Guide

/flow-next:guide is a stateless prompt-first router. It recommends one next workflow from your starting state. It does not create specs, charts, tasks, artifacts, or flowctl state.

Chart is an optional discovery route - never a mandatory stage and never a new pipeline stage. There is no fixed prospect → chart → capture conveyor. Each hop re-evaluates the matrix.

Picking a workflow vs picking a layer set

Guide answers “what do I run next for this piece of work?” The companion question - “which subsystems should this repo have switched on at all?” - is answered by Running Lean: the base loop is spec -> plan -> work, and tracker sync, QA, review backends, and the loops are layers with a stated cost, a trigger, and a manual invocation.

When to use it

When you are unsure which command to run next, which pre-build stage applies, or whether to skip chart / interview / plan:

"I have a vague multi-tenant idea - what should I run?"
"Should I chart this or just capture?"
"What's the smallest path for a one-line docs fix?"

Output contract

Every recommendation leads with a natural-language next prompt - the exact words or slash command you should say or run next. Flags are secondary (automation only). Then:

1. Route - named skill/path
2. Why (positive signal) - which matrix signal matched
3. Safe skip / narrow - when this route may be skipped or narrowed
4. Skip kind - signal absent vs despite unresolved risk

Skip kind matters:

Kind	Meaning
signal absent	The stage’s work is not needed - no consequential unknowns, no judgment gaps, no domain search
despite unresolved risk	You chose a smaller path on purpose; evidence, consent, and review contracts still apply later

Skipping a command never skips the contract that command would have provided.

Smallest-sufficient matrix

Match the starting state. First clear match wins. Chart only when one oversized idea is still unclear.

Starting state	Route	Positive signal	Safe skip / narrow
Looking for candidate investments across a domain	/flow-next:prospect	Domain search; need ranked candidates	Skip prospect when the idea is already singular. After selection: chart only if the candidate remains singular + oversized + unclear; otherwise capture
One large idea, unclear boundaries, several consequential unknowns	/flow-next:chart → briefing → capture	Singular effort too big for one capture; unknowns block stating intent	Skip chart (signal absent) when intent and boundaries are already stateable - go capture or author the spec directly. Chart is never mandatory
One meaningful idea whose intent and boundaries can already be stated	/flow-next:capture or author the spec directly	Clear meaningful idea	Skip chart (signal absent). Do not manufacture a chart for clear work
Existing structured brief with resolved business and technical choices	Capture the brief	Structured brief / chart briefing package ready	Skip chart. Narrow or skip interview only after capture read-back proves no material gaps - never pre-declare skip interview
Tiny, local, low-risk change that fits one implementation context	Direct change + review path appropriate to the repo	One-context fix; low risk	Skip chart and the full spec pipeline (signal absent). Still run the review/consent gates the change would need
A valid spec with unresolved judgment questions	/flow-next:interview	Spec exists; judgment gaps remain	Do not reopen discovery as chart unless the questions reveal the effort itself is not yet specifiable - only then route backward to chart
A ready spec whose work is understood	/flow-next:plan	Spec ready / work understood enough to task	Chart is too late. Unshaped oversized freeform ideas are not plan input - route those to chart first
Planned tasks ready to implement	/flow-next:work, then review / QA / ship choices	Tasks exist and are actionable	Stay on work + the repo’s review/QA/ship menu. Guide does not invent new ship stages
Unsure which of these situations applies	This matrix (this skill)	Ambiguous starting state	Ask at most one blocking question when two routes would materially differ; otherwise recommend one route

Recommendation shape

Next: <natural-language prompt or slash command to run>

Route: <name>
Signal: <positive signal>
Skip/narrow: <explicit safe skip or narrow condition>
Skip kind: signal absent | despite unresolved risk
Why not the alternatives: <one line>

Example next prompts

• “Run prospect for DX improvements in the skills tree”
• “Chart this: multi-tenant billing with unknown pricing and migration risks”
• “Capture what we just agreed - intent and boundaries are clear”
• “Interview fn-12 on the open product judgment questions”
• “Plan the ready spec fn-12”
• “Just fix the typo in README and open a small review”

Prompt-first behavior

1. Infer starting state from your description (optional read-only probes when a handle or path is named)
2. If exactly one matrix row fits, emit one recommendation
3. If two routes would materially change cost, consent, or discovery vs build path, ask at most one blocking question
4. Never present chart as required onboarding, a pipeline stage, or the default after prospect
5. Never mutate .flow/ or invoke write-capable flowctl subcommands

What guide never does

• Create charts, specs, or tasks
• Run plan/work/review for you
• Present chart as mandatory or as a pilot/build-loop stage
• Chain a fixed multi-stage conveyor
• Lead with flag vocabulary when a natural-language next prompt exists
• Claim that skipping a command also skips its evidence/consent/review contracts

Related

• Chart - the optional pre-capture discovery route
• When to Use - situation-oriented entry points
• Menu, Not a Rail - smallest sufficient workflow doctrine
• Pipeline Variations - five worked routes the router’s reasoning produces, epic to docs chore
• The Pipeline - every stage when you do follow the rails
• Cookbook - verified recipes for skip, chain, and evidence-first routes