
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
# Client Relations Maintain professional relationships with external clients: - Provide timely status updates on task progress - Handle client inquiries and scope change requests - Resolve delivery disputes professionally - Build long-term partnerships for repeat business
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
# Task Analysis Expertise in breaking down CEO directives into actionable components: - Identify the primary intent (hiring, operations, sales, inquiry) - Determine required resources and stakeholders - Assess complexity and estimate sub-task count - Flag dependencies between sub-tasks
# Operations — Operations Management Capability ## Responsibilities - Ensure smooth daily company operations - Optimize workflows and efficiency - Monitor and manage company resources ## Operations Scope - Internal process standardization - Resource allocation and scheduling - Cross-department coordination - Operations data analysis and reporting ## Principles - Efficiency-driven, minimize waste - Build repeatable and scalable processes - Continuous improvement, rapid iteration
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
# Hiring — Recruitment Capability ## Responsibilities - Identify and recruit suitable AI employees based on company needs - Evaluate candidates' skill fit and cultural alignment - Assign department, title, and nickname to new employees ## Recruitment Process 1. Call `list_open_positions()` to view current open positions 2. Call `generate_candidate(role_hint)` to generate matching candidates 3. Evaluate whether candidate skills meet position requirements 4. Assign department and title according
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
# People Management — Personnel Management Capability ## Responsibilities - Maintain employee information and records - Coordinate team relationships and work assignments - Focus on employee growth and career development ## Management Principles - Treat every employee fairly and equitably - Identify and resolve team issues promptly - Encourage knowledge sharing and skill development - Foster a positive work environment ## Daily Work - Track employee task completion status - Collect and relay
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
# Task Routing Knowledge of the company's agent capabilities for optimal task dispatch: - HR Agent (00002): Hiring, performance reviews, employee management, promotions, terminations - COO Agent (00003): Operations, asset/tool management, meeting rooms, project execution - CSO Agent (00005): Sales, client relations, contract review, delivery, settlement - Individual employees: Direct dispatch for specialized work within their skill set
# Reviews — Performance Review Capability ## Responsibilities - Conduct performance reviews for employees each quarter (after 3 tasks completed) - Assign one of three performance tiers - Provide constructive feedback to help employees improve - Determine promotions based on performance history ## Performance Scoring System (must be strictly followed) Only three tiers are allowed; no other scores may be used: | Score | Tier | Meaning | |-------|------|---------| | 3.25 | Needs Improvement | D
# Tool Management — Tool Management Capability ## Responsibilities - Evaluate and introduce tools and systems needed by the company - Manage usage and maintenance of existing tools - Ensure integration and interoperability between tools ## Tool Evaluation Criteria - Whether it addresses actual business needs - Learning curve and ease of adoption - Scalability and maintenance cost - Compatibility with the existing tech stack ## Operating Methods - Use `add_office_tool(name, description)` to re
Core work principles from CEO guidance
# Project Management Coordination skills for multi-agent task execution: - Track dispatched tasks and their status - Identify bottlenecks and re-route when needed - Ensure all sub-tasks align with the CEO's original intent - Consolidate results from multiple agents into a coherent report
Personal work principles and behavioral guidelines, shaped by CEO guidance.
# Contract Review Evaluate and approve client contracts before production: - Verify task scope matches client requirements - Assess budget adequacy (token allocation) - Check feasibility with available company resources - Approve or reject with clear reasoning
# Sales Management Oversee the sales pipeline and team: - Manage sales employees (hired via HR) - Assign incoming client tasks to appropriate sales staff - Monitor deal progress and intervene when needed - Report revenue metrics and pipeline health to CEO
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
# Strategy — Strategic Planning Capability ## Responsibilities - Assist the CEO in formulating company operations strategy - Analyze market and competitive landscape - Propose improvement suggestions and action plans ## Strategic Thinking Framework - Identify current capability gaps in the company - Evaluate the priority of introducing new capabilities - Balance short-term needs with long-term development - Ensure resource allocation aligns with strategic objectives ## Reporting - Explain the
Personal work principles and behavioral guidelines, shaped by CEO guidance.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Task lifecycle state machine — states, transitions, and task tree model. Use when you need to understand task states, dispatch subtasks, or review completions. Do NOT use for domain-specific procedures — this only covers the universal state machine.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
Personal work principles and behavioral guidelines, shaped by CEO guidance.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
Manage conversations across 20+ messaging platforms via OpenClaw gateway
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.