voyage/evals/skill-debugging-quiet-2/prompt.md
Kjell Tore Guttormsen cc832fd430
feat(skills): skill workshop, test-first and debugging preloaded into the step helper
The workshop (ordre 7a, contracts S1 and S2): a form check
(lib/skills/skill-lint.mjs) that follows Claude Code's own skill fields,
and a model-free routing test (lib/skills/routing.mjs) over every skill,
the 7 commands and the 21 spawnable agents, reading the eval cases
themselves (evals/skill-*, 3 fire / 2 quiet / 1 effect, tagged with the
event they came from). Thresholds pinned, never lowered.

The two skills were written against failures measured first in helpers
without them: red only as an import crash, the whole suite run from a
hand-made file list instead of the repo's own command, and an
unreproduced fix shipped under authority pressure. step-implementer
preloads both through its skills: line; no tool list change.

Credits: addyosmani/agent-skills @9d0c60d, obra/superpowers @8ca22db,
mattpocock/skills @c55ee46 (MIT), Anthropic skill-creator (Apache-2.0).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:38:58 +02:00

419 B

description expected_outcome tags runs max_turns allowed_tools
Routing case: the debugging skill must stay quiet here; /trekcontinue owns this request. Claude never calls the Skill tool for voyage:debugging.
skill-no-trigger
skill=debugging
owner=trekcontinue
from=skillsanalyse-4.2
3 4
Read
Glob
Grep
Skill

Resume the next session of this multi-session project where the last one stopped.