agentleFS
CreativeActtechCreativeActtech/llm-skills/skills/example-skill/api-design-standardizer/SKILL.md

api-design-standardizer

Skill2 starsChanged 7 months agoMITView on GitHub

Scaffold and audit RESTful API designs against enterprise standards. Use when the user needs to design endpoints, generate OpenAPI/Swagger schemas, or ensure naming consistency (kebab-case, resource-nesting).

The file

We split this skill 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:

    Check for "Deep Nesting" anti-patterns (e.g., /a/b/c/d/e).

    line 39

≈ “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

API Design Standardizer

Guides the systematic creation and validation of RESTful interfaces. This skill enforces industry-standard constraints (OpenAPI 3.1) and enterprise naming conventions to ensure interoperability and security.

🎯 When to Use

  • User needs to convert business requirements into a technical API contract.
  • User asks for a review of existing endpoint structures or URI paths.
  • User requests an OpenAPI/Swagger YAML or JSON definition from a list of features.
  • Do NOT use for generating client-side frontend code or implementation logic.
  • Do NOT use for SOAP, GraphQL, or gRPC designs unless specifically requested.

🧠 Core Workflow

Step 1 — Ingest & Identify Resources Parse requirements to extract primary nouns (resources), relationships, and lifecycle actions. Identify intended consumer (Internal vs. Public).

Step 2 — Profile & Categorize

  • URI Design: Enforce kebab-case, plural nouns, and versioning (e.g., /v1/).
  • HTTP Methods: Map CRUD actions to GET, POST, PUT, PATCH, DELETE.
  • Security: Identify auth requirements (OAuth2, JWT, Scopes).

Step 3 — Apply Standard Rules

  1. Consistency First — Ensure idempotent methods (PUT/DELETE) are correctly used.
  2. Error Handling — Standardize 4xx/5xx responses with consistent schemas.
  3. Performance — Suggest pagination, filtering, and sorting parameters.

Step 4 — Validate & Synthesize Check for "Deep Nesting" anti-patterns (e.g., /a/b/c/d/e). Ensure all paths have associated success and error status codes.

Step 5 — Return Output Provide a structured JSON manifest followed by a valid OpenAPI 3.1 YAML snippet.

📋 Output Format

Section 1 — Design Manifest

{
  "status": "success | error",
  "metadata": {
    "versioning_strategy": "URI-based",
    "auth_type": "string",
    "base_url": "string"
  },
  "endpoints": [
    {
      "path": "/resource-name",
      "method": "POST",
      "summary": "Short description",
      "compliance_notes": "e.g., Missing 403 response schema"
    }
  ],
  "summary": "X endpoints designed. Standard REST conventions applied."
}

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.