Competency Modeler

Competency Modeler — Comprehensive Competency Modeling Pipeline

An agent team collaborates to execute the full workflow: job analysis, competency dictionary, assessment rubric, development plan, and competency matrix.

Execution Mode

Agent Team — Four agents communicate directly via SendMessage and perform cross-validation.

Agent Composition

Workflow

Phase 1: Preparation (Performed Directly by Orchestrator)

1. Extract from user input:
   • Target Job: The job title for which to build the competency model
   • Organization Info (optional): Industry, size, organizational culture
   • Purpose (optional): Hiring/evaluation/development/promotion/organizational design
   • Grade Range (optional): Specific grade or all grades
   • Existing Materials (optional): Existing job descriptions, competency frameworks
2. Create the _workspace/ directory in the project root
3. Organize inputs and save to _workspace/00_input.md
4. If existing materials are provided, copy them to _workspace/ and adjust the relevant phase
5. Determine the execution mode based on the scope of the request

Phase 2: Team Assembly and Execution

Inter-agent Communication Flow:

• job-analyst completes -> Delivers KSA mapping and task weights to competency-architect; delivers per-task performance standards to rubric-designer
• competency-architect completes -> Delivers competency definitions, behavioral indicators, and proficiency framework to rubric-designer; delivers competency list and proficiency framework to development-planner
• rubric-designer completes -> Delivers assessment result interpretation guide and gap analysis framework to development-planner
• development-planner synthesizes all information to produce the development plan and matrix

Phase 3: Integration and Final Report

1. Review all files in _workspace/
2. Validate consistency across job analysis, competency dictionary, rubric, and development plan
3. Present the final summary to the user

Execution Modes by Request Scope

Leveraging Existing Data: If the user provides existing job descriptions or competency frameworks, skip or augment the corresponding phase.

Data Transfer Protocol

File naming convention: {sequence}_{agent}_{deliverable}.{extension}

Error Handling

Test Scenarios

Normal Flow

Prompt: "Build a competency model for a backend developer role at an IT company. Include junior through senior levels." Expected Results:

• Job Analysis: Task analysis, KSA extraction, and NCS mapping for a backend developer
• Competency Dictionary: 10-12 competencies (technical + core), behavioral indicators across 5 proficiency levels
• Assessment Rubric: BARS-based scoring guide, BEI questions, SJT items
• Development Plan: Junior-to-senior growth path, 70:20:10 development activities
• Competency Matrix: Required level mapping by seniority

Partial Request Flow

Prompt: "Write a job description for our company's sales role. We are a mid-sized manufacturer." Expected Results:

• Job Analysis Mode (job-analyst solo)
• Manufacturing sales role job description + KSA extraction

Existing Data Flow

Prompt: "Create an assessment rubric based on this competency dictionary" + existing competency dictionary file Expected Results:

• Rubric Mode (rubric-designer solo)
• BARS scoring guide + evaluation tools based on the existing competency dictionary

Agent Extension Skills

Extension skills that enhance each agent's domain expertise: