open/voyage
1
0
Fork 0
Code Issues Releases 13 Activity
voyage/evals
History
Kjell Tore Guttormsen 837e92545d
 feat(skills): writing-criteria, one source for runnable criteria (order 7c) 
A brief success criterion and a plan's Verify, Regression, End-to-end and
Verification lines are each one command the criteria runner accepts, written
as the line's first backticked span; anything more is bash tests/<name>.sh,
and each must be able to go red (the runner reads the exit code only).

- skills/writing-criteria/SKILL.md (S1 form), with Runs:/Refused:/Never red:
  examples that a pin runs through the criteria runner
- brief-reviewer and plan-critic preload writing-criteria and
  reviewing-adversarially (S3 + S4); the copied runner rules leave them, the
  two templates and /trekplan, which names the skill where the plan is written
  and where its three reviewers start
- eval cases 3 fire / 2 quiet / 1 effect; tests/lib/skills-criteria-prose-pins
- review-630 @~1 pin follows the text into the skill; trekplan-stats line_ref
  re-measured

Baseline without the skill: 24 of 27 written checks refused by the runner,
and 0 of 3 reviewers saw that git status/git log can never go red. With it:
0 of 27 refused, 3 of 3 reviewers flagged both.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-17 07:39:04 +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-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
skill-writing-criteria-effect feat(skills): writing-criteria, one source for runnable criteria (order 7c) 2026-10-17 07:39:04 +02:00
skill-writing-criteria-fires-1 feat(skills): writing-criteria, one source for runnable criteria (order 7c) 2026-10-17 07:39:04 +02:00
skill-writing-criteria-fires-2 feat(skills): writing-criteria, one source for runnable criteria (order 7c) 2026-10-17 07:39:04 +02:00
skill-writing-criteria-fires-3 feat(skills): writing-criteria, one source for runnable criteria (order 7c) 2026-10-17 07:39:04 +02:00
skill-writing-criteria-quiet-1 feat(skills): writing-criteria, one source for runnable criteria (order 7c) 2026-10-17 07:39:04 +02:00
skill-writing-criteria-quiet-2 feat(skills): writing-criteria, one source for runnable criteria (order 7c) 2026-10-17 07:39:04 +02:00