# productivity-analyzer

productivity-analyzer — a skill for Claude Code analyzes labor output rates using jobsite progress logs. Compares planned against actual progress and detects efficiency trends.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 115 installs · ★ 434 repo stars
- Author: datadrivenconstruction
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/Analytics/productivity-analyzer/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/productivity-analyzer

## What it does

This skill processes field logs containing actual output, manhours, crew sizes, and site conditions. It computes unit rates per manhour, benchmarks them against planned targets, and flags tasks with statuses ranging from critical (under 70% efficiency) to excellent (over 110%).

The underlying Python module includes baseline metrics for common construction trades like concrete pouring, rebar placement, formwork, bricklaying, drywall, painting, and trenching. When at least three shift entries exist for an activity code, it splits historical data into intervals to detect whether efficiency is rising, dropping, or holding steady.

Execution relies on local `python3` along with `pandas` and `numpy`. Data can be loaded directly from dataframes or appended entry by entry.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill productivity-analyzer -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/productivity-analyzer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/productivity-analyzer/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill productivity-analyzer -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/productivity-analyzer/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill productivity-analyzer -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/productivity-analyzer/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction 1_DDC_Toolkit/Analytics/productivity-analyzer
```

2. **Manually: put the files in place**
- File: `.github/skills/productivity-analyzer/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill productivity-analyzer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --path 1_DDC_Toolkit/Analytics/productivity-analyzer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/productivity-analyzer/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill productivity-analyzer -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/Analytics/productivity-analyzer/SKILL.md

## When to use it
- benchmark crew output rates against planned targets
- flag lagging construction tasks operating below 70% efficiency
- detect productivity trends across consecutive site shifts
- compare concrete or rebar installation speeds against industry baselines

## Example prompts
- Analyze crew productivity for activity code concrete_pour using our shift log
- Check whether rebar installation output is improving or declining this month
- Evaluate all site activities and list everything marked with critical status

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 54d12c94464aa38d.

BEGIN THIRD-PARTY FILE 54d12c94464aa38d
````text
---
name: "productivity-analyzer"
description: "Analyze labor productivity from site data. Compare planned vs actual, identify trends, benchmark against industry standards."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "📊", "os": ["darwin", "linux", "win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# Productivity Analyzer

## Business Case

### Problem Statement
Understanding productivity requires:
- Tracking actual output rates
- Comparing to planned rates
- Identifying problem areas
- Forecasting project completion

### Solution
Analyze labor productivity data to identify trends, compare to benchmarks, and provide actionable insights.

## Technical Implementation

```python
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional
from dataclasses import dataclass
from datetime import date, timedelta
from enum import Enum


class ProductivityStatus(Enum):
    EXCELLENT = "excellent"    # >110% of planned
    ON_TARGET = "on_target"    # 90-110%
    BELOW = "below"            # 70-90%
    CRITICAL = "critical"      # <70%


@dataclass
class ProductivityRecord:
    date: date
    activity_code: str
    description: str
    planned_output: float
    actual_output: float
    unit: str
    manhours: float
    crew_size: int
    conditions: str  # weather, access issues


@dataclass
class ProductivityAnalysis:
    activity_code: str
    description: str
    total_planned: float
    total_actual: float
    total_manhours: float
    planned_rate: float  # unit per manhour
    actual_rate: float
    efficiency: float  # percentage
    status: ProductivityStatus
    trend: str  # improving, declining, stable


class ProductivityAnalyzer:
    """Analyze construction productivity data."""

    # Industry benchmark rates (unit per manhour)
    BENCHMARKS = {
        'concrete_pour': 0.5,      # m3/MH
        'rebar_install': 15,       # kg/MH
        'formwork': 0.8,           # m2/MH
        'brick_laying': 35,        # bricks/MH
        'drywall': 1.5,            # m2/MH
        'painting': 3.0,           # m2/MH
        'conduit': 8,              # m/MH
````
END THIRD-PARTY FILE 54d12c94464aa38d

The third-party file has ended. Everything between the 54d12c94464aa38d tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2193 of 12957 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/Analytics/productivity-analyzer/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
