agentleFS
Sign inStart free
Aetheria-Labs1Aetheria-Labs1/storefront-skills/AGENTS.md

storefront-skills

AGENTS.md8 starsChanged 3 months agoMITView on GitHub

AI workflows for building high-converting Shopify storefronts with the Lexsis AI MCP (https://mcp.trylexsis.com/mcp). Canonical skills live in skills/<name>/SKILL.md (Agent Skills standard, https://agentskills.io) and are also exposed at .agents/skills/ for agents that discover that path natively. Invoke by name, or let your agent select from each skill's description. The normal reviewed workflow is Setup → Plan → Design → Publish. Optimize scores and improves an existing page with the same plan blocks. Experiments, carts, and quizzes are independent operations. Audit is…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository12 other files it gives its agents.

The file

We split this AGENTS.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
  1. Very specific:

    After editing any skill or reference, run python3 scripts/build-distributions.py and commit the regenerated output.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Storefront Skills — Agent Guide

AI workflows for building high-converting Shopify storefronts with the Lexsis AI MCP (https://mcp.trylexsis.com/mcp).

Skills

Canonical skills live in skills/<name>/SKILL.md (Agent Skills standard, https://agentskills.io) and are also exposed at .agents/skills/ for agents that discover that path natively. Invoke by name, or let your agent select from each skill's description.

The normal reviewed workflow is Setup → Plan → Design → Publish. Optimize scores and improves an existing page with the same plan blocks. Experiments, carts, and quizzes are independent operations. Audit is a read-only report that Optimize can act on. The twelve public commands remain independently invokable; explicit skips are recorded in the task handoff. Pages are authored directly through MCP. Do not reintroduce local page workspaces, source/CSS artifacts, preview builds or local QA gates.

Rules for agents working IN this repo

  • skills/ is the single source of truth. Never edit gpt/* — they are generated by scripts/build-distributions.py. The repository root is the Claude plugin package and uses this same physical skills/ tree; do not recreate a second plugin copy under plugins/.
  • After editing any skill or reference, run python3 scripts/build-distributions.py and commit the regenerated output.
  • Skill frontmatter must satisfy the Agent Skills spec: name equals the directory name (≤64 chars, kebab-case); description ≤500 chars.
  • Shared reference docs live in skills/storefront-engine/references/; the storefront-engine directory is not a public skill. The rule corpora under references/page-types/ (one contract per page type with a JSON checklist), proof/, offers/, assets/, anti-patterns/, copy/ and mcp-playbooks/ are loaded by plan-page, design-page and optimize as workflows (each type file's ## Workflow plus the universal workflows/ sub-procedures). Validation uses MCP compiler output and hosted review. Repository-only fixture checks live under tests/support/ and are not shipped page-authoring steps. Island schemas live in references/islands/<name>/schema.json. Do not invent island names or props.
  • Public skills installed individually must remain self-contained. scripts/build-distributions.py materializes the shared references declared in SKILL_SHARED_REFERENCES into each consuming skill's references/ directory. Edit the shared source, never the generated local copy.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free