent applies it.
Contract-First Rule
- The schema is defined in shared before an endpoint is written.
- FE works against a mock fixture until the API is ready.
- If the contract changes, shared is updated first, then FE and BE adapt.
Definition of Done (every card)
- All acceptance criteria checked and verified
- Lint + typecheck clean
- Relevant tests written and passing
- FE: uses the UI library, responsive, no custom CSS
- Commit message includes the card ID (e.g.
MODULE-BE-003) - Card in
Done ✅
Available Optional Skills
{{SELECTED_SKILLS}}
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.

