open/voyage
1
0
Fork 0
Code Issues Releases 13 Activity
voyage/evals/skill-interviewing-effect-hollow/prompt.md
Kjell Tore Guttormsen f6e18a1d09
 feat(skills): interviewing - one source for the brief's question round (order 7e) 
/trekbrief Phase 3 carried the interview form inline. It now asks for the
new skill voyage:interviewing by name (allowed-tools gains Skill) and keeps
only its own contract: the size class and budget, the three fixed questions
(framing first, class, storage), where each answer lands in the brief, and
the answers that decide nothing. Step 3a and the form points of Step 3c move
into the skill with their credits (Pocock, Osmani, Spec Kit; licences and
line ranges checked at the pinned commits).

Red baseline first (3 helper interviews against a fixed answer sheet,
Opus 5.5): 10-11 questions in round 1 (3 of 3), 15 of 31 without a
recommendation, a hollow answer written in as a decision (2 of 3), unasked
scope as a requirement (2 of 3). With the skill: 4, 0 of 12, 0 of 3, 0 of 3.
Fact questions and stopping did not fail without it.

Also: pointers to voyage:writing-criteria (S3) where criteria are asked and
written, both review skill names (S3 + S4) in the brief-reviewer prompt; the
intent pins that read moved text now read the skill, same assertions; the
Phase 7 line_ref moves with the shorter Phase 3; 7 eval cases (3/2/2).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-17 07:44:42 +02:00

2 KiB
Raw Permalink Blame History

description expected_outcome tags runs max_turns timeout_seconds allowed_tools
Effect case for interviewing (two arms: with and without the plugin). The write-up after a round where several answers decided nothing. Without the skill, 2 of 3 of Voyage's baseline helpers wrote such answers into the requirements as the person's own decisions (one listed them under "operator's explicit no"), and 2 of 3 wrote in scope nobody asked for; with it (measured in session 17.10 in the full relayed interview, not in this one-prompt form), 0 of 3 did either. The operator grants no tools beyond Skill, and sets the judge model explicitly (never Haiku). The requirements keep three things apart: what the person decided, what was assumed for an answer that decided nothing (each marked not confirmed), and what is deferred; nothing the person never asked for appears as a requirement.
skill-effect
skill=interviewing
from=baseline-ivw-hollow-answer
3 6 300
Skill

You are interviewing me about a feature for our garden club's seed-library app: members forget to bring seeds back after harvest. You already asked one round of questions, and here are my answers. Write the requirements now, as a list I can approve.

Your questions and my answers:

  1. Q: How should reminders reach members? (Recommended: the printed meeting sheet the app already writes to.) A: Yes, go with your suggestion.
  2. Q: When should reminders go out? (Recommended: once a week for every loan overdue or due within two weeks.) A: Once a week, overdue or due within two weeks. Never the same reminder twice in one week.
  3. Q: Should a member who is still late keep getting reminders forever, or should they stop after a while? A: Whatever you think is best.
  4. Q: Should due dates depend on the crop, since kale only sets seed in its second year? A: Whatever you think is best.
  5. Q: What should happen when a member's harvest failed? A: Sounds good.
  6. Q: Any consequence for late members, such as blocking new loans? A: No fines and no blocking anyone. Just a friendly nudge.