journey-preflight
Skill535 starsChanged 5 months agoMITView on GitHub
Use before a Butterbase app-building journey stage when project preflight is missing, older than 24 hours, or missing app credentials, or when journey-preflight is invoked directly.
- Reads credentials
- Installs packages
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Butterbase account: Call mcp__butterbase__list_regions (cheapest call).
- Very specific: line 21
MCP server connected: Check whether mcp__butterbase__* tools are listed in the agent's available tools.
- Very specific: line 25
App provisioned: Read 00-state.md front-matter for app_id.
- Very specific: line 30
CLI installed: Run butterbase --version. If "command not found":
- Very specific: line 31
Read the Toolchain section of 02-plan.md.
- Very specific: line 32
If CLI usage: no, skip this check.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Butterbase Preflight
Gate that ensures the user can actually talk to the Butterbase platform before any stage tries to. Writes results to docs/butterbase/03-preflight.md and stamps app_id + api_base into 00-state.md.
When to use
- Automatically as the first step of any
journey-*build stage when03-preflight.mdis missing, older than 24 hours, or00-state.md'sapp_idis null. - Directly via
/butterbase-skills:journey-preflightwhen the user wants to re-verify.
Procedure
For each check, write a one-line result to 03-preflight.md (<check> ✓/✗ <note>). Ask the user to fix any ✗ before continuing — do not auto-skip failures.
- Butterbase account. Call
mcp__butterbase__list_regions(cheapest call). Success → ✓. Auth error → ✗ with"Sign up at https://butterbase.ai, then run npx @butterbase/cli mcp install and complete the OAuth flow in your client (e.g. /mcp in Claude Code).". If MCP tool is not visible at all, jump to step 2. - MCP server connected. Check whether
mcp__butterbase__*tools are listed in the agent's available tools. Absent → ✗ with"Install the Butterbase MCP server: npx @butterbase/cli mcp install. See https://butterbase.ai/docs/mcp.". Present → ✓. - MCP OAuth complete. Auth for
mcp__butterbase__*calls is OAuth, not an env var — step 1 already proved it works iflist_regionssucceeded. If step 1 failed with auth error, retry after the user runs/mcp(orclaude mcp login butterbase) and completes browser consent.BUTTERBASE_API_KEY(bb_sk_…) is still relevant for runtime app code (functions, server-side@butterbase/sdk) — check separately at deploy time, not here. - App provisioned. Read
00-state.mdfront-matter forapp_id.- Non-null and
mcp__butterbase__manage_app(actionget_config) succeeds → ✓. - Null → ask the user:
"No app yet. Create one now? (yes/no — if no, you can paste an existing app_id)". On yes, callmcp__butterbase__init_app(ask for app name and region — recommendus-east-1as default). Captureapp_idandapi_basefrom the response. Update00-state.mdfront-matter. - User-provided app_id → verify with
manage_app get_config; on success update00-state.md.
- Non-null and
- CLI installed. Run
butterbase --version. If "command not found":- Read the Toolchain section of
02-plan.md. IfCLI usage: yes(default), prompt: "Install@butterbase/cliglobally now? (yes / skip)". On yes, runnpm install -g @butterbase/cli. On skip, note in03-preflight.mdthat the CLI is not installed and which workflows will require dashboard fallback. - If
CLI usage: no, skip this check.
- Read the Toolchain section of
03-preflight.md format
# Preflight — <ISO date>
- account ✓
- mcp_connected ✓
- api_key ✓
- app_provisioned ✓ app_id=app_abc123 region=us-east-1
Re-run with /butterbase-skills:journey-preflight.Outputs
- Writes/overwrites
docs/butterbase/03-preflight.md. - Updates
00-state.mdfront-matterapp_id,api_base,last_updated, and ticks- [x] preflight.
Anti-patterns
- ❌ Echoing the API key value back to the user.
- ❌ Skipping a failed check ("I'll just try anyway"). Stop and ask the user to fix it.
- ❌ Calling
init_appwithout confirming with the user — apps cost money on paid plans.
Other versions1 project uses a version of this.
Word for word · 1
- butterbase-ai/butterbase-skills★ 535100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository40 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- butterbase-skillsSkill
- agentsSkill
- aiSkill
- auth-setupSkill
- build-appSkill
- contributingSkill
- debug-rlsSkill
- deploy-frontendSkill
- durable-objectsSkill
- function-devSkill
- integrationsSkill
- journey-agentsSkill
- journey-aiSkill
- journey-authSkill
- journey-deploySkill
- journey-docsSkill
- journey-durableSkill
- journey-frontendSkill
- journey-functionsSkill
- journey-ideaSkill
- journey-planSkill
- journey-ragSkill
- journey-realtimeSkill
- journey-rlsSkill
- journey-schemaSkill
- journeySkill
- journey-storageSkill
- journey-submitSkill
- journey-substrateSkill
- journey-templatesSkill
- meetingsSkill
- migrationsSkill
- paymentsSkill
- rag-devSkill
- realtimeSkill
- schema-designSkill
- storageSkill
- substrateSkill
- templatesSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

