Forge Intake

forge-intake — Prompt Master intake + dispatch shaping

Self-improvement substrate (wp-skill-evals, 2026-07-31): before applying this skill, read learnings.md in this skill's own folder and honor its corrections. After a run that produced a genuine correction (an owner fix, a false assumption caught, a preference stated), append it to learnings.md with a date and real evidence — never invent a lesson that didn't happen.

Two standing behaviours the owner requested (2026-07-13): Prompt Master is always on.

1. INTAKE — ask before building (every build task; trivial tasks skip)

At the START of any /forge task that BUILDS/creates/automates a real deliverable (L2+), before writing work packages, run the intake so the project's goal is captured. Skip only truly trivial turns (a status question, a one-line fix, "what does X do").

1. Detect the project type with forge-router (website · ecommerce · fullstack · electron · n8n · integration · rag · voice · prediction · scraping · dashboard · or a new/mixed type).
2. Generate the question list — the owner chose ONE big list:

   node .claude/forge-bin/forge-intake.cjs --type <slug> --task "<one-line task>" --run <run_id>
   

   It reads the subagent-brainstormed bank at .claude/config/intake/question-bank.json (universal questions first, then type-specific; required before recommended). Use --json if you want to map it to an ask-tool; use --tier required for a quick essential round on small builds.
3. For a NEW / mixed / unusual project type (no matching byType slug): dispatch ONE subagent to brainstorm 6-10 extra high-value questions for that specific project, save them as a JSON array, and merge with --extra <file.json>. (This is the "Prompt Master creates questions with subagent help" path.) Optionally propose adding the new type to the bank.
4. Present the list to the owner as ONE consolidated list (the numbered output, or batched AskUserQuestion rounds of ≤4 if you prefer buttons — the tool's options map straight onto choices). Let the owner answer per number or pick options; every question is skippable.
5. Record the answers into the run: they become the basis for forge-prd (PRD → tickets) and are quoted in the Boss dispatch prompts. A material answer the owner corrects can also be persisted via forge-reflect as an owner-correction lesson.

HONESTY: never build on assumed answers — if the owner skips a required question, state the assumption you're proceeding with. The intake sharpens the goal; it does not replace owner approval gates.

2. DISPATCH SHAPING — every Boss dispatch is Prompt Master-shaped

Every work package the Lead/Head Chef emits MUST already carry the Prompt Master agentic shape (this is the existing forge-router Work Package format): target/deliverable · allowed actions + path anchors · forbidden actions / scope lock · stop condition + human-review triggers · success/acceptance criteria · evidence-required · no vague verbs.

Lint a dispatch prompt before sending (advisory, non-blocking):

node .claude/forge-bin/forge-promptcheck.cjs <promptFile>        # or: echo "<prompt>" | forge-promptcheck.cjs -

It scores the prompt X/7 across those dimensions and names what's missing (e.g. "add a scope lock"). --strict exits 1 below 6/7 for a hard gate; default is a nudge. A canonical Forge work package already scores 6-7/7 — this catches the weak, vague ones ("improve the thing and fix stuff" → 1/7) before they reach a Boss.

Notes

• Zero-dependency, deterministic, no LLM inside the tools, no telemetry, no UI changes (dashboard stays read-only). The bank is owner-editable JSON.
• The intake question bank was generated by a 6-agent subagent brainstorm and is Forge-owned + synced; extend byType for new domains.
• Intake fires for BUILD tasks; it is not a gate on Q&A/status turns. Dispatch shaping applies to every real Boss dispatch.

Iteratieve intake (sweep-verbetering 2026-07-31 — 10 bronvideo's, zie .claude/forge-research/YT-SWEEP-2026-07-31.md)

Waar het kanaal het toelaat (dashboard-wizard, interactieve chat): stel vragen één per keer in plaats van één batchlijst — elk antwoord stuurt de vólgende vraag, tot er gedeeld begrip is. Sluit ALTIJD af met de meta-vraag: "Wat moet ik zelf nog verhelderen dat ik niet gevraagd heb?" — die vangt de gaten die de vragensteller zelf mist. Leg de scope-uitkomst vast in vier lagen: core (moet nu) · nice-to-have (mag nu) · maybe-later (mét concrete trigger wanneer wel) · expliciet-uit-scope (opgeschreven zodat niemand het stilzwijgend alsnog bouwt). Batch-vragen blijven het terugvalpad voor niet-interactieve runs; de recommended-markering per vraag blijft gelden (verdiend advies, nooit random).