LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para (SKILL.md metadata excerpt)
Setup not establishedSource observation · Source example · File structure observedCheck method & evidence →
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage. (SKILL.md metadata excerpt)
Setup not establishedSource observation · Source example · File structure observedCheck method & evidence →
Get reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs. (SKILL.md metadata excerpt)
Setup not establishedSource observation · Source example · File structure observedCheck method & evidence →
Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores each file against a structured checklist (SKILL.md metadata excerpt)
Setup not establishedSource observation · Source example · File structure observedCheck method & evidence →
Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores each file against a structured checklist (SKILL.md metadata excerpt)
Setup not establishedSource observation · Source example · File structure observedCheck method & evidence →
Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix. (SKILL.md metadata excerpt)
Setup not establishedSource observation · Source example · File structure observedCheck method & evidence →