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
npx -y skills add soden46/syarif-laravel-ai-skills --skill prompt-structureAssembled 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
- Detect the Laravel version, PHP version, runner, package manager, and existing project conventions.
- Identify the smallest local skill set that overlaps this topic.
- Implement or review the change using Laravel-native APIs first.
- Add abstractions only when they reduce real complexity or protect a meaningful boundary.
- 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-standardsarchitecturetestingsecurity
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 542 of the 575 authors here whose files we hold, read 2026-09-06
- Provide few-shot examples for complex tasksin 17 of 542, across 16 files
- Ask clarifying questions if information is ambiguousin 16 of 542, across 14 files
- Output a complete optimized prompt for the userin 15 of 542, across 9 files
- Validate structured outputs against schemasin 15 of 542, across 13 files
- Analyze the draft prompt for intent and gapsin 14 of 542, across 8 files
- Detect project tech stack from local filesin 14 of 542, across 8 files
- Recommend a model based on task scopein 13 of 542, across 7 files
- Present results in the specified output formatin 13 of 542, across 7 files
- Match intent and scope to ECC componentsin 13 of 542, across 7 files
- Ask one question at a timein 13 of 542, across 12 files
- Respond in the same language as the user inputin 12 of 542, across 6 files
- Ask up to three clarification questions if context is missingin 11 of 542, across 5 files
Said here and by no other author read
- Follow Laravel conventions before custom abstractions
- Keep controllers focused on HTTP orchestration
- Place validation and authorization at clear boundaries
- Verify behavior with smallest meaningful tests
- Detect Laravel and PHP versions first
- Implement changes using Laravel-native APIs
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.