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 IAPro-Community/Orquestrador-Maestro --skill skill-ai-orchestrationgit clone --depth 1 https://github.com/IAPro-Community/Orquestrador-MaestroWrote 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/iapro-community/orquestrador-maestro/skill-ai-orchestration)<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-ai-orchestration"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-ai-orchestration/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/iapro-community/orquestrador-maestro/skill-ai-orchestration"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-ai-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00961 |
| Opus 5 | $0.00031 | $0.00481 |
| Sonnet 5 | $0.00012 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
skill-ai-orchestration 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 12d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Orchestration
Use this skill to design or modify AI provider integrations. Keep this file as the compact workflow; load product-specific code only when the task names it.
Core Workflow
- Identify the feature, user intent, provider, model, expected output shape, latency target, and cost ceiling.
- Keep provider keys, organization IDs, refresh tokens, webhook secrets, and signing keys server-side only.
- Route all AI calls through one server module or gateway that applies auth, quotas, validation, tracing, retries, and redaction.
- Create durable work records for expensive or long-running calls; run them through queues or workers instead of request handlers.
- Use idempotency keys for retries, dedupe, tool calls, media generation, transcription jobs, and webhook callbacks.
- Version prompts and schemas by feature. Store prompt hash, schema version, model, temperature, and evaluation notes with each request.
- Validate every structured response against a schema before writing business state or triggering external actions.
- Minimize tokens: send only task-relevant fields, summarize or chunk long context, cache stable inputs, and store reusable embeddings or transcripts.
- Require explicit user consent before generating, cloning, publishing, or sending content that uses personal data, voice, likeness, customer messages, or third-party media.
- Emit sanitized observability: feature, tenant, model, token estimate, cost estimate, latency, retry count, queue age, and failure class.
Provider API Selection
- OpenAI: use the Responses API for new integrations; keep Chat Completions only for existing compatibility paths and verify model availability from the Models API.
- Gemini: use the Interactions API for new projects;
generateContentremains a supported legacy path. Use provider-specific response-format settings and still validate semantics locally. - Claude and other providers: use their current official SDK/API reference, pin versions in the host project, and isolate provider-specific request/response adapters behind the common service contract below.
- Never copy model IDs, endpoint versions, or parameter names across providers. Verify them at implementation time and record the verification date in the integration code or ADR.
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.
- 12d ago First seen · 69 lines · 62 tokens per session scan A 2a8a1aeca55d
skill-ai-orchestration is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (42 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 961 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI.
prompt-engineer
Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW).
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
prompt-engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.