experience-creatorlisted

Author runnable OpenExpertise experience files — heterogeneous executable graphs (agent / skill / tool / dataset / experience nodes) backed by a persistent blackboard. Use this skill whenever the user wants to create, write, build, scaffold, or design an OpenExpertise experience: "make an experience for X", "create an OpenExpertise flow", "scaffold a multi-step LLM pipeline with reproducible state". Also use when the user is confused about the experience.yaml format — the schema, state, edges, for_each, pipelines, loops — or when an experience errors and needs debugging. Trigger this whenever the user describes a repeatable multi-step or LLM-backed job that benefits from a graph with state, even if they never say "experience". Do NOT use it to merely run an existing experience.
xingchengxu/OpenExpertise · ★ 4 · AI & Automation · score 75

Install: claude install-skill xingchengxu/OpenExpertise

# Experience Creator Turn a user goal into a **runnable `experience.yaml`** plus its accompanying prompt files, tool modules, and dataset descriptors. The result is a directory that `oe run` can execute end-to-end. The deep material lives in three reference files — read them when the step says so: - `references/api-reference.md` — every field of `experience.yaml`, every node kind's options, every control-flow construct. - `references/patterns.md` — copy-paste topologies (linear, fan-out, pipeline, bounded loop, dataset → agent → score). - `references/lessons.md` — gotchas from earlier V1 work (schema enforcement, cache invalidation, `exactOptionalPropertyTypes`, ESM imports, etc.). Starter templates are in `assets/templates/`. Two worked examples are in `assets/examples/`. A standalone validator is `scripts/validate-experience.mjs`. --- ## Step 0 — Confirm OpenExpertise is installed ```bash oe --version ``` If `oe` is not on PATH, point the user at the OpenExpertise repo and tell them to either install the CLI (`npm install -g @openexpertise/cli`) or run via the workspace (`node packages/cli/dist/bin.js`). --- ## Step 1 — Establish the goal (do NOT skip) Before writing a line of YAML, get crisp answers to: 1. **What does this experience produce?** A reviewed PR? A summarized research finding? A risk score? Name the artifact concretely. 2. **What's the unit of work?** The thing one node does once: review one file, research one topic, score one transacti