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.
Best use case
flow-execution is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using flow-execution 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-execution/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How flow-execution Compares
| Feature / Agent | flow-execution | 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 implementing Flow tasks from Beads or spec.md, claiming ready work, applying TDD, recording task notes, committing, and syncing after task state changes.
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 Execution Use this lifecycle skill when implementation starts after a Flow plan or ready Beads task exists. ## Workflow 1. Select ready work from `bd ready` and claim it before editing. 2. Read the relevant spec, notes, patterns, affected files, and validation commands. 3. Record investigation findings with `bd note`. 4. Follow red-green-refactor: write the failing test, verify the failure, implement minimally, verify green, then refactor. 5. Commit targeted changes, close the Beads task with evidence, and sync markdown when policy requires it. ## Guardrails - Do not manually edit task status markers in markdown. - Do not skip failing-test evidence for behavior changes. - Do not silently descope messy tasks; refine or ask how to prioritize. - Preserve unrelated user changes and keep edits scoped to the claimed task. ## Validation - Verify the new test failed for the intended reason before implementation. - Run focused tests after each task and the repo’s aggregate verification before phase completion. - Record test output, commit reference, and closure reason in Beads. ## References Index - [Implement](../flow/references/implement.md) - [Discipline](../flow/references/discipline.md) ## Example User: "Implement auth flow." Action: claim the next ready Beads task, add code-path notes, write a failing auth test, implement the minimal behavior, verify, commit, close the task, and sync.
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-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.
flow-planning
Use when drafting PRDs, researching, planning, refining, revising, or creating .agents/specs/<flow_id>/spec.md worksheets for Flow.
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.