mcpbeat Sign in

API AI Augmented Skill for Claude

> Designs AI-powered API features, LLM tool/function definitions, MCP server tool schemas, natural language to API conversion, and agentic API workflows. Use whenever the user asks about "AI calling my API", "function calling schema", "tool definition for LLM", "MCP tools", "natural language API", "AI agent", "let Claude use my API", "OpenAI function calling", "Anthropic tool use", "API agent workflow", "LLM plugin", "AI integration", "RAG with my API", or "chatbot that calls my API".

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
343
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/LambdaTest/agent-skills --skill api-ai-augmented

The instruction itself

8 sections, as written by the author

AI-Augmented API Skill

Design LLM tool definitions, agentic workflows, and natural language API interfaces.


Anthropic Tool Use Definition

{
  "name": "search_products",
  "description": "Search for products by keyword, category, or price range. Use when the user wants to find, browse, or compare products.",
  "input_schema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "description": "Search query keywords"
      },
      "category": {
        "type": "string",
        "enum": ["electronics", "clothing", "books", "home"],
        "description": "Optional category filter"
      },
      "min_price": { "type": "number", "description": "Minimum price in USD" },
      "max_price": { "type": "number", "description": "Maximum price in USD" },
      "limit": { "type": "integer", "default": 10, "description": "Max results to return" }
    },
    "required": ["query"]
  }
}

OpenAI Function Calling Definition

{
  "type": "function",
  "function": {
    "name": "create_order",
    "description": "Create a new order for a user. Use when the user wants to purchase a product. Always confirm product and quantity before calling.",
    "parameters": {
      "type": "object",
      "properties": {
        "product_id": { "type": "string", "description": "The product ID to order" },
        "quantity": { "type": "integer", "minimum": 1, "description": "Quantity to order" },
        "shipping_address": {
          "type": "object",
          "properties": {
            "street": { "type": "string" },
            "city": { "type": "string" },
            "country": { "type": "string" }
          },
          "required": ["street", "city", "country"]
        }
      },
      "required": ["product_id", "quantity", "shipping_address"]
    }
  }
}

MCP (Model Context Protocol) Tool Schema

{
  "name": "get_build_status",
  "description": "Get the status of a HyperExecute test job. Use when the user asks about test results, job status, or CI build outcomes.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "job_id": { "type": "string", "description": "The HyperExecute job ID" }
    },
    "required": ["job_id"]
  }
}

> 🔗 Real-World Integration — TestMu AI HyperExecute

> Build MCP tools that let AI agents query and control test jobs via the HyperExecute API.

> Docs: https://www.testmuai.com/support/api-doc/?key=hyperexecute


Tool Design Principles

  • One tool = one action: Don't combine search + filter + sort into one tool. Split them.
  • Description drives routing: The LLM picks tools from descriptions — be specific and include trigger phrases.
  • Required vs optional: Only mark fields required if the API truly needs them.
  • Enum for constrained values: Use enum instead of string for fixed-choice fields.
  • Idempotent where possible: Prefer read tools over write tools for exploration.
  • Confirm before destructive actions: Description should say "Always confirm with the user before calling."

Agentic Workflow Example

User: "Get me the status of my last 3 test builds"

Agent plan:
  1. call list_jobs(limit=3, sort="created_at:desc")
     → returns [{id: "job_1", status: "passed"}, {id: "job_2", status: "failed"}, ...]
  2. call get_job_details(job_id="job_2")  // dig into the failed one
     → returns task breakdown, error logs
  3. Synthesize: "Your last 3 builds: job_1 passed, job_2 failed (2 of 15 tasks failed on Chrome/Win10), job_3 passed."

Natural Language → API Mapping Table

Build this mapping for any domain:

| Natural language intent | API call |

|------------------------|---------|

| "Find hotels in Paris" | GET /hotels/search?location=Paris |

| "Book a room for 2 nights" | POST /bookings |

| "Cancel my reservation" | POST /bookings/{id}/cancel |

| "Show my past orders" | GET /orders?user=me&sort=date:desc |

| "Is the API working?" | GET /health/ready |


API-as-Plugin (OpenAPI → GPT Plugin / Tool)

Minimal ai-plugin.json:

{
  "schema_version": "v1",
  "name_for_human": "My API",
  "name_for_model": "my_api",
  "description_for_human": "Access my service's data and actions.",
  "description_for_model": "Use this plugin to search, create, update and delete resources in My API. Always prefer specific endpoints over generic ones. Confirm destructive actions with the user first.",
  "auth": { "type": "oauth" },
  "api": { "type": "openapi", "url": "https://api.example.com/openapi.json" }
}

Other skills for the same job

different authors, same section of the catalogue
At Dispatch V2
by pytorch
vendor ×3

Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.

2k tokens
Docstring
by pytorch
vendor ×3

Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.

3k tokens
Statsmodels
by christophacham
×3

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

27k tokens
AI SDK
by vercel-labs
vendor ×2

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

6k tokens
Create Llms
by github
vendor ×1

Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/

2k tokens
Esm
by K-Dense-AI
×1

Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

21k tokens
Modal
by K-Dense-AI
×1

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.

19k tokens
Pytdc
by K-Dense-AI
×1

Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits, evaluator metrics, benchmark groups, and bounded molecular-oracle workflows.

27k tokens scripts

How to use it

Copy the folder

Take lambdatest/api-ai-augmented from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.