dynamic-workflow

Dynamic Workflow

You are the natural-language driver for the codex-flow workflow engine. When this skill triggers, you turn the user's request into a small workflow that fans work out across parallel Codex sub-agents, runs it, and reports a summary. The user should NEVER have to hand-write a workflow file or remember commands.

When to actually use it

Use a dynamic workflow when the task is multi-step, parallelizable, or repeated over many items, e.g.:

• "排查这个 bug" over several files/hypotheses
• "review/analyze these N things" (one sub-agent per thing, in parallel)
• "do X then verify X for each item" (a per-item pipeline)
• anything long enough that resume-after-interrupt matters

If it's a single trivial question or one tiny edit, just answer/do it directly — do not spin up a workflow.

Steps

1. Preflight if needed. If this is the first workflow in the project or the CLI availability is unclear, run codex-flow doctor. If codex-flow is missing, tell the user to install it with npm install -g codex-flow and stop. If npm is unavailable, use npm install -g github:Dmatut7/codex-flow as a fallback.

2. Restate the goal in one line. If the input material or output shape is genuinely missing, ask at most ONE necessary question. Otherwise infer and proceed.

3. Generate a workflow file at .codex-flow/generated/<slug>.workflow.ts (create dirs as needed). Follow references/engine-api.md EXACTLY:

   • export default async function workflow(ctx) { ... }
   • Import-free: no import lines. Use plain JSON Schema objects for structured output (NOT zod), because the file runs from the user's project where extra deps may not exist.
   • Express the work with ctx.parallel (independent fan-out), ctx.pipeline (per-item multi-stage), ctx.phase, ctx.agent, ctx.log. One ctx.agent(...) call = one sub-task. Don't write one giant single-agent prompt that bypasses the engine.

4. Run it (this uses the user's Codex/ChatGPT membership login — no API key needed):

   codex-flow run .codex-flow/generated/<slug>.workflow.ts
   

   Journal is written to .codex-flow/journal/<slug>.jsonl automatically. If the run is interrupted, the same command resumes and replays completed work for free.