mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-08 23:36:06 +02:00
feat: interactive /plan-devex-review + plan mode skill fix (v0.15.5.0) (#796)
* fix: skill invocation during plan mode takes precedence over generic plan mode Adds a "Skill Invocation During Plan Mode" section to the preamble resolver so all generated SKILL.md files include it. Fixes a bug where Claude treats loaded skill content as reference material instead of executable instructions, and keeps trying to ExitPlanMode instead of following the skill workflow step by step. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: interactive /plan-devex-review with persona, benchmarks, and forcing questions Complete rewrite of the DX review skill to match CEO/eng review depth. New flow: investigate (persona, empathy, competitors, magical moment, journey tracing) then force decisions, then score with evidence. Three modes: DX EXPANSION, DX POLISH, DX TRIAGE. 20-45 interactive STOP points vs 10-12 before. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: autoplan DX POLISH mode + review log schema for new devex fields Adds mode selection, persona, competitive, and magical moment override rules to autoplan Phase 3.5. Documents new review log fields (mode, persona, competitive_tier) in the plan-file-review-report schema. Syncs package.json version to VERSION. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: update project documentation for v0.15.5.0 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.6
parent
3f080de1b7
commit
447851452a
@@ -541,7 +541,10 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
|
||||
Log: "Phase 3.5 skipped — no developer-facing scope detected."
|
||||
|
||||
**Override rules:**
|
||||
- Focus areas: all relevant DX dimensions (P1)
|
||||
- Mode selection: DX POLISH
|
||||
- Persona: infer from README/docs, pick the most common developer type (P6)
|
||||
- Competitive benchmark: run searches if WebSearch available, use reference benchmarks otherwise (P1)
|
||||
- Magical moment: pick the lowest-effort delivery vehicle that achieves the competitive tier (P5)
|
||||
- Getting started friction: always optimize toward fewer steps (P5, simpler over clever)
|
||||
- Error message quality: always require problem + cause + fix (P1, completeness)
|
||||
- API/CLI naming: consistency wins over cleverness (P5)
|
||||
|
||||
Reference in New Issue
Block a user