gstack/.agents/skills
Garry Tan ae2d841012
feat: adversarial spec review loop + skill chaining (v0.9.1.0) (#249)
* feat: add {{SPEC_REVIEW_LOOP}}, {{DESIGN_SKETCH}}, benefits-from resolvers

Three new resolvers in gen-skill-docs.ts:

- {{SPEC_REVIEW_LOOP}}: adversarial subagent reviews documents on 5
  dimensions (completeness, consistency, clarity, scope, feasibility)
  with convergence guard, quality score, and JSONL metrics
- {{DESIGN_SKETCH}}: generates rough HTML wireframes for UI ideas using
  DESIGN.md constraints and design principles, renders via $B
- {{BENEFITS_FROM}}: parses benefits-from frontmatter and generates
  skill chaining offer prose (one-hop-max, never blocks)

Also extends TemplateContext with benefitsFrom field and adds inline
YAML frontmatter parsing for the new field.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: /office-hours spec review loop + visual sketch phases

- Phase 4.5 ({{DESIGN_SKETCH}}): for UI ideas, generates rough HTML
  wireframe using design principles from {{DESIGN_METHODOLOGY}} and
  DESIGN.md, renders via $B, presents screenshot for iteration
- Phase 5.5 ({{SPEC_REVIEW_LOOP}}): adversarial subagent reviews the
  design doc before user sees it — catches gaps in completeness,
  consistency, clarity, scope, and feasibility
- Adds {{BROWSE_SETUP}} for $B availability in sketch phase

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: skill chaining — plan reviews offer /office-hours

- plan-ceo-review: benefits-from office-hours, offers /office-hours when
  no design doc found, mid-session detection when user seems lost,
  spec review loop on CEO plan documents
- plan-eng-review: benefits-from office-hours, offers /office-hours when
  no design doc found
- One-hop-max chaining: never blocks, max one offer per session

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test: add validation + E2E tests for spec review, sketch, benefits-from

Unit tests (32 new assertions):
- SPEC_REVIEW_LOOP: 5 dimensions, Agent dispatch, 3 iterations, quality
  score, metrics path, convergence guard, graceful failure
- DESIGN_SKETCH: DESIGN.md awareness, wireframe, $B goto/screenshot,
  rough aesthetic, skip conditions
- BENEFITS_FROM: prerequisite offer in CEO + eng review, graceful
  decline, skills without benefits-from don't get offer
- office-hours structure: spec review loop, adversarial dimensions,
  visual sketch section

E2E tests (2 new):
- office-hours-spec-review: verifies agent understands the spec review
  loop from SKILL.md
- plan-ceo-review-benefits: verifies agent understands the skill
  chaining offer

Touchfiles updated for diff-based test selection.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.9.1.0)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-20 06:24:22 -07:00
..
gstack fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-browse fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-careful feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00
gstack-design-consultation fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-design-review fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-document-release fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-freeze feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00
gstack-guard feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00
gstack-investigate fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-office-hours feat: adversarial spec review loop + skill chaining (v0.9.1.0) (#249) 2026-03-20 06:24:22 -07:00
gstack-plan-ceo-review feat: adversarial spec review loop + skill chaining (v0.9.1.0) (#249) 2026-03-20 06:24:22 -07:00
gstack-plan-design-review fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-plan-eng-review feat: adversarial spec review loop + skill chaining (v0.9.1.0) (#249) 2026-03-20 06:24:22 -07:00
gstack-qa fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-qa-only fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-retro fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-review fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-setup-browser-cookies fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-ship fix: plan mode exception for review log + telemetry writes (v0.9.0.1) (#234) 2026-03-19 23:10:26 -07:00
gstack-unfreeze feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00
gstack-upgrade feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00