Spark
Sign In
Skill

Estimate AI-assisted Development Work Accurately

Statistical estimation skill for AI-assisted development using PERT formulas, confidence intervals, and calibration feedback for hybrid human+agent teams.

Get skill
Works with jiralinearclickupgithubmonday
Antigravity
Maintainer?
46
Spark score
out of 100
Updated yesterday
Version 13.1.0
Add to Favorites

Why it matters

Leverage research-backed formulas and PERT statistics to generate accurate, confidence-banded estimates for AI-assisted and hybrid human+agent development tasks.

Outcomes

What it gets done

01

Determine team working mode (human-only, hybrid, agent-first).

02

Classify tasks by size, complexity, and risk.

03

Apply research-backed multipliers and PERT calculations for statistical estimates.

04

Generate P50, P75, and P90 confidence intervals for release forecasting.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-progressive-estimation | bash

Capabilities

What this skill does

Classify

Labels or categorizes text, files, or data points.

Summarize

Condenses long documents or threads into key takeaways.

Review code

Analyzes code for bugs, style issues, and improvements.

Write tests

Creates unit, integration, or end-to-end test cases.

Overview

Progressive Estimation

What it does

Progressive Estimation produces statistical estimates for development work using PERT three-point estimation, confidence bands, and calibration feedback loops. It adapts to human-only, hybrid, or agent-first working modes by applying research-backed velocity multipliers and empirical formulas. The skill classifies tasks by size and complexity, calculates expected values with P50/P75/P90 confidence intervals, and formats output for project management tools including Linear, JIRA, ClickUp, GitHub Issues, Monday, and GitLab.

How it connects

Use this skill when estimating development tasks where AI agents handle part of the work, planning sprints with hybrid human+agent teams, batch sizing backlogs of 5 to 500 issues, conducting staffing and capacity planning with agent multipliers, or forecasting release dates with confidence intervals. Start with single-task calibration before moving to batch mode, and re-calibrate when team composition or tooling changes significantly.

Source README

Progressive Estimation

Estimate AI-assisted and hybrid human+agent development work using research-backed formulas with PERT statistics, confidence bands, and calibration feedback loops.

Overview

Progressive Estimation adapts to your team's working mode - human-only, hybrid, or agent-first - applying the right velocity model and multipliers for each. It produces statistical estimates rather than gut feelings.

When to Use This Skill

  • Estimating development tasks where AI agents handle part of the work
  • Sprint planning with hybrid human+agent teams
  • Batch sizing a backlog (handles 5 or 500 issues)
  • Staffing and capacity planning with agent multipliers
  • Release date forecasting with confidence intervals

How It Works

  1. Mode Detection - Determines if the team works human-only, hybrid, or agent-first
  2. Task Classification - Categorizes by size (XS-XL), complexity, and risk
  3. Formula Application - Applies research-backed multipliers grounded in empirical studies
  4. PERT Calculation - Produces expected values using three-point estimation
  5. Confidence Bands - Generates P50, P75, P90 intervals
  6. Output Formatting - Formats for Linear, JIRA, ClickUp, GitHub Issues, Monday, or GitLab
  7. Calibration - Feeds back actuals to improve future estimates

Examples

Single task:

"Estimate building a REST API with authentication using Claude Code"

Batch mode:

"Estimate these 12 JIRA tickets for our next sprint"

With context:

"We have 3 developers using AI agents for ~60% of implementation. Estimate this feature."

Best Practices

  • Start with a single task to calibrate before moving to batch mode
  • Feed back actual completion times to improve the calibration system
  • Use "instant mode" for quick T-shirt sizing without full PERT analysis
  • Be explicit about team composition and agent usage percentage

Common Pitfalls

  • Problem: Overconfident estimates
    Solution: Use P75 or P90 for commitments, not P50

  • Problem: Missing context
    Solution: The skill asks clarifying questions - provide team size and agent usage

  • Problem: Stale calibration
    Solution: Re-calibrate when team composition or tooling changes significantly

Related Skills

  • @sprint-planning - Sprint planning and backlog management
  • @project-management - General project management workflows
  • @capacity-planning - Team velocity and capacity planning

Additional Resources

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.