New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Journey Plan

by butterbase-ai in butterbase-ai/butterbase-skills

Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md.

MITAuto-check passedAI & LLM Engineering

Install Journey Plan

skills CLI
$ npx skills add butterbase-ai/butterbase-skills --skill journey-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install butterbase-ai/butterbase-skills journey-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/journey-plan .claude/skills/journey-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
journey-plan
GitHub stars
534
Token cost
~2.1k tokens
SKILL.md length
731 words
Files
1
Skills in repo
39
Repo updated
First seen
Licence
MIT

At a glance

Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md.

  • Works in 2 steps: Invoke butterbase-skills:integrations… → If a toolkit fits, the plan should…
  • AI & LLM Engineering work in your project
  • SKILL.md covers When to use, Inputs, Procedure and 02-plan.md format, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Journey Plan is an agent skill from butterbase-ai/butterbase-skills. Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Translates the idea + capability map into a concrete Butterbase plan — tables (with columns/types/RLS shape), auth providers, function list (name + trigger), storage buckets, AI/RAG/realtime/durable usage, and the chosen frontend stack. In hackathon mode, ruthlessly cuts scope into a "ship now" vs "post-hackathon" split. Produces docs/butterbase/02-plan.md.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. The repository describes itself as: Plugin for Butterbase.ai. The licence is MIT.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “ship now”
  • “post-hackathon”
  • “/journey-plan”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Invoke butterbase-skills:integrations and call manage_integrations action: "list_available" to see what Composio covers for this app.
  2. If a toolkit fits, the plan should record "via manage_integrations (toolkit: )" instead of naming an external SDK.

What it can do on your machine

Read from SKILL.md and the folder at commit aa8ae69. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Journey Plan loads about 2.1k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 731 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from butterbase-ai/butterbase-skills at commit aa8ae69, republished under its MIT licence (© butterbase-ai). 731 words, ~2,090 tokens.

Download SKILL.mdSave it as .claude/skills/journey-plan/SKILL.md (or your agent's skills folder).
name
journey-plan
description
Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Translates the idea + capability map into a concrete Butterbase plan — tables (with columns/types/RLS shape), auth providers, function list (name + trigger), storage buckets, AI/RAG/realtime/durable usage, and the chosen frontend stack. In hackathon mode, ruthlessly cuts scope into a "ship now" vs "post-hackathon" split. Produces docs/butterbase/02-plan.md.

Journey: Plan

Stage 2 of the guided journey. Turn the idea brief into an actionable Butterbase plan.

When to use

  • Dispatched by journey when current_stage: plan.
  • Directly via /butterbase-skills:plan.

Inputs

  • docs/butterbase/01-idea.md (must exist — if absent, bounce back to journey-idea).
  • docs/butterbase/00-state.md (for hackathon_mode, hackathon_deadline).
External services — check built-ins first

When the plan needs email, messaging, calendar, CRM, docs, or project-management integration:

  1. Invoke butterbase-skills:integrations and call manage_integrations action: "list_available" to see what Composio covers for this app.
  2. If a toolkit fits, the plan should record "via manage_integrations (toolkit: <name>)" instead of naming an external SDK.

When the plan needs payments:

  1. Invoke butterbase-skills:payments.
  2. Default to Stripe Connect via manage_billing unless the user's region forces a fallback (see the payments skill).
  3. Record the choice ("Stripe Connect" or "<regional gateway> via function proxy") in the plan's Payments section.

Procedure

Work through these sections in order. After each section, write the result to 02-plan.md before moving on. One question at a time per the spec's questioning discipline.

  1. Tables. Read the capability map. Propose a starter table list with columns and types — recommend, don't ask blank. Example: "Tables I'm seeing: users, orders, items. Missing any?" Then for each table: "<table>.<column>: should this be a uuid / text / int / timestamp / enum?". Confirm primary keys, foreign keys, indexes that are obvious (foreign-key columns).

  2. RLS model. For each table: "Can user A see user B's <table> rows? ① no, strict isolation ② yes, public-read ③ only shared via explicit grant." Decide policy shape. In hackathon mode, prefer option ① and recommend manage_rls action: create_user_isolation.

  3. Auth. "OAuth providers: ① Google only ② Google + GitHub ③ email/password too ④ none (anonymous app)." Also ask: "Need a demo / judge account seeded? (hackathon mode only)".

  4. Functions. For each function from the capability map: "<name>: trigger = HTTP / cron / WebSocket? If cron: schedule? If HTTP: idempotency needed?".

  5. Storage. If used: "Which objects (avatars, attachments, …)? Public-read or per-user?".

  6. AI / RAG / realtime / durable. Only if used. Capture model choice (AI), collections (RAG), tables to subscribe to (realtime), object kinds (durable).

6b. Agents. Only if create_agent is tagged in the idea. For each agent, capture:

  • name (slug), one-line purpose.
  • Tool surface: which builtins (query_table, insert_row, …), which functions (must exist in the Functions section), which MCP servers (URL + transport).
  • Visibility: private | authenticated | public. If public AND any write tool is reachable, mark safety_acknowledged_needed: true and set per-IP / per-user / per-app rate limits + daily_budget_usd.
  • Default model.
  • Note that the agent record will not be carried by clone replay — the spec JSON (under agents/<name>.json) rides along in the repo snapshot, so this matters for the publish stage too.
  1. Frontend stack. "Frontend: ① Vite + React ② Next.js ③ static HTML ④ none (API-only)." Write to 00-state.md frontend_stack.

7b. Publish-as-template. Read publish_as_template from 00-state.md front-matter (set by journey-idea). If yes or unlisted, plan for it now:

  • README outline (one-liner, env-var-per-function list, OAuth setup, agent re-import, MCP server registration, seed data, first-run smoke).
  • Which env vars use the auto-mint convention (butterbase_api_key) vs. require manual user input on clone.
  • Whether agents/*.json files need to be exported and committed (yes if Agents section is non-empty).
  • Note that publishing requires butterbase repo push to upload the source tree as a snapshot — without it, cloners get an empty file tree.
Show full SKILL.md (190 more words)Show less
Toolchain question

Ask: "Will your app's code use @butterbase/sdk only in the frontend, only server-side (functions, scripts), or both?" Record under Toolchain → SDK surfaces.

Ask: "Want to install @butterbase/cli for the local dev loop (logs, scaffolding, key rotation)? (yes/no — default yes)" Record under Toolchain → CLI usage.

  1. Scope cut (hackathon mode). Re-read the must-haves list. For each, ask: "Ship now or post-hackathon?" Write the cut list into 02-plan.md's "Post-hackathon" section.

  2. Annotate skipped stages. For every build stage NOT used in this plan (check the capability map and feature list), update 00-state.md's checklist to read - [ ] <stage> (n/a) for that row. Also do this for rls if hackathon_mode: true (mark as (folded into schema)).

  3. Final approval. Show the user the assembled plan and ask: "Plan looks good? (yes / revise <section>)". Loop until yes.

02-plan.md format

markdown
# Plan

## Tables
- `users` (id uuid pk, email text unique, created_at timestamp)
- `orders` (id uuid pk, user_id uuid fk→users.id, status enum[pending,paid,shipped], total int, created_at timestamp; index on user_id)
- ...

## RLS
- `orders`: user-isolation (create_user_isolation, owner column = user_id)
- ...

## Auth
- Providers: Google
- Demo user: yes (email demo@example.com, password set via seed)

## Functions
- `stripe-webhook` — HTTP, idempotency table `_processed_events`
- `daily-digest` — cron 0 9 * * *  UTC

## Storage
- bucket: `avatars` (per-user, private; download via presigned URL)

## AI / RAG / realtime / durable
- (none)

## Agents
- `order-summariser` — purpose: summarise a user's recent orders on demand.
  - Tools: builtin `query_table`, function `format-currency`.
  - Visibility: authenticated. Rate: 60/hr per user. Daily budget: $5.
  - Default model: claude-haiku-4-5-20251001.
  - Spec file: `agents/order-summariser.json` (committed to repo).
- (omit section entirely if no agents)

## Publish-as-template
- Intent: yes / unlisted / no
- README outline: <bullet list of sections>
- Env vars cloners must supply: <list per function>
- Auto-mint eligible keys: `butterbase_api_key` (etc.)
- Agent specs to bundle: `agents/*.json`
- Snapshot push: `butterbase repo push` at end of journey-templates.
- (omit section entirely if publish_as_template = no)

## Frontend
- Vite + React

## Toolchain

- **SDK surfaces**: <client-side only | server-side only | both>
  - Client-side: install `@butterbase/sdk` in the frontend; use `auth`, `db`, `storage`, `realtime`.
  - Server-side: install `@butterbase/sdk` in functions / scripts; use the service-key flow for elevated access.
- **CLI usage**: <yes / no>
  - Yes (default): use `butterbase` CLI for local scaffolding, log tailing (`butterbase logs <fn>`), function invocation, and key rotation.
- **Why both**: MCP tools provision and orchestrate; SDK + CLI are the runtime + dev loop.

## Build order
1. schema
2. rls (folded into schema in hackathon mode)
3. auth
4. storage
5. functions
6. ai          (if used)
7. rag         (if used)
8. realtime    (if used)
9. durable     (if used)
10. agents     (if used — must come after functions, ai, and any MCP-server setup)
11. frontend
12. deploy
13. templates (optional — only if publish_as_template != no)

## Post-hackathon
- email notifications (deferred)
- admin dashboard (deferred)

Outputs

  • Writes docs/butterbase/02-plan.md.
  • Updates 00-state.md: tick - [x] plan, set frontend_stack, set current_stage: preflight, annotate skipped build stages with (n/a).

Anti-patterns

  • ❌ Asking the user to design every table column without recommending defaults first.
  • ❌ Skipping the scope-cut section in hackathon mode.
  • ❌ Writing the plan only at the end — write as you go so progress survives a crash.

© butterbase-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/journey-plan of butterbase-ai/butterbase-skills.

Open the folder on GitHubat commit aa8ae69

Compare with similar skills

Journey Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Journey Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Journey Plan this skillbutterbase-ai/butterbase-skills534—~2.1kAutomated safety check: PassMIT
Agent BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs13k8 repos~3kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.9k14 repos~656Automated safety check: PassApache-2.0

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.9k GitHub starsUsed in 14 repos~656 tokens
    AI & LLM EngineeringAuto-check passed

  • Planning With Files

    jarrodwatts/claude-code-config

    Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

    1.1k GitHub starsUsed in 5 repos~967 tokens
    AI & LLM EngineeringAuto-check passed

More from butterbase-ai/butterbase-skills

All 39 skills in this repo

  • AI

    butterbase-ai/butterbase-skills

    A skill your agent uses when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage

    534 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed

  • Auth Setup

    butterbase-ai/butterbase-skills

    A skill your agent uses when configuring OAuth providers (Google/GitHub/Apple/X/etc.), setting up post-login auth hooks, tuning JWT lifetimes, or generating service API keys

    534 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed

  • Build App

    butterbase-ai/butterbase-skills

    A skill your agent uses when building a new Butterbase app from scratch, creating a full-stack application, or when the user asks to set up a complete backend with database, auth, and deployment

    534 GitHub stars~4.9k tokensUpdated 5 days ago
    Auto-check passed

  • Contributing

    butterbase-ai/butterbase-skills

    A skill your agent uses when contributing to the Butterbase codebase, adding new MCP tools, creating API routes, writing migrations, or understanding the monorepo architecture

    534 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

  • Debug Rls

    butterbase-ai/butterbase-skills

    A skill your agent uses when users report access denied errors, see wrong data, RLS policies are not working, or when troubleshooting Row-Level Security issues in Butterbase

    534 GitHub stars~3.5k tokensUpdated 5 days ago
    Auto-check passed

  • Deploy Frontend

    butterbase-ai/butterbase-skills

    A skill your agent uses when deploying a frontend (React, Next.js, or static HTML) to a live URL on Butterbase, or when troubleshooting deployment issues like MIME type errors or blank pages

    534 GitHub stars~2.8k tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Journey Plan

What does Journey Plan do?

Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Journey Plan is an agent skill from butterbase-ai/butterbase-skills.md.

When should I use Journey Plan?

Journey Plan fits situations like: AI & LLM Engineering work in your project.

How do I install Journey Plan in Claude Code?

Run `npx skills add butterbase-ai/butterbase-skills --skill journey-plan -a claude-code`. Or copy the skill folder (skills/journey-plan in butterbase-ai/butterbase-skills) into .claude/skills/journey-plan in your project. Claude Code loads it when a task matches its description.

How do I install Journey Plan in Codex?

Run `npx skills add butterbase-ai/butterbase-skills --skill journey-plan -a codex`. Or copy the skill folder (skills/journey-plan in butterbase-ai/butterbase-skills) into .agents/skills/journey-plan in your project. Codex loads it when a task matches its description.

Can I use Journey Plan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add butterbase-ai/butterbase-skills --skill journey-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/journey-plan, .gemini/skills/journey-plan, .github/skills/journey-plan and .opencode/skills/journey-plan in your project.

What does Journey Plan need to run?

SKILL.md names no scripts, command-line tools or credentials: Journey Plan is instructions for the agent only.

Does Journey Plan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Journey Plan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Journey Plan use?

Journey Plan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Journey Plan use?

About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Journey Plan?

Skills that share tags, products or a category with Journey Plan: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Journey Plan?

butterbase-ai (a GitHub organization) maintains it in butterbase-ai/butterbase-skills, which has 534 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 5, 2026.

Source: butterbase-ai/butterbase-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.