gsd-antigravity-kit 2.0.0 → 2.1.0

package/.agent/skills/gsd/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gsd
-version: 1.34.2
+version: 1.37.1
 description: "Antigravity GSD (Get Stuff Done) - A spec-driven hierarchical planning and execution system. Triggers on project planning, phase management, and GSD slash commands."
 ---
 
@@ -25,6 +25,7 @@ This skill should be used when:
 - `gsd:add-phase`
 - `gsd:add-tests`
 - `gsd:add-todo`
+- `gsd:ai-integration-phase`
 - `gsd:analyze-dependencies`
 - `gsd:audit-fix`
 - `gsd:audit-milestone`
@@ -39,14 +40,19 @@ This skill should be used when:
 - `gsd:discuss-phase`
 - `gsd:do`
 - `gsd:docs-update`
+- `gsd:eval-review`
 - `gsd:execute-phase`
 - `gsd:explore`
+- `gsd:extract_learnings`
 - `gsd:fast`
 - `gsd:forensics`
+- `gsd:from-gsd2`
+- `gsd:graphify`
 - `gsd:gsd-tools`
 - `gsd:health`
 - `gsd:help`
 - `gsd:import`
+- `gsd:inbox`
 - `gsd:insert-phase`
 - `gsd:intel`
 - `gsd:join-discord`
@@ -81,6 +87,11 @@ This skill should be used when:
 - `gsd:set-profile`
 - `gsd:settings`
 - `gsd:ship`
+- `gsd:sketch`
+- `gsd:sketch-wrap-up`
+- `gsd:spec-phase`
+- `gsd:spike`
+- `gsd:spike-wrap-up`
 - `gsd:stats`
 - `gsd:thread`
 - `gsd:ui-phase`
@@ -128,16 +139,27 @@ The following slash commands are available in this skill. Use them to drive the
 - **[`gsd:review-backlog`](references/commands/milestone/review-backlog.md)**: Review and promote backlog items to active milestone
 
 ### Misc Commands
+- **[`gsd:ai-integration-phase`](references/commands/misc/ai-integration-phase.md)**: Generate AI design contract (AI-SPEC.md) for phases that involve building AI systems — framework selection, implementation guidance from official docs, and evaluation strategy
 - **[`gsd:audit-fix`](references/commands/misc/audit-fix.md)**: Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
 - **[`gsd:audit-uat`](references/commands/misc/audit-uat.md)**: Cross-phase audit of all outstanding UAT and verification items
+- **[`gsd:eval-review`](references/commands/misc/eval-review.md)**: Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
+- **[`gsd:extract_learnings`](references/commands/misc/extract_learnings.md)**: Extract decisions, lessons, patterns, and surprises from completed phase artifacts
+- **[`gsd:from-gsd2`](references/commands/misc/from-gsd2.md)**: Import a GSD-2 (.gsd/) project back to GSD v1 (.planning/) format
+- **[`gsd:graphify`](references/commands/misc/graphify.md)**: Build, query, and inspect the project knowledge graph in .planning/graphs/
+- **[`gsd:inbox`](references/commands/misc/inbox.md)**: Triage and review all open GitHub issues and PRs against project templates and contribution guidelines
 - **[`gsd:next`](references/commands/misc/next.md)**: Automatically advance to the next logical step in the GSD workflow
-- **[`gsd:progress`](references/commands/misc/progress.md)**: Check project progress, show context, and route to next action (execute or plan)
+- **[`gsd:progress`](references/commands/misc/progress.md)**: Check project progress, show context, and route to next action (execute or plan). Use --forensic to append a 6-check integrity audit after the standard report.
+- **[`gsd:sketch-wrap-up`](references/commands/misc/sketch-wrap-up.md)**: Package sketch design findings into a persistent project skill for future build conversations
+- **[`gsd:sketch`](references/commands/misc/sketch.md)**: Rapidly sketch UI/design ideas using throwaway HTML mockups with multi-variant exploration
+- **[`gsd:spec-phase`](references/commands/misc/spec-phase.md)**: Socratic spec refinement — clarify WHAT a phase delivers with ambiguity scoring before discuss-phase. Produces a SPEC.md with falsifiable requirements locked before implementation decisions begin.
+- **[`gsd:spike-wrap-up`](references/commands/misc/spike-wrap-up.md)**: Package spike findings into a persistent project skill for future build conversations
+- **[`gsd:spike`](references/commands/misc/spike.md)**: Rapidly spike an idea with throwaway experiments to validate feasibility before planning
 - **[`gsd:verify-work`](references/commands/misc/verify-work.md)**: Validate built features through conversational UAT
 
 ### Phase Commands
 - **[`gsd:add-phase`](references/commands/phase/add-phase.md)**: Add phase to end of current milestone in roadmap
 - **[`gsd:add-tests`](references/commands/phase/add-tests.md)**: Generate tests for a completed phase based on UAT criteria and implementation
-- **[`gsd:discuss-phase`](references/commands/phase/discuss-phase.md)**: Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Antigravity picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).
+- **[`gsd:discuss-phase`](references/commands/phase/discuss-phase.md)**: Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. Use --auto to skip interactive questions (Antigravity picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).
 - **[`gsd:execute-phase`](references/commands/phase/execute-phase.md)**: Execute all plans in a phase with wave-based parallelization
 - **[`gsd:insert-phase`](references/commands/phase/insert-phase.md)**: Insert urgent work as decimal phase (e.g., 72.1) between existing phases
 - **[`gsd:list-phase-assumptions`](references/commands/phase/list-phase-assumptions.md)**: Surface Antigravity's assumptions about a phase approach before planning
@@ -218,4 +240,4 @@ General documentation on the GSD philosophy, usage patterns, and configuration.
 5.  **CLI Invocation**: `gsd-tools` is **NOT** a global command. Always invoke it with the full node path: `node .agent/skills/gsd/bin/gsd-tools.cjs <command> [args]`. Never run `gsd-tools` bare.
 
 ---
-*Generated by gsd-converter on 2026-04-08*
+*Generated by gsd-converter on 2026-04-18*

package/.agent/skills/gsd/VERSION

@@ -1 +1 @@
-1.34.2
+1.37.1

package/.agent/skills/gsd/assets/templates/AI-SPEC.md

@@ -0,0 +1,246 @@
+# AI-SPEC — Phase {N}: {phase_name}
+
+> AI design contract generated by `/gsd-ai-integration-phase`. Consumed by `gsd-planner` and `gsd-eval-auditor`.
+> Locks framework selection, implementation guidance, and evaluation strategy before planning begins.
+
+---
+
+## 1. System Classification
+
+**System Type:** <!-- RAG | Multi-Agent | Conversational | Extraction | Autonomous Agent | Content Generation | Code Automation | Hybrid -->
+
+**Description:**
+<!-- One-paragraph description of what this AI system does, who uses it, and what "good" looks like -->
+
+**Critical Failure Modes:**
+<!-- The 3-5 behaviors that absolutely cannot go wrong in this system -->
+1.
+2.
+3.
+
+---
+
+## 1b. Domain Context
+
+> Researched by `gsd-domain-researcher`. Grounds the evaluation strategy in domain expert knowledge.
+
+**Industry Vertical:** <!-- healthcare | legal | finance | customer service | education | developer tooling | e-commerce | etc. -->
+
+**User Population:** <!-- who uses this system and in what context -->
+
+**Stakes Level:** <!-- Low | Medium | High | Critical -->
+
+**Output Consequence:** <!-- what happens downstream when the AI output is acted on -->
+
+### What Domain Experts Evaluate Against
+
+<!-- Domain-specific rubric ingredients — in practitioner language, not AI jargon -->
+<!-- Format: Dimension / Good (expert accepts) / Bad (expert flags) / Stakes / Source -->
+
+### Known Failure Modes in This Domain
+
+<!-- Domain-specific failure modes from research — not generic hallucination, but how it manifests here -->
+
+### Regulatory / Compliance Context
+
+<!-- Relevant regulations or constraints — or "None identified" if genuinely none apply -->
+
+### Domain Expert Roles for Evaluation
+
+| Role | Responsibility |
+|------|---------------|
+| <!-- e.g., Senior practitioner --> | <!-- Dataset labeling / rubric calibration / production sampling --> |
+
+---
+
+## 2. Framework Decision
+
+**Selected Framework:** <!-- e.g., LlamaIndex v0.10.x -->
+
+**Version:** <!-- Pin the version -->
+
+**Rationale:**
+<!-- Why this framework fits this system type, team context, and production requirements -->
+
+**Alternatives Considered:**
+
+| Framework | Ruled Out Because |
+|-----------|------------------|
+| | |
+
+**Vendor Lock-In Accepted:** <!-- Yes / No / Partial — document the trade-off consciously -->
+
+---
+
+## 3. Framework Quick Reference
+
+> Fetched from official docs by `gsd-ai-researcher`. Distilled for this specific use case.
+
+### Installation
+```bash
+# Install command(s)
+```
+
+### Core Imports
+```python
+# Key imports for this use case
+```
+
+### Entry Point Pattern
+```python
+# Minimal working example for this system type
+```
+
+### Key Abstractions
+<!-- Framework-specific concepts the developer must understand before coding -->
+| Concept | What It Is | When You Use It |
+|---------|-----------|-----------------|
+| | | |
+
+### Common Pitfalls
+<!-- Gotchas specific to this framework and system type — from docs, issues, and community reports -->
+1.
+2.
+3.
+
+### Recommended Project Structure
+```
+project/
+├── # Framework-specific folder layout
+```
+
+---
+
+## 4. Implementation Guidance
+
+**Model Configuration:**
+<!-- Which model(s), temperature, max tokens, and other key parameters -->
+
+**Core Pattern:**
+<!-- The primary implementation pattern for this system type in this framework -->
+
+**Tool Use:**
+<!-- Tools/integrations needed and how to configure them -->
+
+**State Management:**
+<!-- How state is persisted, retrieved, and updated -->
+
+**Context Window Strategy:**
+<!-- How to manage context limits for this system type -->
+
+---
+
+## 4b. AI Systems Best Practices
+
+> Written by `gsd-ai-researcher`. Cross-cutting patterns every developer building AI systems needs — independent of framework choice.
+
+### Structured Outputs with Pydantic
+
+<!-- Framework-specific Pydantic integration pattern for this use case -->
+<!-- Include: output model definition, how the framework uses it, retry logic on validation failure -->
+
+```python
+# Pydantic output model for this system type
+```
+
+### Async-First Design
+
+<!-- How async is handled in this framework, the one common mistake, and when to stream vs. await -->
+
+### Prompt Engineering Discipline
+
+<!-- System vs. user prompt separation, few-shot guidance, token budget strategy -->
+
+### Context Window Management
+
+<!-- Strategy specific to this system type: RAG chunking / conversation summarisation / agent compaction -->
+
+### Cost and Latency Budget
+
+<!-- Per-call cost estimate, caching strategy, sub-task model routing -->
+
+---
+
+## 5. Evaluation Strategy
+
+### Dimensions
+
+| Dimension | Rubric (Pass/Fail or 1-5) | Measurement Approach | Priority |
+|-----------|--------------------------|---------------------|----------|
+| | | Code / LLM Judge / Human | Critical / High / Medium |
+
+### Eval Tooling
+
+**Primary Tool:** <!-- e.g., RAGAS + Langfuse -->
+
+**Setup:**
+```bash
+# Install and configure
+```
+
+**CI/CD Integration:**
+```bash
+# Command to run evals in CI/CD pipeline
+```
+
+### Reference Dataset
+
+**Size:** <!-- e.g., 20 examples to start -->
+
+**Composition:**
+<!-- What scenario types the dataset covers: critical paths, edge cases, failure modes -->
+
+**Labeling:**
+<!-- Who labels examples and how (domain expert, LLM judge with calibration, etc.) -->
+
+---
+
+## 6. Guardrails
+
+### Online (Real-Time)
+
+| Guardrail | Trigger | Intervention |
+|-----------|---------|--------------|
+| | | Block / Escalate / Flag |
+
+### Offline (Flywheel)
+
+| Metric | Sampling Strategy | Action on Degradation |
+|--------|------------------|----------------------|
+| | | |
+
+---
+
+## 7. Production Monitoring
+
+**Tracing Tool:** <!-- e.g., Langfuse self-hosted -->
+
+**Key Metrics to Track:**
+<!-- 3-5 metrics that will be monitored in production -->
+
+**Alert Thresholds:**
+<!-- When to page/alert -->
+
+**Smart Sampling Strategy:**
+<!-- How to select interactions for human review — signal-based filters -->
+
+---
+
+## Checklist
+
+- [ ] System type classified
+- [ ] Critical failure modes identified (≥ 3)
+- [ ] Domain context researched (Section 1b: vertical, stakes, expert criteria, failure modes)
+- [ ] Regulatory/compliance context identified or explicitly noted as none
+- [ ] Domain expert roles defined for evaluation involvement
+- [ ] Framework selected with rationale documented
+- [ ] Alternatives considered and ruled out
+- [ ] Framework quick reference written (install, imports, pattern, pitfalls)
+- [ ] AI systems best practices written (Section 4b: Pydantic, async, prompt discipline, context)
+- [ ] Evaluation dimensions grounded in domain rubric ingredients
+- [ ] Each eval dimension has a concrete rubric (Good/Bad in domain language)
+- [ ] Eval tooling selected — Arize Phoenix default confirmed or override noted
+- [ ] Reference dataset spec written (size ≥ 10, composition + labeling defined)
+- [ ] CI/CD eval integration specified
+- [ ] Online guardrails defined
+- [ ] Production monitoring configured (tracing tool + sampling strategy)

package/.agent/skills/gsd/assets/templates/DEBUG.md

@@ -20,7 +20,9 @@ updated: [ISO timestamp]
 hypothesis: [current theory being tested]
 test: [how testing it]
 expecting: [what result means if true/false]
-next_action: [immediate next step]
+next_action: [immediate next step — be specific, not "continue investigating"]
+reasoning_checkpoint: null  <!-- populated before every fix attempt — see structured_returns -->
+tdd_checkpoint: null  <!-- populated when tdd_mode is active after root cause confirmed -->
 
 ## Symptoms
 <!-- Written during gathering, then immutable -->
@@ -69,7 +71,10 @@ files_changed: []
 - OVERWRITE entirely on each update
 - Always reflects what Antigravity is doing RIGHT NOW
 - If Antigravity reads this after /clear, it knows exactly where to resume
-- Fields: hypothesis, test, expecting, next_action
+- Fields: hypothesis, test, expecting, next_action, reasoning_checkpoint, tdd_checkpoint
+- `next_action`: must be concrete and actionable — bad: "continue investigating"; good: "Add logging at line 47 of auth.js to observe token value before jwt.verify()"
+- `reasoning_checkpoint`: OVERWRITE before every fix_and_verify — five-field structured reasoning record (hypothesis, confirming_evidence, falsification_test, fix_rationale, blind_spots)
+- `tdd_checkpoint`: OVERWRITE during TDD red/green phases — test file, name, status, failure output
 
 **Symptoms:**
 - Written during initial gathering phase

package/.agent/skills/gsd/assets/templates/config.json

@@ -1,48 +1,56 @@
-{
-  "mode": "interactive",
-  "granularity": "standard",
-  "workflow": {
-    "research": true,
-    "plan_check": true,
-    "verifier": true,
-    "auto_advance": false,
-    "nyquist_validation": true,
-    "security_enforcement": true,
-    "security_asvs_level": 1,
-    "security_block_on": "high",
-    "discuss_mode": "discuss",
-    "research_before_questions": false
-  },
-  "planning": {
-    "commit_docs": true,
-    "search_gitignored": false,
-    "sub_repos": []
-  },
-  "parallelization": {
-    "enabled": true,
-    "plan_level": true,
-    "task_level": false,
-    "skip_checkpoints": true,
-    "max_concurrent_agents": 3,
-    "min_plans_for_parallel": 2
-  },
-  "gates": {
-    "confirm_project": true,
-    "confirm_phases": true,
-    "confirm_roadmap": true,
-    "confirm_breakdown": true,
-    "confirm_plan": true,
-    "execute_next_plan": true,
-    "issues_review": true,
-    "confirm_transition": true
-  },
-  "safety": {
-    "always_confirm_destructive": true,
-    "always_confirm_external_services": true
-  },
-  "hooks": {
-    "context_warnings": true
-  },
-  "project_code": null,
-  "agent_skills": {}
-}
+{
+  "mode": "interactive",
+  "granularity": "standard",
+  "workflow": {
+    "research": true,
+    "plan_check": true,
+    "verifier": true,
+    "auto_advance": false,
+    "nyquist_validation": true,
+    "security_enforcement": true,
+    "security_asvs_level": 1,
+    "security_block_on": "high",
+    "discuss_mode": "discuss",
+    "research_before_questions": false,
+    "code_review_command": null,
+    "plan_bounce": false,
+    "plan_bounce_script": null,
+    "plan_bounce_passes": 2,
+    "cross_ai_execution": false,
+    "cross_ai_command": "",
+    "cross_ai_timeout": 300
+  },
+  "planning": {
+    "commit_docs": true,
+    "search_gitignored": false,
+    "sub_repos": []
+  },
+  "parallelization": {
+    "enabled": true,
+    "plan_level": true,
+    "task_level": false,
+    "skip_checkpoints": true,
+    "max_concurrent_agents": 3,
+    "min_plans_for_parallel": 2
+  },
+  "gates": {
+    "confirm_project": true,
+    "confirm_phases": true,
+    "confirm_roadmap": true,
+    "confirm_breakdown": true,
+    "confirm_plan": true,
+    "execute_next_plan": true,
+    "issues_review": true,
+    "confirm_transition": true
+  },
+  "safety": {
+    "always_confirm_destructive": true,
+    "always_confirm_external_services": true
+  },
+  "hooks": {
+    "context_warnings": true
+  },
+  "project_code": null,
+  "agent_skills": {},
+  "antigravity_md_path": "./ANTIGRAVITY.md"
+}

package/.agent/skills/gsd/assets/templates/research.md

@@ -38,6 +38,18 @@ Template for `.planning/phases/XX-name/{phase_num}-RESEARCH.md` - comprehensive
 **If no CONTEXT.md exists:** Write "No user constraints - all decisions at Antigravity's discretion"
 </user_constraints>
 
+<architectural_responsibility_map>
+## Architectural Responsibility Map
+
+Map each phase capability to its standard architectural tier owner before diving into framework research. This prevents tier misassignment from propagating into plans.
+
+| Capability | Primary Tier | Secondary Tier | Rationale |
+|------------|-------------|----------------|-----------|
+| [capability from phase description] | [Browser/Client, Frontend Server, API/Backend, CDN/Static, or Database/Storage] | [secondary tier or —] | [why this tier owns it] |
+
+**If single-tier application:** Write "Single-tier application — all capabilities reside in [tier]" and omit the table.
+</architectural_responsibility_map>
+
 <research_summary>
 ## Summary
 
@@ -82,6 +94,20 @@ yarn add [packages]
 <architecture_patterns>
 ## Architecture Patterns
 
+### System Architecture Diagram
+
+Architecture diagrams MUST show data flow through conceptual components, not file listings.
+
+Requirements:
+- Show entry points (how data/requests enter the system)
+- Show processing stages (what transformations happen, in what order)
+- Show decision points and branching paths
+- Show external dependencies and service boundaries
+- Use arrows to indicate data flow direction
+- A reader should be able to trace the primary use case from input to output by following the arrows
+
+File-to-implementation mapping belongs in the Component Responsibilities table, not in the diagram.
+
 ### Recommended Project Structure
 ```
 src/
@@ -300,6 +326,20 @@ npm install three @react-three/fiber @react-three/drei @react-three/rapier zusta
 <architecture_patterns>
 ## Architecture Patterns
 
+### System Architecture Diagram
+
+Architecture diagrams MUST show data flow through conceptual components, not file listings.
+
+Requirements:
+- Show entry points (how data/requests enter the system)
+- Show processing stages (what transformations happen, in what order)
+- Show decision points and branching paths
+- Show external dependencies and service boundaries
+- Use arrows to indicate data flow direction
+- A reader should be able to trace the primary use case from input to output by following the arrows
+
+File-to-implementation mapping belongs in the Component Responsibilities table, not in the diagram.
+
 ### Recommended Project Structure
 ```
 src/