@cubis/foundry 0.3.82 → 0.3.83

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

@@ -1,68 +0,0 @@
----
-command: "/create"
-description: "Implement feature work with minimal blast radius and clear verification checkpoints."
-triggers: ["create", "build", "implement", "feature", "develop"]
----
-
-# Create Workflow
-
-## When to use
-
-Use this for net-new implementation after design is stable.
-
-## Routing
-
-- Primary coordinator: `the orchestrator posture`
-- Backend implementation: `the backend-specialist posture`
-- Frontend implementation: `the frontend-specialist posture`
-- Mobile implementation: `the mobile-developer posture`
-- Verification support: `the test-engineer posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach logs, screenshots, failing output, and relevant paths when context is incomplete.
-- Read `ENGINEERING_RULES.md` first and `TECH.md` next for non-trivial work so new code follows the declared architecture and design-system rules.
-
-## Skill Routing
-
-- Primary skills: `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`, `golang-best-practices`, `java-best-practices`, `csharp-best-practices`, `kotlin-best-practices`, `rust-best-practices`, `php-best-practices`, `php-best-practices`, `rust-best-practices`, `rust-best-practices`, `expo-app`, `swift-best-practices`
-- Supporting skills (optional): `api-design`, `api-design`, `javascript-best-practices`, `nestjs`, `fastapi`, `api-design`, `drizzle-orm`, `database-design`, `mcp-server-builder`, `stitch`, `react`, `react`, `nextjs`, `frontend-design`, `frontend-design`, `frontend-design`, `performance-testing`, `skill-creator`, `stripe-integration`, `ci-cd-pipeline`, `frontend-design`
-- Pick one primary language skill from repo signals or touched files. Add the narrowest specialist only when the feature is clearly backend or frontend framework-specific.
-- If the request references Stitch screens, artifacts, design-to-code, or UI sync, add `stitch` first and route the implementation through the frontend or mobile specialist based on the destination surface.
-
-## Workflow steps
-
-1. Confirm target files and contracts.
-2. Implement smallest coherent increment.
-3. Validate behavior with focused tests.
-4. Capture `doc_impact` when the feature changes architecture, boundaries, scale, or design-system rules.
-5. 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
-
-```yaml
-CREATE_WORKFLOW_RESULT:
-  primary_agent: orchestrator
-  supporting_agents: [backend-specialist?, frontend-specialist?, mobile-developer?, test-engineer?]
-  primary_skills: [<dominant-language-skill>]
-  supporting_skills: [stitch?, <framework-specific-skills-used>]
-  implemented_scope:
-    summary: <string>
-    changed_artifacts: [<path-or-artifact>]
-  behavioral_impact: [<string>]
-  doc_impact: none | tech | rules | both
-  verification:
-    checks_run: [<command-or-test>]
-    evidence: [<string>]
-    gaps: [<string>] | []
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

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

@@ -1,67 +0,0 @@
----
-command: "/database"
-description: "Design or review schema, queries, and migrations with performance and integrity controls."
-triggers: ["database", "sql", "schema", "migration", "index"]
----
-
-# Database Workflow
-
-## When to use
-
-Use this for schema design, query optimization, migration planning, or database architecture decisions.
-
-## Routing
-
-- Primary specialist: `the database-architect posture`
-- Implementation support: `the backend-specialist posture`
-- Verification support: `the test-engineer posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach existing schema, migration history, query patterns, and performance requirements.
-- Read `ENGINEERING_RULES.md` and `TECH.md` before changing data ownership, persistence boundaries, or shared schema conventions.
-
-## Skill Routing
-
-- Primary skills: `database-design`, `database-design`, `database-design`
-- Supporting skills (optional): `drizzle-orm`, `database-design`, `database-design`, `database-design`, `database-design`, `database-design`, `database-design`, `database-design`, `database-design`, `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`
-- Start with `database-design` for schema work, `database-design` for performance, or `database-design` for general database operations. Add engine-specific skill when applicable.
-
-## Workflow steps
-
-1. Understand current schema and data model.
-2. Design or review proposed changes with normalization analysis.
-3. Plan migration with rollback strategy.
-4. Optimize queries and indexes for known access patterns.
-5. Validate data integrity constraints.
-6. Set `doc_impact` if the change alters data boundaries, core entities, or persistence patterns that future work should follow.
-
-## Verification
-
-- Schema changes maintain referential integrity.
-- Migrations are reversible or have documented rollback plan.
-- EXPLAIN output reviewed for performance-sensitive queries.
-- No breaking changes to existing consumers without migration plan.
-
-## Output Contract
-
-```yaml
-DATABASE_WORKFLOW_RESULT:
-  primary_agent: database-architect
-  supporting_agents: [backend-specialist?, test-engineer?]
-  primary_skills: [database-design, database-design, database-design]
-  supporting_skills: [<engine-specific-skill>?, drizzle-orm?]
-  schema_changes:
-    tables_affected: [<string>]
-    migration_plan: <string>
-    rollback_plan: <string>
-  query_optimization:
-    queries_reviewed: <number>
-    indexes_recommended: [<string>] | []
-  doc_impact: none | tech | rules | both
-  integrity_checks: [<string>]
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

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

@@ -1,63 +0,0 @@
----
-command: "/debug"
-description: "Isolate root cause quickly, apply the smallest safe remediation, and leave behind regression evidence."
-triggers: ["debug", "bug", "error", "incident", "stack trace"]
----
-
-# Debug Workflow
-
-## When to use
-
-Use this when behavior is failing, inconsistent, flaky, or only reproducible under certain conditions.
-
-## Routing
-
-- Primary specialist: `the debugger posture`
-- Domain implementation support: `the backend-specialist posture`, `the frontend-specialist posture`
-- Verification support: `the test-engineer posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach stack traces, request IDs, traces, repro steps, recent diffs, and environment notes when context is incomplete.
-
-## Skill Routing
-
-- Primary skills: `systematic-debugging`, `observability`
-- Supporting skills (optional): `unit-testing`, `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`, `golang-best-practices`, `java-best-practices`, `csharp-best-practices`, `kotlin-best-practices`, `rust-best-practices`, `integration-testing`, `playwright-interactive`, `skill-creator`
-- Start with `systematic-debugging` for reproduce, isolate, instrument, and verify flow. Add `observability` when the failure involves error states, logging, or tracing gaps. Add the dominant language skill for exact code-path analysis, `integration-testing` or `playwright-interactive` when the failure lives in browser or release verification.
-
-## Workflow steps
-
-1. Reproduce the issue and record expected versus actual behavior.
-2. Narrow the fault domain with the smallest useful evidence.
-3. Fix the confirmed cause with the lowest regression risk.
-4. Add or update the regression proof.
-5. Document any remaining uncertainty or environment-specific gaps.
-
-## Verification
-
-- Re-run the failing scenario first.
-- Run focused regression checks on adjacent high-risk paths.
-- Call out any remaining gaps if the full environment could not be reproduced.
-
-## Output Contract
-
-```yaml
-DEBUG_WORKFLOW_RESULT:
-  primary_agent: debugger
-  supporting_agents: [backend-specialist?, frontend-specialist?, test-engineer?]
-  primary_skills: [systematic-debugging, observability]
-  supporting_skills: [unit-testing?, <language-skill>?, integration-testing?, playwright-interactive?]
-  reproduction:
-    steps: [<string>]
-    expected_vs_actual: <string>
-  root_cause: <string>
-  remediation:
-    summary: <string>
-    changed_artifacts: [<path-or-artifact>]
-  regression_checks: [<command or test>]
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

package/workflows/workflows/agent-environment-setup/platforms/gemini/workflows/devops.md

@@ -1,78 +0,0 @@
----
-command: "/devops"
-description: "Plan and execute deployment, CI/CD, incident response, and operational safety changes with rollback controls."
-triggers:
-  [
-    "devops",
-    "deploy",
-    "ci",
-    "cd",
-    "rollback",
-    "infra",
-    "incident",
-    "outage",
-    "sev",
-    "degraded",
-    "hotfix",
-    "recovery",
-  ]
----
-
-# DevOps Workflow
-
-## When to use
-
-Use this for deployment automation, CI/CD pipeline changes, incident response, or infrastructure operations.
-
-## Routing
-
-- Primary specialist: `the ci-cd-pipeline posture`
-- Reliability support: `the observability posture`
-- Verification support: `the validator posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach deployment targets, pipeline configs, incident details, and infrastructure specs.
-
-## Skill Routing
-
-- Primary skills: `ci-cd-pipeline`, `ci-cd-pipeline`, `kubernetes-deploy`
-- Supporting skills (optional): `observability`, `observability`, `ci-cd-pipeline`, `git-workflow`, `systematic-debugging`, `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`, `golang-best-practices`
-- Start with `ci-cd-pipeline` for operational patterns. Add `ci-cd-pipeline` for pipeline work, `kubernetes-deploy` for container operations, `observability` for incident response, `ci-cd-pipeline` for serverless infrastructure.
-
-## Workflow steps
-
-1. Assess current state and change scope.
-2. Plan change with rollback strategy.
-3. Apply change in staged manner (dev → staging → production).
-4. Verify health at each stage before proceeding.
-5. Document operational procedures and runbooks.
-
-## Verification
-
-- Change applied successfully with no service degradation.
-- Rollback procedure verified or documented.
-- Monitoring confirms normal operation after change.
-- Runbook updated for new procedures.
-
-## Output Contract
-
-```yaml
-DEVOPS_WORKFLOW_RESULT:
-  primary_agent: ci-cd-pipeline
-  supporting_agents: [observability?, validator?]
-  primary_skills: [ci-cd-pipeline, ci-cd-pipeline, kubernetes-deploy]
-  supporting_skills: [observability?, observability?, ci-cd-pipeline?]
-  change:
-    description: <string>
-    blast_radius: <string>
-    rollback_plan: <string>
-  execution:
-    stages_completed: [<string>]
-    health_checks: [<string>]
-  operational_docs: [<string>] | []
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

package/workflows/workflows/agent-environment-setup/platforms/gemini/workflows/implement-track.md

@@ -1,71 +0,0 @@
----
-command: "/implement-track"
-description: "Execute large work in milestones with explicit quality gates and status updates."
-triggers: ["track", "milestone", "delivery", "progress", "execution"]
----
-
-# Implement Track Workflow
-
-## When to use
-
-Use this for large-scale implementation work that spans multiple sessions or milestones and needs progress tracking with quality gates.
-
-## Routing
-
-- Primary coordinator: `the orchestrator posture`
-- Implementation agents: determined by task domain
-- Quality gate: `the validator posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach the implementation plan, milestone definitions, and acceptance criteria per milestone.
-- Reuse `docs/specs/<spec-id>/` when present instead of maintaining a separate progress source of truth.
-- Read `ENGINEERING_RULES.md` first and `docs/foundation/TECH.md` next before starting milestone execution. Use `## Build And Validation` for the validated build sequence and `## Key Commands` for test/lint commands.
-
-## Skill Routing
-
-- Primary skills: `system-design`, `api-design`
-- Supporting skills (optional): `database-design`, `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`, `golang-best-practices`, `react`, `nextjs`
-- Start with `system-design` for milestone planning. Load domain-specific skills per milestone based on implementation needs.
-
-## Workflow steps
-
-1. Review implementation plan and confirm milestone boundaries.
-2. Execute current milestone with focused implementation.
-3. Run quality gate validation at milestone completion.
-4. Update progress tracking and capture status.
-5. Adjust remaining plan, spec traceability, and doc refresh needs based on learnings.
-6. Proceed to next milestone or report completion.
-
-## Verification
-
-- Each milestone has clear acceptance criteria that are verified.
-- Quality gate passed before proceeding to next milestone.
-- Progress tracker updated with evidence of completion.
-- Remaining milestones adjusted for any scope changes.
-
-## Output Contract
-
-```yaml
-IMPLEMENT_TRACK_WORKFLOW_RESULT:
-  primary_agent: orchestrator
-  supporting_agents: [<milestone-agents>]
-  primary_skills: [system-design, api-design]
-  supporting_skills: [database-design?, typescript-best-practices?, javascript-best-practices?, python-best-practices?, golang-best-practices?, react?, nextjs?]
-  milestones:
-    - id: <milestone-id>
-      description: <string>
-      status: completed | in_progress | pending
-      acceptance_criteria_met: [<string>]
-      validation_evidence: <string>
-  overall_progress: <percentage>
-  scope_changes: [<string>] | []
-  spec_id: <string> | null
-  spec_root: docs/specs/<spec-id> | null
-  traceability_status: complete | partial | blocked
-  doc_impact: none | tech | rules | both
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

package/workflows/workflows/agent-environment-setup/platforms/gemini/workflows/migrate.md

@@ -1,78 +0,0 @@
----
-command: "/migrate"
-description: "Plan and execute technology migrations, framework upgrades, and dependency updates with rollback safety, incremental verification, and zero-downtime transition."
-triggers:
-  [
-    "migrate",
-    "upgrade",
-    "update dependency",
-    "framework upgrade",
-    "version bump",
-    "major update",
-  ]
----
-
-# Migrate Workflow
-
-## When to use
-
-Use this for technology migrations, framework upgrades, dependency updates, or major version transitions.
-
-## Routing
-
-- Primary specialist: `the code-archaeologist posture`
-- Implementation support: `the backend-specialist posture`, `the frontend-specialist posture`
-- Verification support: `the test-engineer posture`, `the validator posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach the migration target, current versions, breaking change lists, and impact assessment.
-- Read `ENGINEERING_RULES.md` and `docs/foundation/TECH.md` first because migrations often change accepted patterns and current-state architecture at the same time. After migration, flag updates needed in `docs/foundation/ARCHITECTURE.md` for `## Risks And Tech Debt`.
-
-## Skill Routing
-
-- Primary skills: `system-design`, `system-design`
-- Supporting skills (optional): `code-review`, `unit-testing`, `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`, `golang-best-practices`
-- Start with `system-design` for migration methodology and `system-design` for system impact. Add `code-review` for automated codemod or compatibility analysis.
-
-## Workflow steps
-
-1. Assess current state and migration target.
-2. Map breaking changes and affected code paths.
-3. Plan incremental migration steps with rollback points.
-4. Execute migration one step at a time with verification.
-5. Update tests and documentation for new patterns.
-6. Set `doc_impact` when the migration changes architecture, deployment shape, boundaries, or design-system rules.
-7. Verify full system behavior after migration complete.
-
-## Verification
-
-- All breaking changes addressed.
-- Tests pass on migrated code.
-- Rollback tested at each migration step.
-- No degradation in performance or functionality.
-- Documentation updated for new patterns.
-
-## Output Contract
-
-```yaml
-MIGRATE_WORKFLOW_RESULT:
-  primary_agent: code-archaeologist
-  supporting_agents: [backend-specialist?, frontend-specialist?, test-engineer?, validator?]
-  primary_skills: [system-design, system-design]
-  supporting_skills: [code-review?, unit-testing?]
-  migration:
-    from: <string>
-    to: <string>
-    breaking_changes: [<string>]
-    steps_completed: [<string>]
-    rollback_points: [<string>]
-  verification:
-    tests_passed: true | false
-    performance_impact: <string>
-  doc_impact: none | tech | rules | both
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

package/workflows/workflows/agent-environment-setup/platforms/gemini/workflows/mobile.md

@@ -1,71 +0,0 @@
----
-command: "/mobile"
-description: "Drive mobile implementation decisions for Flutter/cross-platform behavior and reliability."
-triggers: ["mobile", "flutter", "ios", "android", "navigation"]
----
-
-# Mobile Workflow
-
-## When to use
-
-Use this for mobile app development, Flutter architecture, Stitch-driven mobile screen handoff, native integrations, or platform-specific behavior.
-
-## Routing
-
-- Primary specialist: `the mobile-developer posture`
-- Design support: `the frontend-specialist posture`
-- Verification support: `the test-engineer posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach platform targets (iOS, Android, both), Flutter version, and relevant screen/feature context.
-- Read `ENGINEERING_RULES.md` and `docs/foundation/TECH.md` before implementing non-trivial mobile work so screens and features follow the declared architecture and design-system rules. Check `docs/foundation/PRODUCT.md` for `## Domain Glossary` to use consistent terminology.
-
-## Skill Routing
-
-- Primary skills: `expo-app`, `react-native`
-- Supporting skills (optional): `stitch`, `frontend-design`, `expo-app`, `expo-app`, `expo-app`, `expo-app`, `expo-app`, `expo-app`, `expo-app`, `expo-app`, `expo-app`, `swift-best-practices`, `kotlin-best-practices`
-- Start with `expo-app` for feature implementation and `react-native` for UX patterns. Add framework-specific Flutter skill when applicable. Add `frontend-design` for multi-language support.
-- When the request starts from Stitch artifacts or a design sync, load `stitch` first and then pair it with `react-native` plus the narrowest mobile implementation skill for the target stack.
-
-## Workflow steps
-
-1. Clarify platform targets and feature requirements.
-2. Design architecture with platform-appropriate patterns.
-3. Implement with consideration for iOS/Android differences.
-4. Write widget and integration tests.
-5. Review for platform-specific edge cases and UX conventions.
-6. Set `doc_impact` if the feature changes navigation, shared UI rules, or mobile architecture conventions.
-
-## Verification
-
-- Runs correctly on both target platforms.
-- Platform-specific conventions respected (iOS/Android).
-- Touch targets and gesture feedback appropriate.
-- Widget tests cover core behavior.
-- Offline behavior tested if applicable.
-
-## Output Contract
-
-```yaml
-MOBILE_WORKFLOW_RESULT:
-  primary_agent: mobile-developer
-  supporting_agents: [frontend-specialist?, test-engineer?]
-  primary_skills: [expo-app, react-native]
-  supporting_skills: [stitch?, frontend-design?, expo-app?, expo-app?, <flutter-specific>?]
-  implementation:
-    platforms: [ios, android]
-    architecture_decisions: [<string>]
-    changed_artifacts: [<path>]
-  testing:
-    widget_tests: [<path>]
-    integration_tests: [<path>] | []
-  platform_notes:
-    ios: [<string>] | []
-    android: [<string>] | []
-  doc_impact: none | tech | rules | both
-  follow_up_items: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

package/workflows/workflows/agent-environment-setup/platforms/gemini/workflows/onboard.md

@@ -1,72 +0,0 @@
----
-command: "/onboard"
-description: "Survey an unfamiliar codebase, map its architecture, identify patterns and conventions, and produce a structured orientation report for new contributors."
-triggers:
-  [
-    "onboard",
-    "explore codebase",
-    "understand project",
-    "new to this repo",
-    "codebase survey",
-  ]
----
-
-# Onboard Workflow
-
-## When to use
-
-Use this when joining a new project, exploring an unfamiliar codebase, or preparing orientation material.
-
-## Routing
-
-- Primary specialist: `the researcher posture`
-- Architecture mapping: `the code-archaeologist posture`
-- Domain specialists as needed: `the backend-specialist posture`, `the frontend-specialist posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Provide the repo URL, focus areas, and any specific questions to answer during onboarding.
-- Read `ENGINEERING_RULES.md` first, then `docs/foundation/TECH.md`, `docs/foundation/PRODUCT.md`, and `docs/foundation/ARCHITECTURE.md` when present so onboarding distinguishes the intended contract from current implementation reality. Use the `## Domain Glossary` in PRODUCT.md to learn project-specific terms, and `## Build And Validation` in TECH.md to set up the local environment.
-
-## Skill Routing
-
-- Primary skills: `deep-research`, `system-design`
-- Supporting skills (optional): `system-design`, `database-design`, `typescript-best-practices`, `javascript-best-practices`, `python-best-practices`
-- Start with `deep-research` for systematic exploration and `system-design` for architecture mapping. Add `system-design` for undocumented systems. Prefer repo evidence first; use external sources only when setup or dependency behavior cannot be confirmed locally.
-
-## Workflow steps
-
-1. Survey the project structure — directories, entry points, and configuration.
-2. Map the architecture — components, data flow, and integration points.
-3. Identify patterns — naming conventions, design patterns, and coding standards.
-4. Document dependencies — external services, databases, and APIs.
-5. Produce orientation report with development setup instructions.
-
-## Verification
-
-- All major components identified and documented.
-- Development setup instructions verified (can be followed by a newcomer).
-- Architecture diagram or description covers main data flows.
-- Key patterns and conventions explicitly documented.
-
-## Output Contract
-
-```yaml
-ONBOARD_WORKFLOW_RESULT:
-  primary_agent: researcher
-  supporting_agents: [code-archaeologist?, backend-specialist?, frontend-specialist?]
-  primary_skills: [deep-research, system-design]
-  supporting_skills: [system-design?, database-design?]
-  project_overview:
-    purpose: <string>
-    tech_stack: [<string>]
-    architecture: <string>
-  key_components: [<string>]
-  patterns_and_conventions: [<string>]
-  development_setup: [<step>]
-  dependencies: [<string>]
-  knowledge_gaps: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.

package/workflows/workflows/agent-environment-setup/platforms/gemini/workflows/orchestrate.md

@@ -1,73 +0,0 @@
----
-command: "/orchestrate"
-description: "Coordinate multiple specialists to solve cross-cutting tasks with explicit ownership, validation gates, and repeat-until-good iteration."
-triggers: ["orchestrate", "coordinate", "multi-area", "cross-team", "handoff"]
----
-
-# Orchestrate Workflow
-
-## When to use
-
-Use this when a task spans multiple domains (backend + frontend, security + infrastructure, etc.) and requires coordinated specialist work with validation between steps.
-
-## Routing
-
-- Primary coordinator: `the orchestrator posture`
-- Specialist routing determined by task decomposition — delegates to `the backend-specialist posture`, `the frontend-specialist posture`, `the database-architect posture`, `the security-auditor posture`, `the ci-cd-pipeline posture`, `the test-engineer posture`, `the mobile-developer posture`, or other specialist agents as needed.
-- Validation support: `the validator posture`
-
-## Context notes
-
-- This workflow file, active platform rules, and selected agents or skills guide execution.
-- Attach the full task description, constraints, acceptance criteria, and relevant context when starting.
-- Read `ENGINEERING_RULES.md` and `docs/foundation/TECH.md` before decomposing non-trivial work. Check `docs/foundation/TECH.md` for build/validation commands and `docs/foundation/PRODUCT.md` for domain glossary. Then reuse any existing `docs/specs/<spec-id>/` pack as the handoff source of truth.
-
-## Skill Routing
-
-- Primary skills: `system-design`, `api-design`
-- Supporting skills (optional): `database-design`, `deep-research`, `mcp-server-builder`, `tech-doc`, `prompt-engineering`, `skill-creator`
-- Start with `system-design` for system design coordination and `api-design` for integration contracts. Add `deep-research` before implementation when the coordination challenge depends on fresh external facts or public comparison.
-
-## Workflow steps
-
-1. Decompose the task into discrete work items with acceptance criteria.
-2. Identify dependencies and determine execution order (DAG).
-3. Delegate each task to the best specialist agent with full context.
-4. Validate each deliverable against acceptance criteria via independent validation.
-5. Iterate on failed validations with specific feedback (max 3 iterations).
-6. Surface `doc_impact` when the coordinated work changes architecture, boundaries, scale, or the design system.
-7. Integrate outputs, verify cross-task consistency, and report results.
-
-## Verification
-
-- Each task validated independently against its acceptance criteria.
-- Cross-task consistency check after integration.
-- Run any applicable automated tests or checks.
-- Final validation pass on combined result.
-
-## Output Contract
-
-```yaml
-ORCHESTRATE_WORKFLOW_RESULT:
-  primary_agent: orchestrator
-  supporting_agents: [<specialist-agents-used>]
-  primary_skills: [system-design, api-design]
-  supporting_skills: [<supporting-skills-used>]
-  spec_id: <string> | null
-  spec_root: docs/specs/<spec-id> | null
-  task_count: <number>
-  completed: <number>
-  failed: <number>
-  tasks:
-    - id: <task-id>
-      agent: <agent-name>
-      status: completed | failed | skipped
-      iterations: <number>
-      validation_evidence: <string>
-  integration_status: clean | conflicts_resolved | issues_remaining
-  doc_impact: none | tech | rules | both
-  remaining_risks: [<string>] | []
-  follow_up_actions: [<string>] | []
-```
-
-> **Gemini note:** Commands route into workflow files under `.gemini/workflows/`. Specialists are inline postures coordinated through GEMINI.md guidance, not separate agent artifacts.