Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →butterbase-ai/journey-docs
Use as the docs-priming stage of the Butterbase journey, immediately after journey-preflight and before the first build stage. Reads the plan to discover which capabilities the app uses, calls butterbase_docs once per relevant topic, and caches a summary the build stages can re-read.
Passed 3 of 10 test cases with the skill, and 2 of 10 without it.
and 4 more in the full report
6 fixed1 passed either way11 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our team added Durable workflows and standard serverless Functions to docs/butterbase/02-plan.md. Which distinct Butterbase doc topics need to be queried?
| Checked | Without skill | With skill |
|---|---|---|
| The topic 'functions' is requested to cover both Durable workflows and serverless Functions. | Missed | Passed |
The instructions your model reads when the skill loads.
A short, mechanical priming step. The goal is that every downstream stage starts with the relevant docs already in the conversation, so the model doesn't invent API shapes.
Invoke automatically after journey-preflight returns. Also invoke standalone (/butterbase-skills:journey-docs) any time the user changes the plan or you realize a stage is using a capability you haven't refreshed this session.
Read the plan. Open docs/butterbase/02-plan.md. Identify every Butterbase capability in use (Tables → schema; RLS → auth; Auth → auth; Storage → storage; Functions → functions; AI → ai; RAG → rag; Realtime → realtime; Durable → functions; Frontend → frontend; Integrations → integrations; Substrate → substrate; Payments → billing).
Call butterbase_docs per topic. For each unique topic from step 1, call butterbase_docs with that topic argument. Skip duplicates.
Write the cache file. Create docs/butterbase/03b-docs-cache.md with this structure:
---
primed_at: <ISO timestamp>
topics: [<comma-separated list>]
---
# Docs Cache
## <topic-1>
<one-paragraph summary of what the MCP doc says — key endpoints, common patterns, gotchas>
URL: https://docs.butterbase.ai/<area>
## <topic-2>
...
Update 00-state.md. Tick the docs row.
Return. One-line summary: "Primed docs for: schema, auth, storage, functions. Cache at docs/butterbase/03b-docs-cache.md."
butterbase_docs with topic: "all". Burns context. Call once per relevant topic instead.test cases passed, vs 2 / 10 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.