AI Engineering Cookbook Skills

Plugin cookbook-skills from marketplace ai-engineering-cookbook in exponen-agi/ai-engineering-cookbook. Commands read from the repo's manifest — 21 days ago.

Skills (5)

• agent-tracing

  Make an AI agent's behaviour visible by tracing it with the OpenTelemetry GenAI semantic conventions — spans for agent turns, model calls, tool calls and Agent Skill loads, plus token and cost accounting. Use when the user asks why an agent did something, why it is slow or expensive, how to debug an

• doc-coherence

  Keep a documentation corpus coherent by enforcing single-source-of-truth — each fact/term has ONE canonical owning file; others point to it instead of restating it. Use when docs/specs/markdown files drift or contradict each other, when the user worries about "which doc is right", or when setting up

• eval-harness

  Build, review or repair an eval suite (a golden dataset) that scores whether an LLM feature is actually any good, and wire it into CI as a blocking gate. Use when the user is adding a feature that calls a model, asks how to test a prompt or an agent, says their evals always pass or never catch anyth

• prompt-optimizer

  Engineer production-grade prompts for frontier LLMs (Claude, GPT, Gemini). Use when the user wants to optimize, rewrite, evaluate, or troubleshoot a prompt — including system prompts, user-turn prompts, agent instructions, or API pipeline prompts. Applies framework selection (COSTAR / RISEN / RODES

• skill-review

  Review, harden or author an Agent Skill before you install, publish or trust it — the whole skill folder, not just its SKILL.md. Use when the user downloads a skill from a registry or another repository, asks whether a skill is safe, asks what the bundled scripts in a skill do, asks why a skill neve

Similar plugins