plan-estimateeffort

name: plan-estimateeffort description: Provides effort estimates for development tasks using multiple estimation methods including PERT, complexity analysis, and risk factors. Generates estimates with confidence levels and rationale for structured project planning. license: MIT

Plan.EstimateEffort Skill

Intent

Generate accurate effort estimates for development tasks using multiple estimation methodologies (PERT, complexity analysis, historical analogies) with confidence intervals and detailed rationale to support project planning and resource allocation decisions.

Inputs

Source: projects/[project-name]/artifacts/Analysis/task-breakdown.json (generated by plan-derivetasks skill)
Optional: Historical project data or team velocity metrics from previous projects
Format: Structured task data with descriptions, acceptance criteria, and dependencies

Outputs

Files Generated:

projects/[project-name]/artifacts/Analysis/effort-estimates.json - Structured estimation data for programmatic use
projects/[project-name]/artifacts/Analysis/effort-estimates.md - Human-readable estimation report with rationale
projects/[project-name]/artifacts/Analysis/estimation-confidence.md - Confidence analysis and calibration info

JSON Structure (`effort-estimates.json`)

{
  "project_id": "string",
  "generated_at": "ISO_timestamp",
  "estimation_methods": ["PERT", "complexity-points", "analogies"],
  "total_project_estimate": {
    "optimistic_days": 0.0,
    "most_likely_days": 0.0,
    "pessimistic_days": 0.0,
    "expected_days": 0.0,
    "standard_deviation": 0.0,
    "confidence_interval_80": {"min": 0.0, "max": 0.0},
    "confidence_interval_95": {"min": 0.0, "max": 0.0}
  },
  "estimation_factors": {
    "team_experience": "novice|intermediate|expert",
    "technology_familiarity": "new|familiar|expert", 
    "project_complexity": "simple|moderate|complex|very_complex",
    "requirements_clarity": "clear|moderate|unclear",
    "integration_complexity": "simple|moderate|complex"
  },
  "task_estimates": [
    {
      "task_id": "string",
      "title": "string",
      "category": "string",
      "pert_estimate": {
        "optimistic_days": 0.0,
        "most_likely_days": 0.0,
        "pessimistic_days": 0.0,
        "expected_days": 0.0,
        "variance": 0.0
      },
      "complexity_factors": {
        "technical_complexity": "1-5_scale",
        "business_logic_complexity": "1-5_scale",
        "integration_complexity": "1-5_scale",
        "uncertainty_factor": "1-5_scale",
        "total_story_points": 0
      },
      "risk_factors": [
        {
          "risk": "string",
          "impact": "low|medium|high",
          "probability": "low|medium|high",
          "effort_multiplier": 0.0
        }
      ],
      "historical_analogies": [
        {
          "similar_task": "string",
          "similarity_score": "0.0-1.0",
          "actual_effort": 0.0,
          "adjusted_estimate": 0.0
        }
      ],
      "confidence_level": "0-100_percent",
      "rationale": "string",
      "estimation_notes": ["string_list"]
    }
  ],
  "summary_statistics": {
    "total_tasks": 0,
    "tasks_by_category": {
      "development": {"count": 0, "total_effort": 0.0},
      "testing": {"count": 0, "total_effort": 0.0},
      "design": {"count": 0, "total_effort": 0.0},
      "documentation": {"count": 0, "total_effort": 0.0}
    },
    "critical_path_effort": 0.0,
    "parallel_work_potential": 0.0
  }
}

Markdown Structure (`effort-estimates.md`)

# Project Effort Estimates

## Executive Summary
- **Total Expected Effort**: [expected_days] days
- **Confidence Range (80%)**: [min_days] - [max_days] days  
- **Critical Path**: [critical_path_days] days
- **Estimation Approach**: PERT + Complexity + Risk Analysis

## Estimation Context
- **Team Experience**: [experience_level]
- **Technology Stack**: [familiarity_level]
- **Project Complexity**: [complexity_level]
- **Requirements Certainty**: [clarity_level]

## Task Estimates Detail
[Individual task breakdown with rationale]

## Risk Factors & Mitigation
[Risk analysis affecting estimates]

## Estimation Methodology
[Documentation of estimation approach]

## Confidence Analysis
[Discussion of estimate reliability]

Core Estimation Methods

1. PERT (Program Evaluation and Review Technique)

Apply three-point estimation for each task:

Optimistic (O): Best case scenario, everything goes well
Most Likely (M): Realistic estimate based on normal conditions
Pessimistic (P): Worst case with reasonable risks materialized

Formulas:

Expected Time: E = (O + 4M + P) / 6
Variance: V = ((P - O) / 6)²
Standard Deviation: SD = √V

2. Complexity Point Estimation

Assess each task on multiple complexity dimensions (1-5 scale):

Technical Complexity: Algorithm complexity, technical challenges
Business Logic: Domain complexity, rule complexity
Integration Complexity: API dependencies, data flow complexity
Uncertainty Factor: Requirements clarity, unknowns

Calculation:

Story Points = (Technical + Business + Integration + Uncertainty) / 4
Base Effort = Story Points * Team Velocity (days per point)

3. Historical Analogy Method

Compare tasks to historical similar work:

Identify analogous tasks from previous projects
Calculate similarity scores (0.0-1.0) based on:
- Technology similarity
- Complexity similarity
- Team experience similarity
Adjust historical effort based on differences

4. Risk Factor Adjustment

Apply effort multipliers based on identified risks:

Risk Multiplier = 1.0 + (Risk_Impact * Risk_Probability * Base_Multiplier)

Common Risk Factors:
- New technology: 1.2-1.5x multiplier
- External dependencies: 1.1-1.3x multiplier  
- Unclear requirements: 1.3-1.8x multiplier
- Integration complexity: 1.1-1.4x multiplier
- Team inexperience: 1.2-2.0x multiplier

Estimation Algorithm

Step 1: Task Analysis

For each task from task-breakdown.json:

Analyze task description and acceptance criteria
Identify complexity factors and assign scores
Identify potential risks and their impacts
Search for historical analogies

Step 2: Base Estimation

Generate PERT estimates (O, M, P) for each task
Calculate complexity-based story points
Apply analogy-based adjustments

Step 3: Risk Adjustment

Apply risk multipliers to base estimates
Aggregate risk impacts across dependent tasks
Calculate confidence levels based on uncertainty

Step 4: Project-Level Aggregation

Sum individual task estimates
Calculate critical path effort
Identify opportunities for parallel work
Generate confidence intervals for total project

Step 5: Calibration & Validation

Cross-check estimates against industry benchmarks
Validate against team historical performance
Flag estimates outside reasonable bounds
Document assumptions and limitation

Confidence Level Calculation

Confidence = 100 - (Uncertainty_Score * Risk_Score)

Where:
- Uncertainty_Score (0-50): Based on requirements clarity and task definition
- Risk_Score (0-50): Based on identified risks and their probabilities

Confidence Levels:
- 90-100%: High confidence, well-defined tasks, low risk
- 70-89%: Medium confidence, some unknowns or moderate risks  
- 50-69%: Low confidence, significant uncertainties or high risks
- <50%: Very low confidence, requires further analysis

Quality Assurance

Estimation Validation Rules

Sanity Checks:
- No task < 0.25 days (too granular) or > 10 days (needs breakdown)
- PERT pessimistic should be 1.5-3x optimistic
- Total variance should align with project complexity
Consistency Checks:
- Similar complexity tasks have similar estimates
- Dependencies reflect in estimate sequences
- Category totals align with typical project distributions
Calibration Monitoring:
- Track actual vs. estimated effort over time
- Maintain team velocity and complexity factor calibration
- Update risk multipliers based on historical outcomes

Usage Guidelines

When to Use This Skill

After tasks have been derived from requirements (plan-derivetasks)
Before project scheduling and resource planning
When multiple estimation methods needed for accuracy
For projects requiring confidence intervals and risk assessment

Best Practices

Input Quality: Ensure task descriptions are detailed and acceptance criteria clear
Team Calibration: Adjust complexity factors based on team experience and technology familiarity
Historical Data: Leverage previous project data when available for analogy-based estimation
Risk Assessment: Include both technical and non-technical risks in analysis
Iterative Refinement: Update estimates as project progresses and uncertainties resolve

Common Applications

Project proposal effort estimation
Sprint planning and capacity allocation
Risk analysis and contingency planning
Resource planning and team sizing
Client estimation and contract scoping

Expert Patterns

Technology-Specific Multipliers

Web Development:
- Frontend (React/Vue): Base multiplier 1.0
- Backend API: Base multiplier 1.1  
- Database design: Base multiplier 1.2
- Authentication/Security: Base multiplier 1.3

Mobile Development:
- Native iOS/Android: Base multiplier 1.2
- Cross-platform: Base multiplier 1.4
- Device integration: Base multiplier 1.5

Data/ML Projects:  
- Data pipeline: Base multiplier 1.3
- Model development: Base multiplier 1.5
- MLOps deployment: Base multiplier 1.7

Team Experience Adjustments

Expert Team (5+ years): 0.7-0.8x multiplier
Experienced Team (3-5 years): 0.9-1.0x multiplier  
Intermediate Team (1-3 years): 1.1-1.3x multiplier
Novice Team (<1 year): 1.5-2.0x multiplier

This skill provides comprehensive effort estimation that balances analytical rigor with practical applicability, supporting data-driven project planning decisions.

name: plan-estimateeffort description: Provides effort estimates for development tasks using multiple estimation methods including PERT, complexity analysis, and risk factors. Generates estimates with confidence levels and rationale for structured project planning. license: MIT