gstack/scripts/resolvers/preamble
Garry Tan 752865f866
feat: Conductor renders AskUserQuestion decisions as prose by default
In Conductor, native AskUserQuestion is disabled and the MCP variant is
flaky, so skills now render every decision as a plain-text prose brief the
user answers by typing a letter — proactively, not as a failure reaction.

- Preamble emits CONDUCTOR_SESSION, gated on != headless so eval/CI inside
  Conductor still BLOCKs instead of rendering prose to nobody.
- AskUserQuestion Format gains a Conductor-default-prose rule (auto-decide
  preferences still apply first; prose decisions log via gstack-question-log
  since PostToolUse never fires), a one-way/destructive typed-confirmation
  rule, and a typed-reply continuation protocol for split chains.
- Regenerated all SKILL.md + ship golden fixtures; bumped affected carve
  skeleton caps to absorb the always-loaded additions.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-11 20:15:29 -07:00
..
generate-ask-user-format.ts feat: Conductor renders AskUserQuestion decisions as prose by default 2026-06-11 20:15:29 -07:00
generate-brain-health-instruction.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
generate-brain-sync-block.ts v1.29.0.0 feat: worktree-aware gbrain code sources via path-hash IDs and CWD pin (#1382) 2026-05-08 12:46:15 -07:00
generate-completeness-section.ts v1.57.4.0 refactor(ethos): rename Boil the Lake principle to Boil the Ocean (#1912) 2026-06-08 05:41:07 -07:00
generate-completion-status.ts v1.57.2.0 feat: AskUserQuestion prose fallback when the tool fails at runtime (#1908) 2026-06-07 21:38:21 -07:00
generate-confusion-protocol.ts v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712) 2026-05-26 16:50:03 -07:00
generate-context-health.ts v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712) 2026-05-26 16:50:03 -07:00
generate-context-recovery.ts v1.57.5.0 feat: cross-session decision memory + gbrain dream-stage call graph (#1910) 2026-06-08 06:20:58 -07:00
generate-continuous-checkpoint.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
generate-lake-intro.ts v1.57.4.0 refactor(ethos): rename Boil the Lake principle to Boil the Ocean (#1912) 2026-06-08 05:41:07 -07:00
generate-preamble-bash.ts feat: Conductor renders AskUserQuestion decisions as prose by default 2026-06-11 20:15:29 -07:00
generate-proactive-prompt.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
generate-repo-mode-section.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
generate-routing-injection.ts v1.47.0.0 feat: /spec — author backlog-ready spec in 5 phases + optional agent spawn (#1698) (#1733) 2026-05-26 21:36:53 -07:00
generate-search-before-building.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
generate-spawned-session-check.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
generate-telemetry-prompt.ts v1.55.1.0 fix: telemetry consent accuracy + gstack-slug cache sanitization (#1848) 2026-06-02 22:36:34 -07:00
generate-test-failure-triage.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
generate-upgrade-check.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
generate-vendoring-deprecation.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
generate-voice-directive.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
generate-writing-style-migration.ts v1.15.0.0 feat: slim preamble + real-PTY plan-mode E2E harness (#1215) 2026-04-26 13:55:13 -07:00
generate-writing-style.ts v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712) 2026-05-26 16:50:03 -07:00