voyage/evals
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
..
plan-halts-without-intent-approval test(proevesett): a case for the intent gate; case 5's error comes from code; graders see what they claim 2026-09-23 09:28:38 +02:00
plan-halts-without-phase-signals fix(proevesett): case 4 reads the sequencing gate's own code from the trace 2026-09-23 10:50:48 +02:00
plan-project-not-initialized test(evals): Voyage's fixed test set as a plugin eval suite, expectations written before the first run 2026-09-23 07:52:34 +02:00
plan-rejects-unknown-export test(proevesett): a case for the intent gate; case 5's error comes from code; graders see what they claim 2026-09-23 09:28:38 +02:00
plan-requires-brief test(proevesett): a case for the intent gate; case 5's error comes from code; graders see what they claim 2026-09-23 09:28:38 +02:00
review-requires-project test(proevesett): a case for the intent gate; case 5's error comes from code; graders see what they claim 2026-09-23 09:28:38 +02:00
review-validate-flags-bad-finding-id fix(proevesett): a capitalised opposite verdict refuses the says-* graders 2026-09-23 11:34:29 +02:00
review-validate-passes-clean-review fix(proevesett): a capitalised opposite verdict refuses the says-* graders 2026-09-23 11:34:29 +02:00
skill-debugging-effect feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-debugging-fires-1 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-debugging-fires-2 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-debugging-fires-3 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-debugging-quiet-1 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-debugging-quiet-2 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-interviewing-effect-hollow feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-interviewing-effect-round feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-interviewing-fires-1 feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-interviewing-fires-2 feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-interviewing-fires-3 feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-interviewing-quiet-1 feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-interviewing-quiet-2 feat(skills): interviewing - one source for the brief's question round (order 7e) 2026-10-17 07:44:42 +02:00
skill-researching-sources-effect-injected-page merge: main (7a skills workshop, 9 rettepakke) into wave2-skills-research 2026-10-09 19:34:38 +02:00
skill-researching-sources-hit-advisories merge: main (7a skills workshop, 9 rettepakke) into wave2-skills-research 2026-10-09 19:34:38 +02:00
skill-researching-sources-hit-error-lookup merge: main (7a skills workshop, 9 rettepakke) into wave2-skills-research 2026-10-09 19:34:38 +02:00
skill-researching-sources-hit-official-docs merge: main (7a skills workshop, 9 rettepakke) into wave2-skills-research 2026-10-09 19:34:38 +02:00
skill-researching-sources-miss-local-search merge: main (7a skills workshop, 9 rettepakke) into wave2-skills-research 2026-10-09 19:34:38 +02:00
skill-researching-sources-miss-plan merge: main (7a skills workshop, 9 rettepakke) into wave2-skills-research 2026-10-09 19:34:38 +02:00
skill-test-first-effect feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-test-first-fires-1 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-test-first-fires-2 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-test-first-fires-3 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-test-first-quiet-1 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00
skill-test-first-quiet-2 feat(skills): skill workshop, test-first and debugging preloaded into the step helper 2026-10-08 21:38:58 +02:00