Capture

/flow-next:capture turns a recent design conversation into a durable spec without losing the source of each requirement.

The host agent extracts user turns, drafts a structured spec at .flow/specs/<spec-id>.md, tags every acceptance criterion with its origin, and shows the full draft before any file is written.

When to use it

After a design discussion that produced enough material for a spec but stopped short of formal authoring. Capture is upstream of /flow-next:plan and /flow-next:work.

Use it when:

• The conversation already contains the requirement.
• You want the spec to credit user statements vs. agent inferences.
• A teammate will pick up the work and never saw the chat.

If the conversation is thin or one-sided, run /flow-next:interview afterwards to deepen it.

Source tags

Every R-ID carries a tag so reviewers can see where it came from:

• [user]: verbatim user requirement
• [paraphrase]: restated user requirement
• [inferred]: agent filled the gap
• [strategy:<track>]: derived from STRATEGY.md

The read-back surfaces the [inferred] count up front so the user can reject anything fabricated before it lands on disk.

Mandatory read-back

Capture never writes silently. The full draft is shown through the platform’s blocking question primitive. Only an explicit approve writes the spec file. Anything else aborts cleanly with no on-disk state.

Mark-ready offer

Once readiness is adopted in the repo (≥1 spec already marked ready) and tracker.readyState is not configured, an approve is followed by one optional consent question: mark the new spec ready for execution? Default is keep-draft — readiness is the human gate, so the recommendation is to bless the spec after reading it on disk. Non-adopters never see the question; tracker-connected repos set readiness on the board instead (a local toggle would be overwritten by the next sync). --rewrite resets a previously-ready spec back to draft — a full re-authoring re-opens the blessing — and announces the reset only when it actually changed the flag. Autofix never writes readiness.

flowchart LR
  Chat["Conversation"] --> Extract["Extract user turns"]
  Extract --> Draft["Draft spec"]
  Draft --> Tag["Tag R-IDs by source"]
  Tag --> Read["Read-back to user"]
  Read -->|approve| Write[".flow/specs/<id>.md"]
  Read -->|edit / abort| Stop["No write"]

Flags

Flag	Use
mode:autofix	Scripted use; runs without questions and requires --yes to commit.
--rewrite <spec-id>	Re-synthesize over an existing spec instead of refusing.
--from-compacted-ok	Override the compaction-detection refusal for compressed transcripts.
--override-strategy	Proceed when the draft contradicts an active STRATEGY.md track; prompts to log a decision-record entry.

Next step

/flow-next:plan <spec-id>

Or, to deepen via structured Q&A first:

/flow-next:interview <spec-id> --scope=business