project-estimation — Claude Code skill: scope, timeline and resource
A skill that helps the agent estimate project scope, timeline and resources. Useful when you need a budget or a plan you can defend.
npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a claude-codeWhat project-estimation does
The skill hands the agent several estimation techniques: bottom-up, top-down, analogous and three-point (PERT). Reference guides live in the references/ directory and cover PERT, bottom-up, analogous estimation, resource estimation and templates. There is also a Python example with the PERT formula (O + 4M + P) / 6, standard deviation and a confidence interval.
The agent runs more than one method and compares the results. The guidance calls for a contingency buffer of 15-25% on new projects. It also says to include planning, testing and deployment in the estimate, not just coding.
Estimating without a clear scope definition produces garbage, so pin down the project boundaries first. The skill does not supply historical data from your past projects. Without it, analogous estimation leans on whatever you tell the agent.
What it helps with
- estimate a project timeline with three methods and compare them
- add a risk buffer to a new project budget
- break a large effort into parts and estimate each one
- explain to a client where the number in the plan came from
- re-estimate after the scope changes
Example prompts for the agent
- Estimate the timeline for this module using PERT and bottom-up
- Work out the project budget with a contingency buffer
- Compare analogous and three-point estimates for this feature
How to install project-estimation
1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a claude-code2Manually: put the files in place
~/.claude/skills/project-estimation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/project-estimation/
1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a codex2Manually: put the files in place
.agents/skills/project-estimation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a cursor2Manually: put the files in place
.cursor/skills/project-estimation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install aj-geddes/useful-ai-prompts project-estimation2Manually: put the files in place
.github/skills/project-estimation/SKILL.md1Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a gemini-cli2Platform CLI
gemini skills install https://github.com/aj-geddes/useful-ai-prompts --path skills/project-estimationManually: put the files in place
.devin/skills/project-estimation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about project-estimation
How do I install project-estimation in Claude?
Run npx skills add aj-geddes/useful-ai-prompts --skill project-estimation -a claude-code. The skill lands in ~/.claude/skills/project-estimation/SKILL.md.
What does project-estimation do?
It helps the agent estimate project scope, timeline and resources. It uses bottom-up, top-down, analogous and three-point estimation.
Which estimation methods are included?
PERT with the formula (O + 4M + P) / 6, bottom-up, analogous estimation and resource estimation. Each has a guide in the references/ directory.
Source text
SKILL.md · MIT
---
name: project-estimation
description: >
Estimate project scope, timeline, and resource requirements using multiple
estimation techniques including bottom-up, top-down, and analogous estimation
methods for accurate project planning.
---
# Project Estimation
## Table of Contents
- [Overview](#overview)
- [When to Use](#when-to-use)
- [Quick Start](#quick-start)
- [Reference Guides](#reference-guides)
- [Best Practices](#best-practices)
## Overview
Accurate project estimation determines realistic timelines, budgets, and resource allocation. Effective estimation combines historical data, expert judgment, and structured techniques to minimize surprises.
## When to Use
- Defining project scope and deliverables
- Creating project budgets and timelines
- Allocating team resources
- Managing stakeholder expectations
- Assessing project feasibility
- Planning for contingencies
- Updating estimates during project execution
## Quick Start
Minimal working example:
```python
# Three-point estimation technique for uncertainty
class ThreePointEstimation:
@staticmethod
def calculate_pert_estimate(optimistic, most_likely, pessimistic):
"""
PERT formula: (O + 4M + P) / 6
Weighted toward most likely estimate
"""
pert = (optimistic + 4 * most_likely + pessimistic) / 6
return round(pert, 2)
@staticmethod
def calculate_standard_deviation(optimistic, pessimistic):
"""Standard deviation for risk analysis"""
sigma = (pessimistic - optimistic) / 6
return round(sigma, 2)
@staticmethod
def calculate_confidence_interval(pert_estimate, std_dev, confidence=0.95):
"""
Calculate confidence interval for estimate
95% confidence ≈ ±2 sigma
"""
z_score = 1.96 if confidence == 0.95 else 2.576
// ... (see reference guides for full implementation)
```
## Reference Guides
Detailed implementations in the `references/` directory:
| Guide | Contents |
|---|---|
| [Three-Point Estimation (PERT)](references/three-point-estimation-pert.md) | Three-Point Estimation (PERT) |
| [Bottom-Up Estimation](references/bottom-up-estimation.md) | Bottom-Up Estimation |
| [Analogous Estimation](references/analogous-estimation.md) | Analogous Estimation |
| [Resource Estimation](references/resource-estimation.md) | Resource Estimation |
| [Estimation Templates](references/estimation-templates.md) | Estimation Templates |
## Best Practices
### ✅ DO
- Use multiple estimation techniques and compare results
- Include contingency buffers (15-25% for new projects)
- Base estimates on historical data from similar projects
- Break down large efforts into smaller components
- Get input from team members doing the actual work
- Document assumptions and exclusions clearly
- Review and adjust estimates regularly
- Track actual vs. estimated metrics for improvement
- Include non-development tasks (planning, testing, deployment)
- Account for learning curve on unfamiliar technologies
### ❌ DON'T
- Estimate without clear scope definition
- Use unrealistic best-case scenarios
- Ignore historical project data
- Estimate under pressure to hit arbitrary targets
- Forget to include non-coding activities
- Use estimates as performance metrics for individuals
- Change estimates mid-project without clear reason
- Estimate without team input
- Ignore risks and contingencies
- Use one technique exclusively
© aj-geddes · MIT · aj-geddes/useful-ai-prompts