flow-setup
Use when initializing Flow in a repo, configuring .agents, installing or checking Beads bd, setting local-only sync policy, or creating first project context files.
Best use case
flow-setup is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when initializing Flow in a repo, configuring .agents, installing or checking Beads bd, setting local-only sync policy, or creating first project context files.
Teams using flow-setup should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/flow-setup/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How flow-setup Compares
| Feature / Agent | flow-setup | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when initializing Flow in a repo, configuring .agents, installing or checking Beads bd, setting local-only sync policy, or creating first project context files.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Flow Setup Use this lifecycle skill for project initialization, installation checks, setup validation, and first context files. ## Workflow 1. Detect project root, existing `.agents/` state, Beads availability, and repo-native commands. 2. If Beads is missing, offer official Beads (`bd`) installation or no-Beads degraded mode. 3. Initialize Flow context files from templates and prefer local-only Beads settings. 4. Store setup decisions in Beads notes when a backend exists. 5. Re-run setup validation before handing off to planning. ## Guardrails - Prefer `.git/info/exclude` for local-only ignores. - Do not edit `.gitignore` unless the user wants shared repository policy. - Do not run `bd dolt push`, export, or auto-stage unless policy explicitly allows it. - Keep setup idempotent; preserve existing user context files and merge rather than overwrite. ## Validation - Confirm `.agents/` root, `workflow.md`, `patterns.md`, `knowledge/index.md`, and Beads config existence when setup is expected. - Confirm Beads config defaults are local-only: no git ops, no auto export, and no auto git add. - Run repository validation commands documented in `.agents/workflow.md` or hook context. ## References Index - [Setup command details](../flow/references/setup.md) - [Validate command details](../flow/references/validate.md) - [Refresh command details](../flow/references/refresh.md) ## Example User: "Use Flow to set up this repo." Action: detect the repo root, initialize `.agents/`, configure local-only Beads, capture setup notes, validate files, then hand off to `flow-planning` for the first flow.
Related Skills
flow-memory-keeper
Use at task, phase, flow, sync, archive, finish, revise, or failure checkpoints to keep Flow specs clean, capture learnings and failures, elevate durable patterns, and refine this skill with project-specific nuances
flow
Use when a repository has .agents, when the user asks for Flow lifecycle routing, Beads-backed task memory, spec-first planning, TDD implementation, sync/status, review, finish, archive, or /flow:* help.
flow-sync-status
Use when syncing Beads state to markdown, checking Flow status, refreshing context docs, validating task markers, or reporting ready/blocked Flow work.
flow-planning
Use when drafting PRDs, researching, planning, refining, revising, or creating .agents/specs/<flow_id>/spec.md worksheets for Flow.
flow-execution
Use when implementing Flow tasks from Beads or spec.md, claiming ready work, applying TDD, recording task notes, committing, and syncing after task state changes.
flow-completion
Use when reviewing, finishing, archiving, reverting, validating, or cleaning up Flow work after implementation or phase completion.
vue
Use when editing Vue projects, .vue files, vue.config.js, Vue 3 components, Composition API, <script setup>, SFC state, deployment workflows, or Vue CI configuration.
vite
Use when editing Vite projects, vite.config.ts, vite.config.js, Vite plugins, HMR, asset bundling, frontend build settings, deployment config, or Litestar/Vite integration.
uvicorn
Use when deploying ASGI apps with uvicorn, editing uvicorn CLI commands, Config or Server usage, workers, reload, event loop selection, SSL, lifespan, logging, or development server behavior.
tracer
Use when tracing execution paths, mapping dependencies, understanding unfamiliar code, following data flow, investigating end-to-end behavior, debugging call chains, or deciding which files to read next.
testing
Use when writing or refactoring tests, editing test_*.py, *.test.ts, *.spec.ts, conftest.py, vitest.config.ts, pytest fixtures, mocks, coverage, async tests, anyio, or test failure debugging.
terraform
Use when creating, adopting, refactoring, or operating Terraform, *.tf files, .terraform.lock.hcl, terragrunt.hcl, root modules, backends, state, workspaces, imports, CI plan/apply, tests, or policy checks.