ask-marcel-office-cli
CLAUDE.md9 starsChanged 20 days agoMITView on GitHub
Guidance for Claude Code when working in this repository. Every code task in this repo MUST follow the atelier skill — writing, editing, scaffolding, testing, refactoring, reviewing, or debugging. The skill is installed at .claude/skills/atelier (also in .agents/skills/atelier) and is the source of truth for conventions: Clean Architecture (src/{domain,use-cases,infra,presenter,composition}), strict TDD (red-green-refactor), Result<T, E> at IO boundaries, branded types at trust boundaries, Bun-only toolchain, and the five-gate pre-commit hook. Rules are non-negotiable — when in doubt, consult the skill before…
In this repository7 other files it gives its agents.
- atelier-greenfieldSkill
- atelier-grill-meSkill
- atelier-review-meSkill
- atelierSkill
- qa-auditSkill
- simplified-technical-englishSkill
- ask-marcelSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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 20
Always use Atelier Skill
- Distinctive: line 22
Before Commit always use Atelier Review Me
- Distinctive: line 24
When user Ask Questions or want to change anything, always use Atelier Grill Me
- Distinctive: line 29
Use the simplified-technical-english skill for all text: chat, docs, comments, commit messages, and error messages.
- Very specific: line 34
Use conventional commit messages (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md
Guidance for Claude Code when working in this repository.
Always use the atelier skill
Every code task in this repo MUST follow the atelier
skill — writing, editing, scaffolding, testing, refactoring, reviewing, or debugging. The skill is
installed at .claude/skills/atelier (also in .agents/skills/atelier) and is the source of
truth for conventions: Clean Architecture (src/{domain,use-cases,infra,presenter,composition}),
strict TDD (red-green-refactor), Result<T, E> at IO boundaries, branded types at trust boundaries,
Bun-only toolchain, and the five-gate pre-commit hook. Rules are non-negotiable — when in doubt,
consult the skill before acting. If the skill and any doc disagree, the skill wins.
Each of auth/ core/ read/ write/ is an atelier Bun TypeScript script repo (package split, ADR 0003):
its own src/{domain,use-cases,infra,presenter,composition}, coverage tiers and mutation, run from
that folder. Since phase 6 of the split the root holds no package and no src/: it keeps the shared
configs, scripts/ and the docs.
Always use Atelier Skill
Before Commit always use Atelier Review Me
When user Ask Questions or want to change anything, always use Atelier Grill Me
Writing style
Use the simplified-technical-english skill for all text: chat, docs, comments, commit messages, and error messages. Do not apply it to code, commands, or quoted text.
Commits
Use conventional commit messages (e.g. feat:, fix:, chore:, docs:).
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.