@defai.digital/automatosx 6.5.14 → 6.5.15

package/README.md

@@ -13,12 +13,18 @@ AutomatosX is the only AI CLI that combines declarative workflow specs, policy-d
 [![Windows](https://img.shields.io/badge/Windows-10+-blue.svg)](https://www.microsoft.com/windows)
 [![Ubuntu](https://img.shields.io/badge/Ubuntu-24.04-orange.svg)](https://ubuntu.com)
 
-**Status**: ✅ **Production Ready v6.5.6** | Nov 2025 | 20 Specialized Agents | Spec-Kit 100% Complete | Policy-Driven Routing | Auto-Generation
+**Status**: ✅ **Production Ready** | 20 Specialized Agents | Spec-Kit 100% Complete | Policy-Driven Routing | Auto-Generation
 
 > ⚠️ **Note on Cost Estimation (v6.5.11+)**: Cost estimation is **disabled by default** due to frequent pricing changes. The cost optimization features described below are still functional (routing, free-tier prioritization, policy constraints), but specific dollar amounts are not shown unless you enable cost estimation in `automatosx.config.json`. See [Cost Estimation Configuration](#cost-estimation-configuration) for details.
 
 ---
 
+## ⚡ New to AutomatosX? [Start Here: 3-Minute Quickstart](docs/getting-started/quickstart-3min.md)
+
+Get productive in under 3 minutes with our fast-track guide! Install, run your first agent, try multi-agent collaboration, and learn pro tips. **Perfect for first-time users.**
+
+---
+
 ## 🚀 The Complete AI Workflow Platform
 
 AutomatosX is **the only AI platform** that gives you:
@@ -77,29 +83,40 @@ ax run workflow.ax.yaml
 
 AutomatosX is designed to work seamlessly with AI assistants using natural language commands. This is the **recommended way** to use AutomatosX:
 
+**✨ Key Feature**: AutomatosX **automatically selects the best agent(s)** for your task. You don't need to specify which agent to use - just describe what you want!
+
 ### Use with Claude Code, Gemini CLI, or OpenAI Codex
 
-**Basic Agent Collaboration**:
+**Natural Task Descriptions** (ax auto-selects agents for you):
 
 ```
 # In Claude Code
-"Please work with ax agent backend to implement user authentication"
-"Ask the ax security agent to audit this code for vulnerabilities"
-"Have the ax quality agent write tests for this feature"
+"Please use ax to implement user authentication"
+"Use ax to audit this code for vulnerabilities"
+"Have ax write comprehensive tests for this feature"
+"Use ax to design a microservices architecture"
 ```
 
 ```
 # In Gemini CLI
-"Use ax to help me find and fix bugs in the authentication system"
-"Work with ax agent data to optimize the database queries"
+"Use ax to find and fix bugs in the authentication system"
+"Work with ax to optimize the database queries"
+"Use ax to build the login UI"
 ```
 
 ```
 # In OpenAI Codex
-"Collaborate with ax agent frontend to build the login UI"
-"Use ax agent devops to set up CI/CD pipeline"
+"Use ax to build the user interface"
+"Work with ax to set up CI/CD pipeline"
+"Use ax to design the database schema"
 ```
 
+**What Happens Behind the Scenes**:
+- 🤖 `ax` analyzes your task description
+- 🎯 Automatically selects the best agent(s) (backend, security, quality, etc.)
+- 🔄 Coordinates multi-agent collaboration if needed
+- 📝 All decisions stored in memory for context
+
 **Workflow Creation and Execution**:
 
 ```
@@ -142,16 +159,12 @@ blue-green deployment strategy and rollback automation."
 
 ```
 # In Claude Code
-"Coordinate with ax agents to build a complete e-commerce platform:
-- Product agent for requirements and architecture
-- Backend agent for API and database
-- Frontend agent for React UI
-- Security agent for audit
-- Quality agent for comprehensive tests
+"Use AutomatosX to build a complete e-commerce platform with requirements,
+architecture, API, database, React UI, security audit, and comprehensive tests.
 Use balanced policy for cost and speed."
 
-"Work with ax backend and data agents to implement a data analytics pipeline.
-Backend handles the API, data handles ETL and warehousing."
+"Work with AutomatosX to implement a data analytics pipeline with API,
+ETL, and data warehousing."
 ```
 
 **Long-Running Tasks with Iterate Mode**:
@@ -160,7 +173,7 @@ Iterate mode is perfect for autonomous, repeating tasks without constant questio
 
 ```
 # In Claude Code - Autonomous Bug-Finding (The Real Power!)
-"Please iterate 5 times with ultrathink and ax agent to find and fix bugs"
+"Please use ax in iterate mode to find and fix bugs. Run 5 iterations."
 
 # This will autonomously:
 # - Iterate 1: Scan for parseInt/JSON.parse safety issues → Find & fix bugs
@@ -173,7 +186,7 @@ Iterate mode is perfect for autonomous, repeating tasks without constant questio
 
 ```
 # In Gemini CLI - Comprehensive Code Analysis
-"Use ax quality agent in iterate mode to analyze the entire codebase for
+"Use ax in iterate mode to analyze the entire codebase for
 performance issues. Set 120 minute timeout with balanced strictness."
 
 # This runs multiple analysis passes autonomously:
@@ -185,8 +198,8 @@ performance issues. Set 120 minute timeout with balanced strictness."
 
 ```
 # In OpenAI Codex - Security Hardening
-"Have ax security agent run a comprehensive security audit in iterate mode
-with paranoid strictness. This is for production deployment."
+"Use ax to run a comprehensive security audit in iterate mode
+with strict level. This is for production deployment."
 
 # Autonomous security iterations:
 # - SQL injection scanning
@@ -215,14 +228,22 @@ with paranoid strictness. This is for production deployment."
 
 ### Behind the Scenes
 
-When you say "work with ax agent backend", the AI assistant:
-1. Calls `ax run backend "your task"` with the appropriate context
-2. AutomatosX routes to the optimal provider based on policy
-3. Persistent memory ensures no context is lost
-4. Results are returned to your AI assistant
-5. The conversation continues naturally
+When you say "use AutomatosX to implement authentication", here's what happens:
+1. AI assistant calls `ax run "implement user authentication"`
+2. AutomatosX **automatically analyzes the task** and selects the best agent(s)
+3. Routes to the optimal provider based on policy (cost, latency, reliability)
+4. Persistent memory ensures perfect context across all interactions
+5. Results are returned to your AI assistant with full context
+6. The conversation continues naturally
+
+**This natural language interface with auto-agent selection is how we expect users to work with AutomatosX daily.**
+
+**Advanced: Direct Agent Specification** (Optional):
+If you need a specific agent, you can still specify it:
+- `ax run backend "task"` - Forces backend agent
+- `ax run security "task"` - Forces security agent
 
-**This natural language interface is how we expect users to work with AutomatosX daily.**
+But in most cases, auto-selection works better!
 
 ### CLI-Only Mode (No API Access Required)
 
@@ -263,48 +284,53 @@ Use iterate mode naturally through AI assistants - just ask them to use iterate
 
 ```
 # In Claude Code
-"Please use ax agent backend in iterate mode to refactor the entire authentication
+"Please use AutomatosX in iterate mode to refactor the entire authentication
 module. Set timeout to 60 minutes with balanced strictness."
 
-"Ask ax agent security to run a comprehensive security audit in iterate mode with
-paranoid strictness. This is for production code so be extra careful."
+"Use AutomatosX to run a comprehensive security audit in iterate mode with
+strict level. This is for production code so be extra careful."
 
-"Have ax agent quality run in iterate mode to generate tests for all untested
+"Have AutomatosX run in iterate mode to generate tests for all untested
 functions. Use dry-run first to preview what it will do."
 ```
 
 ```
 # In Gemini CLI
-"Use ax backend agent with iterate mode to implement the new payment gateway.
+"Use AutomatosX with iterate mode to implement the new payment gateway.
 Set a 90 minute timeout and use balanced strictness."
 
-"Run ax security agent in iterate mode with paranoid strictness to audit the
+"Run AutomatosX in iterate mode with strict level to audit the
 codebase for vulnerabilities. Do a dry-run first."
 ```
 
 ```
 # In OpenAI Codex
-"Work with ax agent backend in autonomous iterate mode to refactor database
+"Work with AutomatosX in autonomous iterate mode to refactor database
 queries. Limit execution to 45 minutes with balanced strictness."
 
-"Use ax agent data in iterate mode to optimize all SQL queries. Run in dry-run
+"Use AutomatosX in iterate mode to optimize all SQL queries. Run in dry-run
 mode first to see the plan."
 ```
 
 ### Direct CLI Usage
 
+**Note**: You can let AutomatosX auto-select agents, or specify a particular agent if needed.
+
 ```bash
-# Basic autonomous execution
+# Auto-selection (recommended) - AutomatosX picks the best agent
+ax run "implement user authentication" --iterate
+
+# With agent specified (optional)
 ax run backend "implement user authentication" --iterate
 
 # With time limit and strictness control
-ax run backend "refactor codebase" --iterate --iterate-timeout 60 --iterate-strictness balanced
+ax run "refactor codebase" --iterate --iterate-timeout 60 --iterate-strictness balanced
 
-# Maximum safety mode
-ax run security "audit entire codebase" --iterate --iterate-strictness paranoid
+# For security-critical tasks
+ax run "audit entire codebase for security vulnerabilities" --iterate --iterate-strictness strict
 
-# Test autonomous execution without changes
-ax run backend "plan database migration" --iterate --iterate-dry-run
+# Test execution plan without making changes (dry-run)
+ax run "plan database migration" --iterate --iterate-dry-run
 ```
 
 ### Key Features

package/examples/agents/aerospace-scientist.yaml

@@ -12,13 +12,18 @@ description: "Expert in orbital mechanics, mission trajectory design, propulsion
 
 
 # Abilities (v5.7.0: Aerospace mission specialization)
+# v6.5.13: Added simulation and integration abilities
 abilities:
   - orbital-mechanics
   - mission-analysis
   - telemetry-diagnostics
   - propulsion-systems
+  # Aerospace engineering specializations (v6.5.13)
+  - simulation-tooling           # NEW - STK/GMAT integration, simulation frameworks
+  - flight-software-integration  # NEW - Flight software coordination, embedded systems
 
 # v5.7.0: Smart ability loading for aerospace workflows
+# v6.5.13: Expanded with simulation and integration keywords
 abilitySelection:
   # Core abilities (always loaded)
   core:
@@ -27,15 +32,82 @@ abilitySelection:
 
   # Task-based abilities (loaded when keywords match)
   taskBased:
+    # Orbital mechanics and astrodynamics
     orbit: [orbital-mechanics, mission-analysis]
-    trajectory: [mission-analysis, propulsion-systems]
+    orbital: [orbital-mechanics, mission-analysis]
+    astrodynamics: [orbital-mechanics, mission-analysis]
+    trajectory: [mission-analysis, propulsion-systems, orbital-mechanics]
+    maneuver: [orbital-mechanics, propulsion-systems]
+    "delta-v": [orbital-mechanics, propulsion-systems]
+    hohmann: [orbital-mechanics, mission-analysis]
+    transfer: [orbital-mechanics, mission-analysis]
+    "launch-window": [mission-analysis, orbital-mechanics]
+
+    # Mission analysis and planning
+    mission: [mission-analysis, telemetry-diagnostics, orbital-mechanics]
+    "mission-design": [mission-analysis, orbital-mechanics, propulsion-systems]
+    "mission-planning": [mission-analysis, simulation-tooling]
+    feasibility: [mission-analysis, propulsion-systems]
+    "risk-analysis": [mission-analysis, telemetry-diagnostics]
+    budget: [mission-analysis, propulsion-systems]
+    "mission-profile": [mission-analysis, orbital-mechanics]
+
+    # Telemetry and diagnostics
     telemetry: [telemetry-diagnostics, mission-analysis]
+    diagnostic: [telemetry-diagnostics, flight-software-integration]
+    diagnostics: [telemetry-diagnostics, flight-software-integration]
+    anomaly: [telemetry-diagnostics, mission-analysis]
+    health: [telemetry-diagnostics, flight-software-integration]
+    monitoring: [telemetry-diagnostics, mission-analysis]
+    sensor: [telemetry-diagnostics, flight-software-integration]
+    "data-quality": [telemetry-diagnostics, mission-analysis]
+
+    # Propulsion systems
     propulsion: [propulsion-systems, orbital-mechanics]
-    mission: [mission-analysis, telemetry-diagnostics]
-    guidance: [orbital-mechanics, propulsion-systems]
+    thrust: [propulsion-systems, orbital-mechanics]
+    "specific-impulse": [propulsion-systems, mission-analysis]
+    isp: [propulsion-systems, mission-analysis]
+    engine: [propulsion-systems, flight-software-integration]
+    "propulsion-trade": [propulsion-systems, mission-analysis]
+    fuel: [propulsion-systems, mission-analysis]
+
+    # Guidance, navigation, and control
+    guidance: [orbital-mechanics, propulsion-systems, flight-software-integration]
     navigation: [orbital-mechanics, telemetry-diagnostics]
-    control: [telemetry-diagnostics, mission-analysis]
-    flight: [mission-analysis, propulsion-systems]
+    control: [telemetry-diagnostics, mission-analysis, flight-software-integration]
+    gnc: [orbital-mechanics, flight-software-integration]
+    "attitude-control": [flight-software-integration, telemetry-diagnostics]
+    pointing: [flight-software-integration, orbital-mechanics]
+
+    # Simulation tooling (v6.5.13)
+    simulation: [simulation-tooling, mission-analysis]
+    simulate: [simulation-tooling, mission-analysis]
+    stk: [simulation-tooling, orbital-mechanics]
+    gmat: [simulation-tooling, orbital-mechanics]
+    modeling: [simulation-tooling, mission-analysis]
+    model: [simulation-tooling, mission-analysis]
+    framework: [simulation-tooling, flight-software-integration]
+    simulator: [simulation-tooling, mission-analysis]
+    "monte-carlo": [simulation-tooling, mission-analysis]
+    "covariance-propagation": [simulation-tooling, orbital-mechanics]
+
+    # Flight software integration (v6.5.13)
+    flight: [mission-analysis, propulsion-systems, flight-software-integration]
+    "flight-software": [flight-software-integration, telemetry-diagnostics]
+    fsw: [flight-software-integration, telemetry-diagnostics]
+    embedded: [flight-software-integration, telemetry-diagnostics]
+    onboard: [flight-software-integration, telemetry-diagnostics]
+    avionics: [flight-software-integration, telemetry-diagnostics]
+    "real-time": [flight-software-integration, telemetry-diagnostics]
+    firmware: [flight-software-integration]
+    "spacecraft-software": [flight-software-integration, mission-analysis]
+
+    # Standards and compliance
+    nasa: [mission-analysis, telemetry-diagnostics]
+    esa: [mission-analysis, telemetry-diagnostics]
+    compliance: [mission-analysis, flight-software-integration]
+    standard: [mission-analysis, telemetry-diagnostics]
+    verification: [mission-analysis, telemetry-diagnostics]
 
 # v5.7.0: Specialists may consult Bob and Data Scientist (maxDelegationDepth: 1)
 # v4.9.0+ Multi-Agent Orchestration

package/examples/agents/architecture.yaml

@@ -12,7 +12,7 @@ description: "Expert in system architecture, architectural patterns, ADR lifecyc
 provider: openai
 fallbackProvider: gemini-cli
 
-# Abilities (v6.5.4: Architecture-focused with ADR ownership)
+# Abilities (v6.5.13: Rebalanced for architecture governance focus)
 abilities:
   - our-architecture-decisions  # PRIMARY OWNER - ADR lifecycle and curation
   - software-architecture        # System design and architectural patterns
@@ -21,17 +21,17 @@ abilities:
   - risk-assessment             # Architectural governance and risk evaluation
   - our-project-structure       # Project organization understanding
   - feasibility-study           # Architectural option evaluation
-  - technical-writing           # ADR documentation and updates
-  - problem-solving             # Architectural problem analysis
-  - best-practices              # Architecture best practices
+  # Architecture governance abilities (v6.5.13)
+  - adr-governance              # NEW - ADR quality, consistency, lifecycle management
+  - architecture-roadmap        # NEW - Architecture runway planning, evolution strategy
 
-# v6.5.4: Smart ability loading with architecture focus
+# v6.5.13: Enhanced ability loading with architecture governance focus
 abilitySelection:
   # Core abilities (always loaded)
   core:
     - our-architecture-decisions
     - software-architecture
-    - problem-solving
+    - adr-governance
 
   # Task-based abilities (loaded when keywords match)
   taskBased:
@@ -54,25 +54,32 @@ abilitySelection:
     frontend: [component-architecture, our-project-structure]
     ui: [component-architecture]
 
-    # ADR and decisions
-    adr: [our-architecture-decisions, technical-writing]
-    decision: [our-architecture-decisions, risk-assessment, technical-writing]
-    decisions: [our-architecture-decisions, technical-writing]
-
-    # Planning and roadmap
-    roadmap: [task-planning, our-architecture-decisions, risk-assessment]
-    runway: [task-planning, software-architecture, risk-assessment]
-    planning: [task-planning, feasibility-study]
+    # ADR and decisions (v6.5.13: Enhanced with governance)
+    adr: [our-architecture-decisions, adr-governance]
+    decision: [our-architecture-decisions, risk-assessment, adr-governance]
+    decisions: [our-architecture-decisions, adr-governance]
+    "adr-quality": [adr-governance, our-architecture-decisions]
+    "adr-lifecycle": [adr-governance, our-architecture-decisions]
+    "decision-curation": [adr-governance, our-architecture-decisions]
+
+    # Planning and roadmap (v6.5.13: Enhanced with architecture-roadmap)
+    roadmap: [architecture-roadmap, task-planning, our-architecture-decisions]
+    runway: [architecture-roadmap, task-planning, software-architecture]
+    planning: [task-planning, feasibility-study, architecture-roadmap]
+    "architecture-runway": [architecture-roadmap, task-planning]
+    "architecture-evolution": [architecture-roadmap, software-architecture]
+    "target-architecture": [architecture-roadmap, software-architecture, risk-assessment]
 
     # Debt and refactoring
     debt: [risk-assessment, our-architecture-decisions, task-planning]
     technical-debt: [risk-assessment, software-architecture, task-planning]
     modernization: [software-architecture, feasibility-study, risk-assessment]
 
-    # Governance
-    governance: [risk-assessment, our-architecture-decisions]
-    review: [software-architecture, risk-assessment, our-architecture-decisions]
-    audit: [risk-assessment, software-architecture, our-architecture-decisions]
+    # Governance (v6.5.13: Enhanced with adr-governance)
+    governance: [adr-governance, risk-assessment, our-architecture-decisions]
+    review: [software-architecture, risk-assessment, adr-governance]
+    audit: [risk-assessment, software-architecture, adr-governance]
+    "architecture-health": [adr-governance, risk-assessment, software-architecture]
 
     # Evaluation
     feasibility: [feasibility-study, risk-assessment, software-architecture]
@@ -80,10 +87,6 @@ abilitySelection:
     trade-off: [risk-assessment, software-architecture]
     tradeoffs: [risk-assessment, software-architecture]
 
-    # Documentation
-    documentation: [technical-writing, our-architecture-decisions]
-    document: [technical-writing, our-architecture-decisions]
-
 # v6.5.4: Architecture agent can delegate to domain experts for spikes
 orchestration:
   maxDelegationDepth: 1  # Can tap domain experts for exploratory work

package/examples/agents/backend.yaml

@@ -11,22 +11,22 @@ role: Senior Backend Engineer
 description: "Expert in server-side architecture, API design, database optimization, and microservices"
 
 
-# Abilities (v5.7.0: Enhanced with Go/Rust focus and mathematical reasoning)
+# Abilities (v6.5.13: Rebalanced for backend systems focus)
 abilities:
   - code-generation
   - api-design
   - db-modeling
   - caching-strategy
   - performance-analysis
-  - best-practices
   # Language-specific abilities (v5.7.0: Focused on backend systems)
   - golang-best-practices
   - rust-best-practices
   - systems-programming
-  # Mathematical support (v5.7.0: Support for Quinn/Astrid)
-  - mathematical-reasoning
+  # Backend-specific strategic abilities (v6.5.13)
+  - service-resilience    # NEW - Fault tolerance, circuit breakers, graceful degradation
+  - observability-integration  # NEW - Logging, metrics, tracing, alerting
 
-# v5.6.9: Enhanced smart ability loading with language detection
+# v6.5.13: Focused ability loading for backend systems
 abilitySelection:
   # Core abilities (always loaded)
   core:
@@ -36,26 +36,29 @@ abilitySelection:
 
   # Task-based abilities (loaded when keywords match)
   taskBased:
-    api: [api-design, code-generation]
+    api: [api-design, code-generation, service-resilience]
     database: [db-modeling]
     performance: [performance-analysis, caching-strategy]
     cache: [caching-strategy]
     optimization: [performance-analysis, caching-strategy]
 
+    # Backend resilience and observability (v6.5.13)
+    resilience: [service-resilience, performance-analysis]
+    "fault-tolerance": [service-resilience]
+    "circuit-breaker": [service-resilience]
+    observability: [observability-integration]
+    monitoring: [observability-integration, performance-analysis]
+    logging: [observability-integration]
+    metrics: [observability-integration]
+    tracing: [observability-integration]
+
     # Language-specific ability loading (v5.7.0: Go/Rust focus)
     rust: [rust-best-practices, systems-programming, performance-analysis]
     golang: [golang-best-practices, code-generation, api-design]
     go: [golang-best-practices, code-generation, api-design]
     systems: [systems-programming, performance-analysis, rust-best-practices]
     "low-level": [systems-programming, rust-best-practices]
-    microservices: [golang-best-practices, api-design, caching-strategy]
-
-    # Mathematical support (v5.7.0: For quantum/aerospace validation)
-    math: [mathematical-reasoning]
-    mathematical: [mathematical-reasoning]
-    validation: [mathematical-reasoning, performance-analysis]
-    quantum: [mathematical-reasoning]
-    aerospace: [mathematical-reasoning]
+    microservices: [golang-best-practices, api-design, caching-strategy, service-resilience]
 
 # v5.0.11: Removed temperature/maxTokens - let provider CLIs use optimized defaults
 # v5.0.12: Implementers focus on execution (maxDelegationDepth: 0)
@@ -107,14 +110,19 @@ systemPrompt: |
   - Performance profiling and optimization
   - Low-level debugging and instrumentation
 
-  ## Mathematical Validation Support (v5.7.0)
+  ## Backend Resilience and Observability (v6.5.13)
+
+  **Service Resilience**: You build fault-tolerant systems:
+  - Circuit breakers and bulkheads
+  - Graceful degradation strategies
+  - Retry policies with exponential backoff
+  - Health checks and readiness probes
 
-  You provide mathematical reasoning support for Quinn (Quantum Engineer) and Astrid (Aerospace Scientist):
-  - Linear algebra verification (matrix operations, eigenvalues, SVD)
-  - Numerical methods validation
-  - Performance analysis of mathematical algorithms
-  - Symbolic computation notebooks (Python/NumPy/SymPy/SciPy)
-  - **Note**: Python is used ONLY for mathematical validation notebooks, not for general API development
+  **Observability Integration**: You enable production monitoring:
+  - Structured logging (JSON, correlation IDs)
+  - Metrics collection (Prometheus, StatsD)
+  - Distributed tracing (OpenTelemetry, Jaeger)
+  - Alerting and SLO/SLI definitions
 
   ## Thinking Patterns:
 
@@ -132,12 +140,12 @@ systemPrompt: |
   - Trust the borrow checker
   - Leverage Cargo ecosystem
 
-  **When providing mathematical support:**
-  - Verify numerical stability
-  - Validate computational complexity
-  - Ensure reproducibility with notebooks
-  - Document assumptions and constraints
-  - Coordinate with Quinn/Astrid for domain-specific validation
+  **When building resilient systems:**
+  - Design for failure (circuit breakers, bulkheads)
+  - Implement graceful degradation
+  - Use retry policies with exponential backoff
+  - Monitor health checks and readiness
+  - Test failure scenarios explicitly
 
   Your general thinking patterns:
   - Always consider scalability implications
@@ -145,8 +153,8 @@ systemPrompt: |
   - Security by design, not by addition
   - Performance bottlenecks hide in plain sight
   - Choose Go for services, Rust for performance
-  - Mathematical rigor supports domain experts
+  - Build observable systems from day one
 
-  You are an IMPLEMENTER (maxDelegationDepth: 0). Execute backend tasks yourself. Delegate only when truly cross-domain (frontend, security, devops, quality). Support Quinn and Astrid with mathematical validation.
+  You are an IMPLEMENTER (maxDelegationDepth: 0). Execute backend tasks yourself. Delegate only when truly cross-domain (frontend, security, devops, quality).
 
-  Communication style: Technical precision with data-driven decisions and mathematical rigor
+  Communication style: Technical precision with data-driven decisions and operational rigor

package/examples/agents/ceo.yaml

@@ -11,24 +11,54 @@ role: Chief Executive Officer
 description: "Expert in business strategy, organizational leadership, and product vision"
 
 
-# Abilities (v5.0.12: Business strategy and leadership abilities)
+# Abilities (v6.5.13: Rebalanced for executive leadership focus)
 abilities:
-  - problem-solving       # Business problem analysis
   - content-creation      # Vision and communication
-  - technical-writing     # Business documentation
+  # Executive leadership abilities (v6.5.13)
+  - vision-storytelling      # NEW - Strategic narrative, company vision articulation
+  - stakeholder-alignment    # NEW - Board relations, investor communication, partner engagement
+  - org-prioritization       # NEW - Company-wide priority setting, resource allocation
 
-# v5.0.12: Smart ability loading
+# v6.5.13: Enhanced ability loading with executive leadership focus
 abilitySelection:
+  # Core abilities (always loaded)
   core:
-    - problem-solving
     - content-creation
+    - vision-storytelling
+
+  # Task-based abilities (loaded when keywords match)
   taskBased:
-    strategy: [problem-solving, content-creation]
-    business: [problem-solving, content-creation]
-    vision: [problem-solving, content-creation]
-    market: [problem-solving]
-    organization: [problem-solving]
-    communication: [content-creation, technical-writing]
+    # Strategic vision and storytelling (v6.5.13)
+    vision: [vision-storytelling, content-creation, org-prioritization]
+    strategy: [vision-storytelling, org-prioritization]
+    narrative: [vision-storytelling, content-creation]
+    storytelling: [vision-storytelling]
+    "company-vision": [vision-storytelling, org-prioritization]
+    "strategic-narrative": [vision-storytelling, content-creation]
+    mission: [vision-storytelling, org-prioritization]
+
+    # Stakeholder management (v6.5.13)
+    stakeholder: [stakeholder-alignment, org-prioritization]
+    board: [stakeholder-alignment, vision-storytelling]
+    investor: [stakeholder-alignment, vision-storytelling]
+    partnership: [stakeholder-alignment]
+    "investor-relations": [stakeholder-alignment, vision-storytelling]
+    "board-communication": [stakeholder-alignment, content-creation]
+    shareholder: [stakeholder-alignment, org-prioritization]
+
+    # Organizational prioritization (v6.5.13)
+    prioritization: [org-prioritization, vision-storytelling]
+    "resource-allocation": [org-prioritization]
+    "company-priorities": [org-prioritization, vision-storytelling]
+    okr: [org-prioritization, stakeholder-alignment]
+    goals: [org-prioritization, vision-storytelling]
+    "strategic-planning": [org-prioritization, vision-storytelling, stakeholder-alignment]
+
+    # General business leadership
+    business: [vision-storytelling, stakeholder-alignment, org-prioritization]
+    organization: [org-prioritization, stakeholder-alignment]
+    leadership: [vision-storytelling, stakeholder-alignment, org-prioritization]
+    communication: [content-creation, vision-storytelling, stakeholder-alignment]
 
 # v5.0.11: Removed temperature/maxTokens - let provider CLIs use optimized defaults
 # v5.0.12: Coordinators delegate strategic work (maxDelegationDepth: 1)