Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add oyusypenko/creo --skill creo-ai-generationgit clone --depth 1 https://github.com/oyusypenko/creoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/oyusypenko/creo/creo-ai-generation)<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-ai-generation"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-ai-generation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-ai-generation"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-ai-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.01539 |
| Opus 5 | $0.00044 | $0.00770 |
| Sonnet 5 | $0.00018 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
creo-ai-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Generation Pipeline Expert
Expert in AI-powered content generation pipelines. Specializes in LLM generation flows: prompt engineering, structured output validation, queue-based async processing, real-time progress tracking via SSE, and multi-mode generation strategies.
Commands
| Command | Description |
|---|---|
/creo ai-generation debug |
Debug an AI generation pipeline issue |
/creo ai-generation optimize |
Optimize prompts, validation, or performance |
/creo ai-generation pipeline |
Design or extend a generation pipeline |
Core Instructions
Configuration
- Check for project-specific config at
.claude/project-config.md - Read
project_id,project_url,dev_server_url - Load project extension if it exists at
.claude/skills/creo-ai-generation/creo-ai-generation-{project_id}.md. This file contains project-specific file paths, Zod schemas, prompt templates, queue names, and domain knowledge for the generation pipeline.{project_id}comes fromproject-config.md. The extension file is critical -- always load it before doing any work.
Expertise Areas
LLM Generation Pipelines
- Multi-stage flows: data fetch -> prompt build -> LLM call -> validate -> persist
- Structured output with Zod schemas and JSON Schema
- Prompt engineering for content generation
- Smart distribution logic based on user profiles
- Model selection and provider configuration (OpenAI, Anthropic, local models)
Vercel AI SDK
generateObject()with Zod schemas for type-safe structured outputstreamObject()for progressive UI updates- Provider abstraction (OpenAI, Anthropic, Google, custom)
- Error handling, retries, and fallback strategies
- Telemetry integration for monitoring generation quality
LangChain / LangGraph
- Chain composition for complex generation flows
- StateGraph for multi-step agent workflows
- Tool calling and function execution
- Output parsers and structured output
- Callbacks for logging and monitoring
- Human-in-the-loop patterns
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 177 lines · 88 tokens per session scan A 69bc274f3f93
creo-ai-generation is a skill published in the GitHub repository oyusypenko/creo (4 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 1,539 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vllm-chat-templates
Target audience: operators deploying vLLM in production. Assumes OpenAI-API-compatible frontend (/v1/chat/completions or /v1/responses), multi-GPU, mid-2024 through 2026 model families.
llm-first-code
Write comments, docstrings and types for a model reader, not a human one. Use when writing or reviewing any function, module or docstring.
ai-integration
Generates LLM API integration code for OpenAI, Anthropic, and Google. Includes prompt engineering patterns, streaming responses, error handling, cost estimation, and RAG pipeline setup.
claude-api
Anthropic Claude API: prompt caching, streaming, tool use, batch processing, model selection, cost optimization.
guidance
Constrain LLM output with grammars; guarantee valid JSON.
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.