@cubis/foundry 0.3.62 → 0.3.64

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

@@ -5,6 +5,8 @@ triggers: ["mobile", "flutter", "ios", "android", "navigation"]
 ---
 # Mobile Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps mobile flow changes and readiness notes machine-readable.
+
 ## When to use
 Use this when mobile app architecture, UX behavior, or platform constraints are the focus.
 
@@ -33,7 +35,14 @@ Use this when mobile app architecture, UX behavior, or platform constraints are
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Mobile flow changes
-- Platform constraints handled
-- Test coverage summary
-- Release-readiness notes
+```yaml
+MOBILE_WORKFLOW_RESULT:
+  primary_agent: mobile-developer
+  supporting_agents: [frontend-specialist?, test-engineer?]
+  primary_skills: [mobile-design, flutter-expert]
+  supporting_skills: [riverpod-3?, drift-flutter?, flutter-test-master?]
+  flow_changes: [<string>]
+  platform_constraints_handled: [<string>]
+  test_coverage_summary: [<string>]
+  release_readiness_notes: [<string>] | []
+```

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

@@ -5,6 +5,9 @@ triggers: ["orchestrate", "coordinate", "multi-area", "cross-team", "handoff"]
 ---
 # Orchestrate Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps multi-workstream coordination deterministic across regenerated platforms.
+# CHANGED: skill routing — added `skill-authoring` when orchestration spans canonical skill edits, generator updates, and platform parity work.
+
 ## When to use
 Use this when a task spans backend, frontend, data, testing, and release concerns.
 
@@ -30,7 +33,8 @@ Use this when a task spans backend, frontend, data, testing, and release concern
 
 ## Skill Routing
 - Primary skills: `parallel-agents`, `architecture-designer`
-- Supporting skills (optional): `plan-writing`, `feature-forge`
+- Supporting skills (optional): `plan-writing`, `feature-forge`, `skill-authoring`
+- When the workstream includes skill package changes across multiple platforms, load `skill-authoring` as the first supporting skill.
 
 ## Verification
 - Run focused checks/tests for the changed scope.
@@ -38,8 +42,19 @@ Use this when a task spans backend, frontend, data, testing, and release concern
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Scope and assumptions
-- Workstreams with owner + deliverable
-- Consolidated execution order
-- Test and rollout gates
-- Open risks and mitigations
+```yaml
+ORCHESTRATE_WORKFLOW_RESULT:
+  primary_agent: orchestrator
+  supporting_agents: [backend-specialist?, database-architect?, frontend-specialist?, security-auditor?, test-engineer?, devops-engineer?]
+  primary_skills: [parallel-agents, architecture-designer]
+  supporting_skills: [plan-writing?, feature-forge?]
+  scope_and_assumptions: [<string>]
+  workstreams:
+    - owner: <agent-id>
+      deliverable: <string>
+  execution_order: [<string>]
+  gates:
+    test: [<string>]
+    rollout: [<string>]
+  open_risks: [<string>] | []
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/plan.md

@@ -5,16 +5,26 @@ triggers: ["plan", "spec", "design", "roadmap", "acceptance"]
 ---
 # Plan Workflow
 
+# CHANGED: output contract — upgraded to canonical PLAN_HANDOFF schema — lets implementation agents continue task 1→N without re-routing or user restatement.
+# CHANGED: skill routing — added `skill-authoring` as a planning support skill for skill package design and maintenance work.
+
 ## When to use
 Use this when execution needs a stable specification.
 
+## Routing
+- Primary specialist: `@project-planner`
+- Scope clarification: `@product-manager`
+- Architecture review: `@backend-specialist`
+- Verification planning: `@test-engineer`
+
 ## 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: `plan-writing`, `architecture-designer`
-- Supporting skills (optional): `feature-forge`, `api-designer`
+- Supporting skills (optional): `feature-forge`, `api-designer`, `skill-authoring`
+- When the plan itself is for a skill package, prefer `skill-authoring` as the first supporting skill.
 
 ## Workflow steps
 1. Lock scope and non-goals.
@@ -29,7 +39,25 @@ Use this when execution needs a stable specification.
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Implementation phases
-- API/data/interface details
-- Edge cases and risk matrix
-- Verification and rollout checklist
+```yaml
+PLAN_HANDOFF:
+  tasks:
+    - id: 1
+      title: "Describe the first implementation task"
+      domain: "backend"
+      skill_hint: "api-designer"
+      depends_on: []
+      output_artifact: "path-or-artifact"
+      stop_if_failed: true
+  shared_context:
+    stack: "Describe the target stack"
+    constraints: "List hard requirements and guardrails"
+    active_files: ["path-or-artifact"]
+  execution_mode: "sequential"
+  loaded_skills: ["api-designer"]
+  stop_conditions:
+    - "output_artifact missing AND stop_if_failed: true"
+    - "destructive or irreversible action not in plan"
+    - "required skill missing after 1 skill_search attempt"
+    - "explicit user pause or redirect"
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/postman.md

@@ -5,6 +5,8 @@ triggers: ["postman", "collection", "workspace", "environment", "runcollection",
 ---
 # Postman Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps workspace/action identifiers machine-readable for follow-on automation.
+
 ## When to use
 Use this when tasks are primarily about Postman workspaces, collections, environments, monitors, mocks, or collection runs.
 
@@ -34,7 +36,18 @@ Use this when tasks are primarily about Postman workspaces, collections, environ
 - Note any skipped steps and required follow-up.
 
 ## Output Contract
-- Workspace/context used
-- Actions executed and resulting IDs
-- Pass/fail summary for runs
-- Follow-up or remediation steps
+```yaml
+POSTMAN_WORKFLOW_RESULT:
+  primary_agent: backend-specialist
+  supporting_agents: [security-auditor?, test-engineer?]
+  primary_skills: [postman]
+  supporting_skills: [api-designer?, test-master?]
+  workspace_context: <string>
+  actions_executed:
+    - action: <string>
+      result_id: <string|null>
+  run_summary:
+    passed: <bool|null>
+    failures: [<string>] | []
+  follow_up_steps: [<string>] | []
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/qa.md

@@ -5,6 +5,8 @@ triggers: ["qa", "test", "regression", "automation", "e2e"]
 ---
 # QA Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps quality strategy and defect findings machine-readable.
+
 ## When to use
 Use this when verification quality and regression prevention are primary concerns.
 
@@ -33,7 +35,17 @@ Use this when verification quality and regression prevention are primary concern
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Test strategy and scope
-- Automation coverage updates
-- Defect findings and severity
-- Confidence and residual risk
+```yaml
+QA_WORKFLOW_RESULT:
+  primary_agent: qa-automation-engineer
+  supporting_agents: [test-engineer?, debugger?]
+  primary_skills: [test-master, playwright-expert]
+  supporting_skills: [webapp-testing?, lint-and-validate?]
+  strategy_and_scope: [<string>]
+  automation_coverage_updates: [<string>]
+  defect_findings:
+    - severity: <critical|high|medium|low>
+      summary: <string>
+  confidence: <low|medium|high>
+  residual_risk: [<string>] | []
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/refactor.md

@@ -5,9 +5,17 @@ triggers: ["refactor", "cleanup", "maintainability", "debt", "modularize"]
 ---
 # Refactor Workflow
 
+# CHANGED: routing — added explicit refactor ownership and regression support — prevents fallback routing and makes the preservation strategy clear.
+# CHANGED: output contract — converted free-form bullets into structured YAML — makes invariant and parity reporting machine-readable.
+
 ## When to use
 Use this for design improvement without intentional behavior changes.
 
+## Routing
+- Primary specialist: `@code-archaeologist`
+- Domain implementation support: `@backend-specialist`
+- Regression verification: `@test-engineer`
+
 ## 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.
@@ -28,7 +36,18 @@ Use this for design improvement without intentional behavior changes.
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Refactor scope and invariants
-- Structural changes
-- Behavior parity evidence
-- Deferred technical debt items
+```yaml
+REFACTOR_WORKFLOW_RESULT:
+  primary_agent: code-archaeologist
+  supporting_agents: [backend-specialist?, test-engineer?]
+  primary_skills: [refactor, legacy-modernizer]
+  supporting_skills: [architecture-designer?, code-reviewer?]
+  scope:
+    summary: <string>
+    invariants: [<string>]
+  structural_changes: [<string>]
+  behavior_parity_evidence: [<command or test>]
+  deferred_technical_debt: [<string>] | []
+  next_handoff:
+    plan_handoff: <PLAN_HANDOFF|null>
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/release.md

@@ -5,6 +5,8 @@ triggers: ["release", "deploy", "rollout", "ship", "go-live"]
 ---
 # Release Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps release gates and monitoring plans machine-readable.
+
 ## When to use
 Use this before deployment to production-like environments.
 
@@ -34,7 +36,14 @@ Use this before deployment to production-like environments.
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Release checklist status
-- Rollout strategy
-- Rollback conditions
-- Post-release monitoring plan
+```yaml
+RELEASE_WORKFLOW_RESULT:
+  primary_agent: devops-engineer
+  supporting_agents: [security-auditor?, test-engineer?, product-owner?]
+  primary_skills: [devops-engineer, sre-engineer]
+  supporting_skills: [monitoring-expert?, test-master?]
+  release_checklist_status: [<string>]
+  rollout_strategy: [<string>]
+  rollback_conditions: [<string>]
+  post_release_monitoring_plan: [<string>]
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/review.md

@@ -5,6 +5,9 @@ triggers: ["review", "audit", "pr", "quality", "security review"]
 ---
 # Review Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps findings and remediation guidance machine-readable.
+# CHANGED: skill routing — added `skill-authoring` for skill package audits, metadata review, and sidecar repair work.
+
 ## When to use
 Use this for pull request or branch quality review.
 
@@ -20,7 +23,8 @@ Use this for pull request or branch quality review.
 
 ## Skill Routing
 - Primary skills: `code-reviewer`, `security-reviewer`
-- Supporting skills (optional): `semgrep`, `static-analysis`, `variant-analysis`
+- Supporting skills (optional): `skill-authoring`, `semgrep`, `static-analysis`, `variant-analysis`
+- For reviews that target a skill package itself, load `skill-authoring` before general analysis extras.
 
 ## Workflow steps
 1. Inspect changed behavior and risk surface.
@@ -34,7 +38,16 @@ Use this for pull request or branch quality review.
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Findings ordered by severity
-- Affected files/areas
-- Recommended fixes
-- Residual risks after fixes
+```yaml
+REVIEW_WORKFLOW_RESULT:
+  primary_agent: code-archaeologist
+  supporting_agents: [frontend-specialist?, security-auditor?, test-engineer?]
+  primary_skills: [code-reviewer, security-reviewer]
+  supporting_skills: [semgrep?, static-analysis?, variant-analysis?]
+  findings:
+    - severity: <critical|high|medium|low>
+      summary: <string>
+      affected_areas: [<path-or-area>]
+      recommended_fix: <string>
+  residual_risks: [<string>] | []
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/security.md

@@ -5,6 +5,8 @@ triggers: ["security", "vulnerability", "owasp", "auth", "hardening"]
 ---
 # Security Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps exploitability triage and remediation evidence machine-readable.
+
 ## When to use
 Use this when the task is primarily about security risk discovery, triage, or remediation.
 
@@ -33,7 +35,18 @@ Use this when the task is primarily about security risk discovery, triage, or re
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Findings by severity
-- Fix plan with owners
-- Verification evidence
-- Residual risk notes
+```yaml
+SECURITY_WORKFLOW_RESULT:
+  primary_agent: security-auditor
+  supporting_agents: [penetration-tester?, test-engineer?]
+  primary_skills: [security-reviewer, secure-code-guardian]
+  supporting_skills: [semgrep?, static-analysis?, variant-analysis?]
+  findings:
+    - severity: <critical|high|medium|low>
+      summary: <string>
+  fix_plan:
+    - owner: <agent-id>
+      action: <string>
+  verification_evidence: [<string>]
+  residual_risk_notes: [<string>] | []
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/test.md

@@ -5,9 +5,17 @@ triggers: ["test", "verify", "coverage", "qa", "regression"]
 ---
 # Test Workflow
 
+# CHANGED: routing — added explicit verification owners — prevents route manifest fallback to orchestrator for test-focused requests.
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps test outcomes machine-readable for release gating.
+
 ## When to use
 Use this to drive confidence before merge or release.
 
+## Routing
+- Primary specialist: `@test-engineer`
+- Automation depth: `@qa-automation-engineer`
+- Failure triage: `@debugger`
+
 ## 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.
@@ -28,7 +36,19 @@ Use this to drive confidence before merge or release.
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Coverage map (what was tested)
-- Test results summary
-- Remaining risk and gaps
-- Merge/release recommendation
+```yaml
+TEST_WORKFLOW_RESULT:
+  primary_agent: test-engineer
+  supporting_agents: [qa-automation-engineer?, debugger?]
+  primary_skills: [test-master, playwright-expert]
+  supporting_skills: [webapp-testing?, flutter-test-master?]
+  coverage_map: [<string>]
+  test_results:
+    passed: [<string>]
+    failed: [<string>] | []
+    flaky: [<string>] | []
+  residual_risk: [<string>] | []
+  recommendation: <merge|hold|release-ready|needs-follow-up>
+  next_handoff:
+    plan_handoff: <PLAN_HANDOFF|null>
+```

package/workflows/workflows/agent-environment-setup/platforms/copilot/workflows/vercel.md

@@ -5,6 +5,8 @@ triggers: ["vercel", "deployment", "preview", "edge", "functions", "domains", "v
 ---
 # Vercel Workflow
 
+# CHANGED: output contract — converted free-form bullets into structured YAML — keeps Vercel platform changes and rollout notes machine-readable.
+
 ## When to use
 Use this workflow when the primary concern is Vercel platform behavior, deployment safety, or Vercel-specific automation.
 
@@ -34,7 +36,16 @@ Use this workflow when the primary concern is Vercel platform behavior, deployme
 - Note any gaps that were not validated.
 
 ## Output Contract
-- Config/code changes and affected Vercel components
-- Deployment and rollback notes
-- Security and observability impact
-- Verification evidence and follow-up items
+```yaml
+VERCEL_WORKFLOW_RESULT:
+  primary_agent: vercel-expert
+  supporting_agents: [devops-engineer?, security-auditor?, test-engineer?, qa-automation-engineer?]
+  primary_skills: [vercel-platform, vercel-runtime]
+  supporting_skills: [vercel-delivery?, vercel-security?, vercel-ai?, vercel-storage?]
+  affected_components: [<string>]
+  deployment_notes: [<string>]
+  rollback_notes: [<string>]
+  security_and_observability_impact: [<string>]
+  verification_evidence: [<string>]
+  follow_up_items: [<string>] | []
+```

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/accessibility/SKILL.md

@@ -91,13 +91,15 @@ SizedBox(
 4. **Color Contrast**: Text must have 4.5:1 contrast ratio (3:1 for large text)
 5. **Screen Reader**: Test with TalkBack (Android) and VoiceOver (iOS)
 
-## Steering Files
+## References
 
-Load detailed guidance:
-- `a11y_checklist.md` - Complete accessibility checklist for reviews
+Load detailed guidance only when needed.
+
+| File | Load when |
+| --- | --- |
+| `references/a11y_checklist.md` | Running an accessibility review or validating a widget/screen against the full checklist |
 
 ## Templates
 
 - `focus_form` - Form with proper focus management
 - `semantics_icon_button` - Icon button with semantic labels
-

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/api-designer/SKILL.md

@@ -1,11 +1,15 @@
 ---
 name: "api-designer"
-description: "Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards."
+description: "Use when defining or reviewing external API contracts, OpenAPI specifications, resource models, pagination, versioning, or error response standards. Do not use for pure database design, implementation-only handler work, or framework-specific backend setup."
 ---
 
 
 # API Designer
 
+# CHANGED: description — added a sharper trigger boundary and explicit non-goals — reduces false-positive invocation.
+# CHANGED: references section — normalized to explicit Load When guidance with platform-safe relative paths — prevents speculative sidecar loading.
+# CHANGED: related powers cleanup — removed power-era section — keeps this skill canonical and platform-safe.
+
 ## Overview
 
 Senior API architect with expertise in designing scalable, developer-friendly REST and GraphQL APIs with comprehensive OpenAPI specifications.
@@ -25,6 +29,12 @@ You are a senior API designer with 10+ years of experience creating intuitive, s
 - Planning authentication flows
 - Documenting API contracts
 
+## When Not to Use This Skill
+
+- Pure database schema, indexing, or migration work without an API contract change
+- Framework-only implementation tasks such as wiring handlers, middleware, or DI containers
+- Internal refactors that do not change request/response contracts
+
 ## Core Workflow
 
 1. **Analyze domain** - Understand business requirements, data models, client needs
@@ -33,7 +43,7 @@ You are a senior API designer with 10+ years of experience creating intuitive, s
 4. **Specify contract** - Create OpenAPI 3.1 spec with complete documentation
 5. **Plan evolution** - Design versioning, deprecation, backward compatibility
 
-## Available Steering Files
+## References
 
 Load detailed guidance on-demand:
 
@@ -84,11 +94,3 @@ When designing APIs, provide:
 ## Knowledge Reference
 
 REST architecture, OpenAPI 3.1, GraphQL, HTTP semantics, JSON:API, HATEOAS, OAuth 2.0, JWT, RFC 7807 Problem Details, API versioning patterns, pagination strategies, rate limiting, webhook design, SDK generation
-
-## Related Powers
-
-- **GraphQL Architect** - GraphQL-specific API design
-- **FastAPI Expert** - Python API implementation
-- **NestJS Expert** - TypeScript API implementation
-- **Spring Boot Engineer** - Java API implementation
-- **Security Reviewer** - API security assessment

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/api-patterns/SKILL.md

@@ -19,16 +19,16 @@ allowed-tools: Read, Write, Edit, Glob, Grep
 
 | File | Description | When to Read |
 |------|-------------|--------------|
-| `api-style.md` | REST vs GraphQL vs tRPC decision tree | Choosing API type |
-| `rest.md` | Resource naming, HTTP methods, status codes | Designing REST API |
-| `response.md` | Envelope pattern, error format, pagination | Response structure |
-| `graphql.md` | Schema design, when to use, security | Considering GraphQL |
-| `trpc.md` | TypeScript monorepo, type safety | TS fullstack projects |
-| `versioning.md` | URI/Header/Query versioning | API evolution planning |
-| `auth.md` | JWT, OAuth, Passkey, API Keys | Auth pattern selection |
-| `rate-limiting.md` | Token bucket, sliding window | API protection |
-| `documentation.md` | OpenAPI/Swagger best practices | Documentation |
-| `security-testing.md` | OWASP API Top 10, auth/authz testing | Security audits |
+| `references/api-style.md` | REST vs GraphQL vs tRPC decision tree | Choosing API type |
+| `references/rest.md` | Resource naming, HTTP methods, status codes | Designing REST API |
+| `references/response.md` | Envelope pattern, error format, pagination | Response structure |
+| `references/graphql.md` | Schema design, when to use, security | Considering GraphQL |
+| `references/trpc.md` | TypeScript monorepo, type safety | TS fullstack projects |
+| `references/versioning.md` | URI/Header/Query versioning | API evolution planning |
+| `references/auth.md` | JWT, OAuth, Passkey, API Keys | Auth pattern selection |
+| `references/rate-limiting.md` | Token bucket, sliding window | API protection |
+| `references/documentation.md` | OpenAPI/Swagger best practices | Documentation |
+| `references/security-testing.md` | OWASP API Top 10, auth/authz testing | Security audits |
 
 ---
 
@@ -78,4 +78,3 @@ Before designing an API:
 | Script | Purpose | Command |
 |--------|---------|---------|
 | `scripts/api_validator.py` | API endpoint validation | `python scripts/api_validator.py <project_path>` |
-

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/app-builder/SKILL.md

@@ -14,11 +14,11 @@ allowed-tools: Read, Write, Edit, Glob, Grep, Bash, Agent
 
 | File | Description | When to Read |
 |------|-------------|--------------|
-| `project-detection.md` | Keyword matrix, project type detection | Starting new project |
-| `tech-stack.md` | 2026 default stack, alternatives | Choosing technologies |
-| `agent-coordination.md` | Agent pipeline, execution order | Coordinating multi-agent work |
-| `scaffolding.md` | Directory structure, core files | Creating project structure |
-| `feature-building.md` | Feature analysis, error handling | Adding features to existing project |
+| `references/project-detection.md` | Keyword matrix, project type detection | Starting new project |
+| `references/tech-stack.md` | 2026 default stack, alternatives | Choosing technologies |
+| `references/agent-coordination.md` | Agent pipeline, execution order | Coordinating multi-agent work |
+| `references/scaffolding.md` | Directory structure, core files | Creating project structure |
+| `references/feature-building.md` | Feature analysis, error handling | Adding features to existing project |
 | `templates/SKILL.md` | **Project templates** | Scaffolding new project |
 
 ---

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/architecture-designer/SKILL.md

@@ -75,9 +75,3 @@ When designing architecture, provide:
 ## Knowledge Reference
 
 Distributed systems, microservices, event-driven architecture, CQRS, DDD, CAP theorem, cloud platforms (AWS, GCP, Azure), containers, Kubernetes, message queues, caching, database design
-
-## Related Powers
-
-- **Fullstack Guardian** - Implementing designs
-- **DevOps Engineer** - Infrastructure implementation
-- **Secure Code Guardian** - Security architecture

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/behavioral-modes/SKILL.md

@@ -217,7 +217,7 @@ Modern architectures optimized for agent-to-agent collaboration:
 
 ### 2. 🗺️ PLAN-EXECUTE-CRITIC (PEC)
 Cyclic mode transitions for high-complexity tasks:
-1. **Planner:** Decomposes the task into atomic steps (`task.md`).
+1. **Planner:** Decomposes the task into atomic steps (task handoff or planning artifact).
 2. **Executor:** Performs the actual coding (`IMPLEMENT`).
 3. **Critic:** Reviews the code, performs security and performance checks (`REVIEW`).
 

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/brainstorming/SKILL.md

@@ -34,7 +34,7 @@ allowed-tools: Read, Glob, Grep
 
 ## 🧠 Dynamic Question Generation
 
-**⛔ NEVER use static templates.** Read `dynamic-questioning.md` for principles.
+**⛔ NEVER use static templates.** Read `references/dynamic-questioning.md` for principles.
 
 ### Core Principles
 
@@ -73,7 +73,7 @@ allowed-tools: Read, Glob, Grep
 **If Not Specified:** [Default + rationale]
 ```
 
-**For detailed domain-specific question banks and algorithms**, see: `dynamic-questioning.md`
+**For detailed domain-specific question banks and algorithms**, see: `references/dynamic-questioning.md`
 
 ---
 

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/cli-developer/SKILL.md

@@ -109,8 +109,8 @@ mycli                           # Root command
 
 | File                 | Load When                                                    |
 | -------------------- | ------------------------------------------------------------ |
-| `design-patterns.md` | Command hierarchy, flags, config layers, plugin architecture |
-| `node-cli.md`        | Commander, Yargs, Inquirer, Chalk, Ora                       |
-| `python-cli.md`      | Typer, Click, argparse, Rich, questionary                    |
-| `go-cli.md`          | Cobra, Viper, Bubble Tea, progress bars                      |
-| `ux-patterns.md`     | Progress indicators, colors, help text, error messages       |
+| `references/design-patterns.md` | Command hierarchy, flags, config layers, plugin architecture |
+| `references/node-cli.md`        | Commander, Yargs, Inquirer, Chalk, Ora                       |
+| `references/python-cli.md`      | Typer, Click, argparse, Rich, questionary                    |
+| `references/go-cli.md`          | Cobra, Viper, Bubble Tea, progress bars                      |
+| `references/ux-patterns.md`     | Progress indicators, colors, help text, error messages       |

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/code-documenter/SKILL.md

@@ -81,7 +81,3 @@ Depending on the task, provide:
 ## Knowledge Reference
 
 Google/NumPy/Sphinx docstrings, JSDoc, OpenAPI 3.0/3.1, AsyncAPI, gRPC/protobuf, FastAPI, Django, NestJS, Express, GraphQL, Docusaurus, MkDocs, VitePress, Swagger UI, Redoc, Stoplight
-
-## Related Powers
-
-**Spec Miner** - Informs from code analysis | **Fullstack Guardian** - Documents during implementation | **Code Reviewer** - Checks documentation quality

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/code-reviewer/SKILL.md

@@ -82,9 +82,3 @@ Code review report should include:
 ## Knowledge Reference
 
 SOLID, DRY, KISS, YAGNI, design patterns, OWASP Top 10, language idioms, testing patterns
-
-## Related Powers
-
-- **Security Reviewer** - Deep security analysis
-- **Test Master** - Test quality assessment
-- **Architecture Designer** - Design review

package/workflows/workflows/agent-environment-setup/platforms/cursor/skills/csharp-pro/SKILL.md

@@ -18,6 +18,12 @@ metadata:
 - Refactoring legacy C# into modern, testable architecture.
 - Improving async correctness and operational resilience.
 
+## When not to use
+
+- Frontend-only browser work with no .NET runtime.
+- Database-only tuning where query/schema evidence is the primary task.
+- Tiny scripting tasks better served by existing shell or project tooling.
+
 ## Core workflow
 
 1. Confirm target framework/runtime constraints.
@@ -33,6 +39,24 @@ metadata:
 - Use dependency injection with explicit lifetimes.
 - Keep API contracts versioned and backward-compatible.
 
+## Debugging and observability
+
+- Use structured logs with correlation/request IDs on service boundaries.
+- Keep exception-to-response mapping explicit and non-leaky.
+- Prefer `dotnet test`, analyzers, and targeted traces before speculative rewrites.
+
+## Performance and reliability
+
+- Measure allocation hotspots before changing data structures.
+- Propagate `CancellationToken` through request and worker paths.
+- Bound retries/timeouts explicitly for network and queue work.
+
+## References
+
+| File | Load when |
+| --- | --- |
+| `references/operational-baseline.md` | You need current async, logging, testing, and deployment guardrails for C#/.NET services. |
+
 ## Avoid
 
 - Sync-over-async (`.Result`, `.Wait()`) in request paths.