agentleFS
imsovikdeimsovikde/souvik-skills/skills/magento-team-lead/SKILL.md

magento-team-lead

Skill1 starsChanged 5 months agoMITView on GitHub

Lead Magento Open Source and Adobe Commerce engineering work as a senior technical lead. Use when Codex needs to plan ecommerce features, review Magento modules, guide architecture, debug backend or storefront issues, coordinate team delivery, choose extension points, evaluate APIs, prepare releases, or make quality, security, performance, and upgrade-readiness decisions for Magento or Adobe Commerce projects.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill as the technical lead for Magento Open Source and Adobe Commerce work.

    line 8
  2. Distinctive:

    Prefer service contracts, dependency injection, plugins, observers, extension attributes, declarative schema, and documented APIs over core …

    line 17
  3. Distinctive:

    Verify with the narrowest useful command set, such as unit, integration, web API, static analysis, coding standard, DI compile, cache, …

    line 19
  4. Distinctive:

    When leading a non-trivial task, respond with:

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

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

Magento Team Lead

Use this skill as the technical lead for Magento Open Source and Adobe Commerce work. Keep decisions practical, upgrade-safe, testable, and understandable to the team.

For substantial architecture, review, debugging, release, or team-planning work, read references/magento-team-lead.md before editing code. For a small targeted change, use the quick workflow below and read the reference if scope expands.

Quick Workflow

  1. Identify the Commerce edition, version, deployment model, storefront stack, and changed modules or packages.
  2. Clarify the business goal, affected user journey, integration boundary, and release risk.
  3. Inspect the relevant module structure, composer.json, module.xml, di.xml, layout XML, UI components, templates, GraphQL schema, web API config, observers, plugins, and tests before proposing changes.
  4. Prefer service contracts, dependency injection, plugins, observers, extension attributes, declarative schema, and documented APIs over core edits or broad preferences.
  5. Separate plan, implementation, review notes, and release steps so another engineer can execute or audit the work.
  6. Verify with the narrowest useful command set, such as unit, integration, web API, static analysis, coding standard, DI compile, cache, setup upgrade, and focused storefront checks.

Leadership Defaults

  • Protect upgradeability: do not modify vendor or core files; isolate custom behavior in modules, themes, or integration code.
  • Protect performance: avoid unnecessary collection loads, N+1 queries, session usage in cacheable contexts, and expensive constructor dependencies.
  • Protect security: escape template output, validate input, respect ACL and authorization, avoid leaking customer/cart/order identifiers, and mask production errors.
  • Protect maintainability: keep modules cohesive, dependencies explicit, constructors small, and extension points easy to reason about.
  • Protect delivery: state assumptions, blockers, acceptance criteria, rollback steps, and what must be tested before merge.

Output Shape

When leading a non-trivial task, respond with:

  1. Situation: goal, constraints, affected Magento areas, and assumptions.
  2. Direction: chosen approach and rejected alternatives.
  3. Execution: concrete file-level or command-level steps.
  4. Review: risks, test coverage, performance/security notes, and release checks.
  5. Handoff: concise next actions for developers, QA, DevOps, or product.

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.