Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →butterbase-ai/journey-ai
Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai skill. Calls manage_ai (update_config) to set defaults and optionally BYOK. Skipped if the plan has no LLM/embeddings usage.
Passed 15 of 23 test cases with the skill, and 3 of 23 without it.
and 12 more in the full report
14 fixed3 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Under what exact state condition in `00-state.md` does the journey orchestrator automatically dispatch stage 3f?
| Checked | Without skill | With skill |
|---|---|---|
| Dispatches stage 3f when current_stage is set to ai. | Missed | Passed |
The instructions your model reads when the skill loads.
Stage 3f of the guided journey. Configure AI gateway defaults (model, BYOK).
journey when current_stage: ai./butterbase-skills:journey-ai.(n/a)) if the plan has no AI section.If docs/butterbase/03-preflight.md is missing, older than 24 hours, or 00-state.md has app_id: null, invoke butterbase-skills:journey-preflight first. Wait for it to return successfully before proceeding.
docs/butterbase/02-plan.md — the AI section.docs/butterbase/00-state.md — for app_id.Refresh docs. Call butterbase_docs with topic: "ai". For BYOK and model lists, also WebFetch https://docs.butterbase.ai/ai. Skip if cache is fresh.
Read the AI section. Print it back: "About to configure AI: default model=<m>, BYOK=<yes/no>. Proceed?". Wait for yes.
Invoke butterbase-skills:ai via the Skill tool with the AI plan and app_id. The wrapped skill calls manage_ai action: update_config (and per-provider key updates if BYOK).
Smoke: call manage_ai action: chat with a tiny prompt ("say ok") to confirm the gateway responds.
Append one line to docs/butterbase/04-build-log.md:
<ISO timestamp> ai manage_ai ok
Tick - [x] ai in 00-state.md, set current_stage: to the next unchecked stage.
Return to journey orchestrator (or ask "Continue to the next stage? (yes/no)").
04-build-log.md.manage_ai action: list_models — list first.test cases passed, vs 3 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.