generate-laravel-agent-instructions

Generate or update `.ai/guidelines/project.md` for Laravel codebases by extracting architecture, domain logic, jobs, workflows, and integration details from repository evidence. Use when the user asks to create, refresh, or improve Laravel-specific agent instructions or project overview guidance.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "generate-laravel-agent-instructions" with this command: npx skills add sebkay/skills/sebkay-skills-generate-laravel-agent-instructions

Generate or update .ai/guidelines/project.md using evidence from the current Laravel repository.

.ai/guidelines/project.md is pulled into AGENTS.md, so avoid duplicating guidance already present in AGENTS.md unless needed for local clarity.

Workflow

  1. Locate existing .ai/guidelines/project.md and use it as the base when present.
  2. Inspect the codebase deeply enough to capture:
    • Core business and domain logic.
    • Laravel architecture and boundaries (routes, controllers, services/actions, models, policies).
    • Background processing (jobs, queues, listeners, notifications, scheduled tasks).
    • External integrations and cross-component data flow.
  3. Extract only repository-backed facts from code, config, migrations, and docs.
  4. Merge intelligently with the existing file: keep valid guidance, remove stale guidance, fill important gaps.
  5. Write concise, actionable instructions for future coding agents.

Output Requirements

  • Keep the file under 100 lines.
  • Prefer project-specific guidance over generic Laravel advice.
  • Include concrete file or directory references for critical behavior.
  • Prioritize domain rules, side effects, async flows, and failure-sensitive logic.
  • Document current-state behavior only.

Quality Bar

  • Avoid assumptions not supported by repository evidence.
  • Capture details that prevent costly mistakes in future agent runs.
  • Favor brevity, but stay explicit on high-impact logic.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

review-code

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

generate-agent-instructions

No summary provided by upstream source.

Repository SourceNeeds Review
General

add-plan-todos

No summary provided by upstream source.

Repository SourceNeeds Review
General

commit

No summary provided by upstream source.

Repository SourceNeeds Review