shopify-theme-builder
CLAUDE.md1 starsChanged 55 days agoMITView on GitHub
Issues live in GitHub Issues at itsmylife44/shopify-theme-builder, managed via the gh CLI. See docs/agents/issue-tracker.md. Default five-role vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. See docs/agents/triage-labels.md. Single-context: one CONTEXT.md and docs/adr/ at the repo root. See docs/agents/domain.md. The development skills live in .claude/skills/ (installed with npx skills add, pinned in skills-lock.json), next to the repo's own theme-tooling skill (Theme Check, theme dev, Section Catalog conventions). Load the matching skill before editing a file area: Also available, not enforced: vite (Vite config and…
In this repository10 other files it gives its agents.
- .claude/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- shadcnSkill
- shopify-liquidSkill
- tailwind-design-systemSkill
- theme-toolingSkill
- typescript-advanced-typesSkill
- vercel-react-best-practicesSkill
- viteSkill
- vitestSkill
- shopify-theme-builderSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 11
Default five-role vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
shopify-theme-builder
Agent skills
Issue tracker
Issues live in GitHub Issues at itsmylife44/shopify-theme-builder, managed via the gh CLI. See docs/agents/issue-tracker.md.
Triage labels
Default five-role vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. See docs/agents/triage-labels.md.
Domain docs
Single-context: one CONTEXT.md and docs/adr/ at the repo root. See docs/agents/domain.md.
Development skills
The development skills live in .claude/skills/ (installed with npx skills add, pinned in skills-lock.json), next to the repo's own theme-tooling skill (Theme Check, theme dev, Section Catalog conventions). Load the matching skill before editing a file area:
| File area | Skill to load |
**/*.liquid | shopify-liquid, theme-tooling |
skills/shopify-theme-builder/studio/src/**/*.tsx | vercel-react-best-practices (ignore its server-* rules: the Studio is a Vite SPA) |
skills/shopify-theme-builder/studio/src/components/ui/** | shadcn |
skills/shopify-theme-builder/studio/src/**/*.css | tailwind-design-system |
Also available, not enforced: vite (Vite config and the Studio's server plugin), vitest (tests), typescript-advanced-types.
In Claude Code, .claude/hooks/skill-gate.mjs enforces this table: an edit to a mapped file is blocked until the skill was loaded in the session. The rules live in that script; keep this table, and its copy in CONTRIBUTING.md, in sync. On other agents, read .claude/skills/<name>/SKILL.md yourself before editing.
.claude/settings.json sets OPT_OUT_INSTRUMENTATION=true, which turns off the shopify-liquid skill's telemetry (it would otherwise send your prompts to Shopify). On another agent, create ~/.config/shopify-ai-toolkit/opt-out instead.
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.

