agentsclimarketplace

Prompt structure

Skill soden46/syarif-laravel-ai-skills/skills/prompt-structure

Laravel guidance to structure prompts for clarity-separate concerns, prioritize requests, specify acceptance criteria, and break work into testable incrementsFrom its SKILL.md

Install
npx -y skills add soden46/syarif-laravel-ai-skills --skill prompt-structure

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 343 tokens by cl100k_base, as published. Nobody here has run it

Prompt Structure

Use this skill when a Laravel task involves prompt structure.

This skill is adapted to the personal Laravel standards in this repository. It maps the public prompt-structure topic from jpcaparas/superpowers-laravel into the local prompt-structure catalog without copying third-party skill body text.

Syarif Defaults

  • Follow Laravel conventions before introducing custom abstractions.
  • Prefer project-local patterns when they are explicit and tested.
  • Keep controllers focused on HTTP orchestration.
  • Put validation, authorization, transactions, side effects, and integrations at clear boundaries.
  • Keep client names, credentials, internal URLs, provider secrets, and project-specific business rules out of reusable standards.
  • Verify important behavior with the smallest meaningful tests and quality checks.

Workflow

  1. Detect the Laravel version, PHP version, runner, package manager, and existing project conventions.
  2. Identify the smallest local skill set that overlaps this topic.
  3. Implement or review the change using Laravel-native APIs first.
  4. Add abstractions only when they reduce real complexity or protect a meaningful boundary.
  5. Run targeted tests and available quality checks before handoff.

Checkpoints

  • Authorization and validation boundaries are explicit.
  • Query shape, transactions, queues, cache, files, and external calls are intentional when touched.
  • User-facing behavior has feature, unit, browser, or integration tests at the right level.
  • Logs and errors are useful without exposing secrets or unnecessary personal data.
  • Documentation or proposals avoid importing source-project names or one-off business rules.

Related Skills

  • using-laravel-standards
  • architecture
  • testing
  • security

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most prompt engineering skills give in 343 tokens

Counted across 564 of the 626 authors here whose files we hold, read 2026-08-07

  • Ask at most three clarifying questionsin 21 of 564, across 14 files
  • Establish baseline metrics and collect representative examplesin 12 of 564, across 2 files
  • Identify failure modes and prioritize high-impact fixesin 12 of 564, across 2 files
  • Apply prompt and workflow improvements with measurable goalsin 12 of 564, across 2 files
  • Roll back quickly if quality or safety metrics regressin 12 of 564, across 2 files
  • Validate changes with tests and roll out in controlled stagesin 12 of 564, across 2 files
  • Generate quantitative baseline performance reportsin 12 of 564, across 2 files
  • Create representative test scenariosin 12 of 564, across 2 files
  • Treat prompts as codein 12 of 564, across 5 files
  • Preserve the original intentin 12 of 564, across 10 files
  • Test prompts on diverse inputsin 11 of 564, across 7 files
  • Format the output as a markdown templatein 10 of 564, across 4 files

Said here and by no other author read

  • follow Laravel conventions before custom abstractions
  • keep controllers focused on HTTP orchestration
  • place integrations at clear boundaries
  • omit credentials and secrets from standards
  • verify behavior with small meaningful tests
  • detect Laravel and PHP versions early

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.