my-llm-api
API gateway for LLM primitives and task-specific AI verbs.
Install
mkdir -p .claude/skills/my-llm-api && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13443" && unzip -o skill.zip -d .claude/skills/my-llm-api && rm skill.zipInstalls to .claude/skills/my-llm-api
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Two-surface LLM primitive. Raw chat completion against self-hosted open-source models (you pick the model), and objective verbs (classify / extract / summarize / draft) that hide the model behind a task. Pricing in cents per 1M tokens; charged from your MyAPI balance.Key capabilities
- →Perform raw chat completions against self-hosted open-source models
- →Embed text into dense vectors
- →Classify input text into specified labels
- →Extract structured data from input text based on a JSON schema
- →Summarize input text in various styles
- →Draft text content based on kind, context, and prompt
How it works
MyLLMAPI provides a two-surface LLM gateway: raw completion/embedding against self-hosted models and task-based verbs (classify, extract, summarize, draft). It manages token-based pricing and debits from a MyAPI balance.
Inputs & outputs
When to use my-llm-api
- →Summarizing documentation
- →Classifying inbound emails
- →Extracting structured JSON
- →Drafting text content
About my-llm-api
This skill provides access to raw model completions and specific task-based verbs like classification and summarization. It manages token-based balance and focuses on efficient, recurring tasks.
>
When not to use it
- →When the user's agent model is more capable than the models exposed by MyLLMAPI
- →When real-time streaming responses are required
- →When using proprietary models not available in the self-hosted catalog
Limitations
- →Proprietary models are not callable via raw completion
- →The model/provider is never named in the verb response
- →Context fields in `draft` are quoted verbatim; sensitive keys are not redacted
How it compares
This skill offers both raw LLM access and task-oriented verbs, allowing users to choose between fine-grained control and abstracted task execution, while managing costs and using self-hosted models, unlike direct interaction with a single L
Compared to similar skills
my-llm-api side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| my-llm-api (this skill) | 0 | 3mo | Review | Intermediate |
| openrouter | 19 | 11mo | Review | Intermediate |
| llama-factory | 15 | 10mo | No flags | Advanced |
| grpo-rl-training | 5 | 8mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by myapihq
View all by myapihq →You might also like
openrouter
rawveg
OpenRouter API - Unified access to 400+ AI models through one API
llama-factory
zechenzhangAGI
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
grpo-rl-training
davila7
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
senior-prompt-engineer
davila7
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
agent-evaluation
davila7
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
dspy
davila7
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming