@cubis/foundry 0.3.31 → 0.3.32

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/game-developer.md

@@ -3,7 +3,7 @@ name: game-developer
 description: Game development across all platforms (PC, Web, Mobile, VR/AR). Use when building games with Unity, Godot, Unreal, Phaser, Three.js, or any game engine. Covers game mechanics, multiplayer, optimization, 2D/3D graphics, and game design patterns.
 tools: Read, Write, Edit, Bash, Grep, Glob
 model: inherit
-skills: clean-code, game-development, javascript-pro, typescript-pro, ui-ux-pro-max, web-perf, test-master
+skills: game-development, javascript-pro, typescript-pro, ui-ux-pro-max
 ---
 
 # Game Developer Agent

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/mobile-developer.md

@@ -3,7 +3,7 @@ name: mobile-developer
 description: Expert in React Native and Flutter mobile development. Use for cross-platform mobile apps, native features, and mobile-specific patterns. Triggers on mobile, react native, flutter, ios, android, app store, expo.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: clean-code, mobile-design, flutter-expert, riverpod-3, gorouter-restoration, drift-flutter, database-skills, flutter-test-master, accessibility, test-master
+skills: mobile-design, flutter-expert, riverpod-3, gorouter-restoration, drift-flutter, flutter-test-master, accessibility
 ---
 
 # Mobile Developer

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/orchestrator.md

@@ -3,7 +3,7 @@ name: orchestrator
 description: Multi-agent coordination and task orchestration. Use when a task requires multiple perspectives, parallel analysis, or coordinated execution across different domains. Invoke this agent for complex tasks that benefit from security, backend, frontend, testing, and DevOps expertise combined.
 tools: Read, Grep, Glob, Bash, Write, Edit, Agent
 model: inherit
-skills: clean-code, parallel-agents, behavioral-modes, plan-writing, brainstorming, architecture, lint-and-validate, powershell-windows, bash-linux, sub-agents, feature-forge, architecture-designer, test-master, security-reviewer, devops-engineer
+skills: parallel-agents, plan-writing, architecture-designer, feature-forge, sub-agents, security-reviewer, devops-engineer
 ---
 
 # Orchestrator - Native Multi-Agent Coordination

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/penetration-tester.md

@@ -3,7 +3,7 @@ name: penetration-tester
 description: Expert in offensive security, penetration testing, red team operations, and vulnerability exploitation. Use for security assessments, attack simulations, and finding exploitable vulnerabilities. Triggers on pentest, exploit, attack, hack, breach, pwn, redteam, offensive.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: clean-code, vulnerability-scanner, red-team-tactics, api-patterns, security-reviewer, semgrep, static-analysis, variant-analysis, secure-code-guardian, sarif-parsing, test-master
+skills: security-reviewer, semgrep, static-analysis, variant-analysis, red-team-tactics, sarif-parsing
 ---
 
 # Penetration Tester

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/performance-optimizer.md

@@ -3,7 +3,7 @@ name: performance-optimizer
 description: Expert in performance optimization, profiling, Core Web Vitals, and bundle optimization. Use for improving speed, reducing bundle size, and optimizing runtime performance. Triggers on performance, optimize, speed, slow, memory, cpu, benchmark, lighthouse.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: clean-code, performance-profiling, web-perf, monitoring-expert, database-design, database-optimizer, database-skills, react-best-practices, test-master
+skills: performance-profiling, web-perf, monitoring-expert, database-optimizer, react-best-practices
 ---
 
 # Performance Optimizer

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/product-manager.md

@@ -3,7 +3,7 @@ name: product-manager
 description: Expert in product requirements, user stories, and acceptance criteria. Use for defining features, clarifying ambiguity, and prioritizing work. Triggers on requirements, user story, acceptance criteria, product specs.
 tools: Read, Grep, Glob, Bash
 model: inherit
-skills: plan-writing, brainstorming, clean-code, feature-forge, architecture-designer, prompt-engineer, code-documenter
+skills: feature-forge, plan-writing, architecture-designer, prompt-engineer, code-documenter
 ---
 
 # Product Manager

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/product-owner.md

@@ -3,7 +3,7 @@ name: product-owner
 description: Strategic facilitator bridging business needs and technical execution. Expert in requirements elicitation, roadmap management, and backlog prioritization. Triggers on requirements, user story, backlog, MVP, PRD, stakeholder.
 tools: Read, Grep, Glob, Bash
 model: inherit
-skills: plan-writing, brainstorming, clean-code, feature-forge, architecture-designer, changelog-generator, spec-miner
+skills: feature-forge, plan-writing, architecture-designer, changelog-generator, spec-miner
 ---
 
 # Product Owner

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/project-planner.md

@@ -3,7 +3,7 @@ name: project-planner
 description: Smart project planning agent. Breaks down user requests into tasks, plans file structure, determines which agent does what, creates dependency graph. Use when starting new projects or planning major features.
 tools: Read, Grep, Glob, Bash
 model: inherit
-skills: clean-code, app-builder, plan-writing, brainstorming, feature-forge, architecture-designer, api-designer, test-master, devops-engineer
+skills: app-builder, plan-writing, feature-forge, architecture-designer, api-designer, devops-engineer, test-master
 ---
 
 # Project Planner - Smart Project Planning

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/qa-automation-engineer.md

@@ -3,7 +3,7 @@ name: qa-automation-engineer
 description: Specialist in test automation infrastructure and E2E testing. Focuses on Playwright, Cypress, CI pipelines, and breaking the system. Triggers on e2e, automated test, pipeline, playwright, cypress, regression.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: webapp-testing, testing-patterns, web-design-guidelines, clean-code, lint-and-validate, playwright-expert, test-master, code-reviewer, monitoring-expert
+skills: playwright-expert, webapp-testing, test-master, lint-and-validate, monitoring-expert, code-reviewer
 ---
 
 # QA Automation Engineer

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/security-auditor.md

@@ -3,7 +3,7 @@ name: security-auditor
 description: Elite cybersecurity expert. Think like an attacker, defend like an expert. OWASP 2025, supply chain security, zero trust architecture. Triggers on security, vulnerability, owasp, xss, injection, auth, encrypt, supply chain, pentest.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: clean-code, vulnerability-scanner, red-team-tactics, api-patterns, security-reviewer, semgrep, static-analysis, secure-code-guardian, sarif-parsing, variant-analysis, test-master
+skills: security-reviewer, semgrep, static-analysis, variant-analysis, secure-code-guardian, sarif-parsing
 ---
 
 # Security Auditor

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/seo-specialist.md

@@ -3,7 +3,7 @@ name: seo-specialist
 description: SEO and GEO (Generative Engine Optimization) expert. Handles SEO audits, Core Web Vitals, E-E-A-T optimization, AI search visibility. Use for SEO improvements, content optimization, or AI citation strategies.
 tools: Read, Grep, Glob, Bash, Write
 model: inherit
-skills: clean-code, seo-fundamentals, geo-fundamentals, web-perf, code-documenter, nextjs-developer, react-expert, ui-ux-pro-max
+skills: seo-fundamentals, geo-fundamentals, web-perf, nextjs-developer, code-documenter
 ---
 
 # SEO Specialist

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/test-engineer.md

@@ -3,7 +3,7 @@ name: test-engineer
 description: Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: clean-code, testing-patterns, tdd-workflow, webapp-testing, code-review-checklist, lint-and-validate, test-master, playwright-expert, flutter-test-master, code-reviewer
+skills: test-master, playwright-expert, flutter-test-master, webapp-testing, lint-and-validate, code-reviewer
 ---
 
 # Test Engineer

package/workflows/workflows/agent-environment-setup/platforms/antigravity/agents/vercel-expert.md

@@ -3,7 +3,7 @@ name: vercel-expert
 description: Expert in Vercel platform delivery, runtime behavior, security controls, observability, and automation. Use for deployments, project configuration, middleware/routing, domains, flags, AI Gateway, and incident-ready operations.
 tools: Read, Grep, Glob, Bash, Edit, Write
 model: inherit
-skills: vercel-platform, vercel-functions, vercel-routing, vercel-caching, vercel-observability, vercel-deployments, vercel-domains, vercel-cli, vercel-ai-gateway, vercel-ai-sdk, vercel-flags, vercel-firewall, vercel-storage, nextjs-developer, devops-engineer, monitoring-expert, secure-code-guardian, web-perf
+skills: vercel-platform, vercel-runtime, vercel-delivery, vercel-security, vercel-ai, vercel-storage, nextjs-developer, devops-engineer, monitoring-expert, secure-code-guardian
 ---
 
 # Vercel Expert

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/backend.toml

@@ -0,0 +1,11 @@
+description = "Drive backend architecture and implementation via backend specialist with API, data, and reliability focus."
+prompt = '''
+Follow the /backend workflow from .agent/workflows/backend.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/brainstorm.toml

@@ -0,0 +1,11 @@
+description = "Generate concrete solution options and tradeoffs before committing to implementation."
+prompt = '''
+Follow the /brainstorm workflow from .agent/workflows/brainstorm.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/create.toml

@@ -0,0 +1,11 @@
+description = "Implement feature work with minimal blast radius and clear verification checkpoints."
+prompt = '''
+Follow the /create workflow from .agent/workflows/create.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/database.toml

@@ -0,0 +1,11 @@
+description = "Design or review schema, queries, and migrations with performance and integrity controls."
+prompt = '''
+Follow the /database workflow from .agent/workflows/database.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/debug.toml

@@ -0,0 +1,11 @@
+description = "Isolate root cause quickly and apply the smallest safe remediation with verification."
+prompt = '''
+Follow the /debug workflow from .agent/workflows/debug.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/devops.toml

@@ -0,0 +1,11 @@
+description = "Plan and execute deployment, CI/CD, and operational safety changes with rollback controls."
+prompt = '''
+Follow the /devops workflow from .agent/workflows/devops.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/implement-track.toml

@@ -0,0 +1,11 @@
+description = "Execute large work in milestones with explicit quality gates and status updates."
+prompt = '''
+Follow the /implement-track workflow from .agent/workflows/implement-track.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/incident.toml

@@ -0,0 +1,11 @@
+description = "Handle production incidents with triage, mitigation, root cause, and post-incident actions."
+prompt = '''
+Follow the /incident workflow from .agent/workflows/incident.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/mobile.toml

@@ -0,0 +1,11 @@
+description = "Drive mobile implementation decisions for Flutter/cross-platform behavior and reliability."
+prompt = '''
+Follow the /mobile workflow from .agent/workflows/mobile.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/orchestrate.toml

@@ -0,0 +1,11 @@
+description = "Coordinate multiple specialists to solve cross-cutting tasks with explicit ownership and handoff."
+prompt = '''
+Follow the /orchestrate workflow from .agent/workflows/orchestrate.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/plan.toml

@@ -0,0 +1,11 @@
+description = "Build a decision-complete implementation plan with interfaces, failure modes, and acceptance criteria."
+prompt = '''
+Follow the /plan workflow from .agent/workflows/plan.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/qa.toml

@@ -0,0 +1,11 @@
+description = "Create and execute quality strategy with automation and regression-focused coverage."
+prompt = '''
+Follow the /qa workflow from .agent/workflows/qa.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/refactor.toml

@@ -0,0 +1,11 @@
+description = "Improve maintainability while preserving behavior through incremental safe refactoring."
+prompt = '''
+Follow the /refactor workflow from .agent/workflows/refactor.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/release.toml

@@ -0,0 +1,11 @@
+description = "Prepare and execute release with rollout guardrails, verification, and rollback plan."
+prompt = '''
+Follow the /release workflow from .agent/workflows/release.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/review.toml

@@ -0,0 +1,11 @@
+description = "Run a strict review for bugs, regressions, and security issues with prioritized findings."
+prompt = '''
+Follow the /review workflow from .agent/workflows/review.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/security.toml

@@ -0,0 +1,11 @@
+description = "Run security-focused analysis and remediation planning with exploitability-first triage."
+prompt = '''
+Follow the /security workflow from .agent/workflows/security.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/test.toml

@@ -0,0 +1,11 @@
+description = "Design and execute verification strategy aligned to risk and acceptance criteria."
+prompt = '''
+Follow the /test workflow from .agent/workflows/test.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/commands/vercel.toml

@@ -0,0 +1,11 @@
+description = "Drive Vercel implementation and operations via vercel-expert with deployment, runtime, security, and observability guardrails."
+prompt = '''
+Follow the /vercel workflow from .agent/workflows/vercel.md.
+
+Execution contract:
+1. Confirm the request fits the workflow's "When to use" section.
+2. Execute according to "Workflow steps" and apply "Context notes".
+3. Complete "Verification" checks and report concrete evidence.
+
+If command arguments are provided, treat them as additional user context.
+'''

package/workflows/workflows/agent-environment-setup/platforms/antigravity/rules/GEMINI.md

@@ -11,6 +11,7 @@ This file defines mandatory behavior for Antigravity projects installed via `cbx
 - Workflows: `.agent/workflows`
 - Agents: `.agent/agents`
 - Skills: `.agent/skills`
+- Gemini commands: `.gemini/commands`
 - Rules file: `.agent/rules/GEMINI.md`
 
 ## Startup Transparency (Required)
@@ -27,8 +28,8 @@ Keep this user-visible summary concise and factual; do not expose private chain-
 
 ## 2) Workflow-First Contract
 
-1. If the user explicitly requests a slash command, run that workflow first.
-2. Otherwise choose the best workflow by intent from `.agent/workflows`.
+1. If the user explicitly requests a slash command, run that command/workflow first.
+2. Otherwise choose the best workflow by intent from `.agent/workflows` and use matching `.gemini/commands/*.toml` when available.
 3. For cross-domain tasks, use orchestrated delegation with `@orchestrator`.
 4. Keep one primary workflow; use others only as supporting references.
 
@@ -39,6 +40,19 @@ Keep this user-visible summary concise and factual; do not expose private chain-
 3. Simple code changes: minimal edits with focused verification.
 4. Complex code/design changes: plan first, then implement and verify.
 
+## 3A) Workflow Pattern Map (Antigravity)
+
+Map intent to one primary workflow first:
+
+- Explain codebase -> `/plan`
+- Fix bug -> `/debug`
+- Write test -> `/test` or `/qa`
+- Prototype from screenshot -> `/create` + `@frontend-specialist`
+- Iterate UI updates -> `/create` with verification loop
+- Refactor safely -> `/refactor` (or `@code-archaeologist` if scope is narrow)
+- Local code review -> `/review`
+- Documentation update -> `/create` + `@documentation-writer`
+
 ## 4) Agent Routing Policy
 
 Use the best specialist first:

package/workflows/workflows/agent-environment-setup/platforms/antigravity/workflows/backend.md

@@ -1,21 +1,37 @@
 ---
 command: "/backend"
-description: "Route backend-focused tasks to the backend specialist with API, data, and reliability focus."
+description: "Drive backend architecture and implementation via backend specialist with API, data, and reliability focus."
 triggers: ["backend", "api", "service", "database", "performance"]
 ---
 # Backend Workflow
 
-Use this workflow when backend architecture or implementation is primary.
+## When to use
+Use this when backend architecture or service logic is primary.
 
 ## Routing
 - Primary specialist: `@backend-specialist`
+- Add `@database-architect` for schema/query changes.
+- Add `@security-auditor` when auth, secrets, or sensitive data are involved.
 
-## Steps
-1. Ask `@backend-specialist` for solution outline.
-2. Validate API contracts, data model, and failure handling.
-3. Implement backend changes with tests and observability.
+## Context notes
+- This workflow file, active platform rules, and selected agents/skills guide execution.
+- Attach logs, screenshots, failing output, and relevant paths when context is incomplete.
+
+## Skill Routing
+- Primary skills: `nodejs-best-practices`, `api-designer`
+- Supporting skills (optional): `api-patterns`, `database-skills`, `secure-code-guardian`
+
+## Workflow steps
+1. Ask specialist(s) for design and risk assessment.
+2. Validate contracts, data model, and failure handling.
+3. Implement backend changes with observability.
 4. Always update API docs: OpenAPI spec, Swagger UI route, and Stoplight Elements route/component.
-5. Return summary including migration and rollout notes.
+5. Run targeted tests and summarize rollout notes.
+
+## Verification
+- Run focused checks/tests for the changed scope.
+- Confirm no regressions in adjacent behavior.
+- Note any gaps that were not validated.
 
 ## Output Contract
 - API/contract changes

package/workflows/workflows/agent-environment-setup/platforms/antigravity/workflows/brainstorm.md

@@ -1,14 +1,34 @@
 ---
 command: "/brainstorm"
-description: "Generate options, tradeoffs, and architecture ideas before implementation."
-triggers: ["idea", "explore", "tradeoff", "approach", "brainstorm"]
+description: "Generate concrete solution options and tradeoffs before committing to implementation."
+triggers: ["idea", "brainstorm", "options", "tradeoff", "approach"]
 ---
 # Brainstorm Workflow
 
-Use this workflow when requirements are open-ended and multiple solution paths are possible.
+## When to use
+Use this when requirements are still fluid and architecture choices are open.
 
-## Steps
-1. Clarify goals, constraints, and non-goals.
-2. Produce 2-4 implementation options.
-3. Compare complexity, risk, and maintainability.
-4. Recommend one option and explain why.
+## Context notes
+- This workflow file, active platform rules, and selected agents/skills guide execution.
+- Attach logs, screenshots, failing output, and relevant paths when context is incomplete.
+
+## Skill Routing
+- Primary skills: `brainstorming`, `feature-forge`
+- Supporting skills (optional): `plan-writing`
+
+## Workflow steps
+1. Restate problem, constraints, and success metrics.
+2. Produce 2-4 options with architecture shape.
+3. Compare complexity, risk, and implementation speed.
+4. Recommend one option and justify rejection of others.
+
+## Verification
+- Run focused checks/tests for the changed scope.
+- Confirm no regressions in adjacent behavior.
+- Note any gaps that were not validated.
+
+## Output Contract
+- Option table (pros/cons)
+- Recommended option
+- Known unknowns
+- First implementation milestone

package/workflows/workflows/agent-environment-setup/platforms/antigravity/workflows/create.md

@@ -1,14 +1,34 @@
 ---
 command: "/create"
-description: "Implement new feature code with clear boundaries and minimal regression risk."
-triggers: ["implement", "build", "create", "feature", "code"]
+description: "Implement feature work with minimal blast radius and clear verification checkpoints."
+triggers: ["create", "build", "implement", "feature", "develop"]
 ---
 # Create Workflow
 
-Use this workflow for net-new implementation work.
+## When to use
+Use this for net-new implementation after design is stable.
 
-## Steps
-1. Identify target files and expected behavior.
-2. Implement minimal viable change.
-3. Validate with tests/checks.
-4. Summarize behavior and follow-up actions.
+## Context notes
+- This workflow file, active platform rules, and selected agents/skills guide execution.
+- Attach logs, screenshots, failing output, and relevant paths when context is incomplete.
+
+## Skill Routing
+- Primary skills: `feature-forge`, `architecture-designer`
+- Supporting skills (optional): `lint-and-validate`, `test-master`
+
+## Workflow steps
+1. Confirm target files and contracts.
+2. Implement smallest coherent increment.
+3. Validate behavior with focused tests.
+4. Capture remaining gaps and follow-ups.
+
+## Verification
+- Run focused checks/tests for the changed scope.
+- Confirm no regressions in adjacent behavior.
+- Note any gaps that were not validated.
+
+## Output Contract
+- Changed components/files
+- Behavioral impact
+- Test evidence
+- Follow-up items

package/workflows/workflows/agent-environment-setup/platforms/antigravity/workflows/database.md

@@ -5,6 +5,7 @@ triggers: ["database", "sql", "schema", "migration", "index"]
 ---
 # Database Workflow
 
+## When to use
 Use this when data modeling, query quality, migration safety, or database performance is core to the task.
 
 ## Routing
@@ -17,7 +18,15 @@ Use this when data modeling, query quality, migration safety, or database perfor
 - Power bridge: `workflows/powers/database-skills`
 - Engine wrappers: `postgres`, `mysql`, `vitess`, `neki`, `mongodb`, `sqlite`, `supabase`, `redis`
 
-## Steps
+## Context notes
+- This workflow file, active platform rules, and selected agents/skills guide execution.
+- Attach logs, screenshots, failing output, and relevant paths when context is incomplete.
+
+## Skill Routing
+- Primary skills: `database-skills`, `database-design`
+- Supporting skills (optional): `database-optimizer`
+
+## Workflow steps
 1. Confirm data shape, access patterns, and workload size.
 2. Choose track: `database-design` (schema/migrations), `database-optimizer` (tuning), or `database-skills` (engine wrappers).
 3. Choose engine wrapper and define index strategy.
@@ -25,6 +34,11 @@ Use this when data modeling, query quality, migration safety, or database perfor
 5. Plan migration and rollback.
 6. Validate with query-plan evidence and production-risk notes.
 
+## Verification
+- Run focused checks/tests for the changed scope.
+- Confirm no regressions in adjacent behavior.
+- Note any gaps that were not validated.
+
 ## Output Contract
 - Schema/query changes
 - Indexing plan

package/workflows/workflows/agent-environment-setup/platforms/antigravity/workflows/debug.md

@@ -1,14 +1,34 @@
 ---
 command: "/debug"
-description: "Investigate failures, isolate root cause, and propose the smallest safe fix."
-triggers: ["bug", "error", "stack trace", "investigate", "debug"]
+description: "Isolate root cause quickly and apply the smallest safe remediation with verification."
+triggers: ["debug", "bug", "error", "incident", "stack trace"]
 ---
 # Debug Workflow
 
-Use this workflow when behavior is broken or uncertain.
+## When to use
+Use this when behavior is failing or inconsistent.
 
-## Steps
-1. Reproduce the issue reliably.
-2. Narrow fault domain and inspect evidence.
-3. Identify root cause and impact radius.
-4. Implement and validate focused remediation.
+## Context notes
+- This workflow file, active platform rules, and selected agents/skills guide execution.
+- Attach logs, screenshots, failing output, and relevant paths when context is incomplete.
+
+## Skill Routing
+- Primary skills: `systematic-debugging`, `find-bugs`
+- Supporting skills (optional): `monitoring-expert`, `error-ux-observability`
+
+## Workflow steps
+1. Reproduce issue and collect evidence.
+2. Narrow fault domain and identify root cause.
+3. Apply focused fix with low regression risk.
+4. Verify resolution and monitor for recurrence.
+
+## Verification
+- Run focused checks/tests for the changed scope.
+- Confirm no regressions in adjacent behavior.
+- Note any gaps that were not validated.
+
+## Output Contract
+- Reproduction notes
+- Root cause summary
+- Fix summary
+- Regression checks performed