atelier-setup
Skill49 starsChanged 24 days agoMITView on GitHub
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Read the repository before proposing any change:
- Distinctive: line 28
Do not create, install, configure, or modify anything during exploration.
- Very specific: line 45
If docs/agents/issue-tracker.md already defines one, preserve it unless the developer asks to change it.
- Distinctive: line 55
If both files exist, ask which file should own the agent guidance.
- Distinctive: line 58
If neither exists, ask which instruction file to create.
- Distinctive: line 66
Stop and wait for explicit approval.
- Distinctive: line 70
Add the following block to the selected instruction file:
- Very specific: line 91
If an ## Agent skills section already exists, update the ### Planning and implementation, ### Issue tracking, and ### Domain documentation …
- Very specific: line 95
Create docs/agents/ when needed, then write the approved tracker and domain documents.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Atelier Setup
Set up repository guidance that Atelier skills need without taking ownership of the developer's installation, harness configuration, or project structure. Explore first, present every proposed edit exactly, and write only after the developer approves it.
1. Explore
Read the repository before proposing any change:
- Root
AGENTS.mdandCLAUDE.md, if present. Note whether either already has an## Agent skillsheading. - Root
CONTEXT.mdandCONTEXT-MAP.md. docs/adr/and any context-localdocs/adr/directories.docs/agents/, including existingissue-tracker.mdanddomain.md.- Existing issue-tracker conventions: remotes, issue links in documentation, local issue directories, and project guidance.
- Genuine monorepo signals: a workspace manifest, or multiple independently deployable packages with their own source directories.
Do not create, install, configure, or modify anything during exploration.
2. Present Findings
Summarize what exists and recommend a domain-document layout:
- Single-context is the default: domain language belongs in root
CONTEXT.md; architectural decisions belong in rootdocs/adr/. - Multi-context is appropriate only when the repository has genuinely separate bounded
contexts.
CONTEXT-MAP.mdbelongs at the root and points to each context'sCONTEXT.mdanddocs/adr/directory.
Explain that domain documents remain lazy: do not create CONTEXT.md, CONTEXT-MAP.md, or an ADR
directory until another Atelier skill has resolved terminology or made a decision worth recording.
Select or confirm the issue tracker:
- If
docs/agents/issue-tracker.mdalready defines one, preserve it unless the developer asks to change it. - Otherwise recommend the tracker indicated by existing repository practice, then ask the developer to confirm or describe their tracker.
- Accept GitHub, GitLab, local Markdown, another tracker described by the developer, or
none. - Record the chosen workflow in
docs/agents/issue-tracker.md; do not install, initialize, or create external tracker resources.
Select the instruction file to edit:
- If both files exist, ask which file should own the agent guidance; do not duplicate it.
- Otherwise use root
AGENTS.mdwhen it exists. - Otherwise use root
CLAUDE.mdwhen it exists. - If neither exists, ask which instruction file to create; do not choose on the developer's behalf.
Show the developer the selected file, domain layout, and exact contents for:
- the
## Agent skillsblock; docs/agents/issue-tracker.mdusingreferences/issue-tracker.md;docs/agents/domain.mdusingreferences/domain.md.
Stop and wait for explicit approval.
3. Write After Approval
Add the following block to the selected instruction file:
## Agent skills
### Planning and implementation
Use `atelier-orchestrator` at the start of development work. It selects an Inline Plan for bounded
changes or a Spec-backed Plan when durable design and coordination artifacts are warranted.
### Issue tracking
Read `docs/agents/issue-tracker.md` when issue tracking is relevant. It defines this repository's
tracker workflow; `plan.json` remains authoritative for Spec-backed task details and dependencies.
### Domain documentation
Read `docs/agents/domain.md` before working in a domain area. It defines how to locate and use this
repository's context documents and ADRs.If an ## Agent skills section already exists, update the ### Planning and implementation,
### Issue tracking, and ### Domain documentation subsections in place rather than appending
duplicates. Preserve other subsections and all content outside the section, including user edits.
Create docs/agents/ when needed, then write the approved tracker and domain documents. Do not
create any other files or directories.
4. Report
State which instruction file and agent documents changed, the selected tracker, and the chosen domain-document layout. Remind the developer that the layout is a convention only: the first domain-modelling or architectural-decision task creates the relevant documents when it has substantive content.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- atelier-orchestratorSkill
- code-commitSkill
- code-handoffSkill
- code-pull-requestSkill
- code-reviewSkill
- code-subagentsSkill
- oracle-codebase-designSkill
- oracle-debugSkill
- oracle-domain-modellingSkill
- oracle-grill-meSkill
- spec-brainstormSkill
- spec-finishSkill
- spec-implementSkill
- spec-loopSkill
- spec-planSkill
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.

