# cwicr-bid-analyzer

cwicr-bid-analyzer compares contractor pricing against CWICR benchmarks to spot cost anomalies. Helps evaluate bids and flag unbalanced line items.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 117 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/CWICR-Database/cwicr-bid-analyzer/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/cwicr-bid-analyzer

## What it does

The skill checks contractor line items against the CWICR cost benchmark. It tallies benchmark rates by combining labor, material, and equipment expenses for each work item code. Individual rates then receive variance scores and categorical flags, sorting standard pricing from low or excessive unit costs.

When item variations exceed predefined boundaries, the analyzer flags them for review. A submission enters review status if extreme rate variances affect more than a tenth of all lines, or if the aggregate bid total deviates from the reference total by over thirty percent. This mechanism pinpoints front-loading and inflated pricing before contracts are awarded.

Execution relies on Python 3 with pandas and numpy packages installed. The benchmark table must contain matching work item codes, otherwise the analyzer falls back to the submitted rate without running comparative checks.

## Install

### Claude Code (native platform)

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

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

### Codex

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

2. **Manually: put the files in place**
- File: `.agents/skills/cwicr-bid-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 cwicr-bid-analyzer -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/cwicr-bid-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/CWICR-Database/cwicr-bid-analyzer
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill cwicr-bid-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/CWICR-Database/cwicr-bid-analyzer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/cwicr-bid-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 cwicr-bid-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/CWICR-Database/cwicr-bid-analyzer/SKILL.md

## When to use it
- evaluate contractor unit rates against CWICR benchmarks
- detect front-loading and artificially low line items
- flag excessive material or labor markups across bids
- produce structured bid review summaries for procurement records

## Example prompts
- Analyze contractor bids in `bid_data.csv` against CWICR reference rates.
- Check the submitted bid items for abnormal variances and highlight flagged rates.
- Compare multiple contractor proposals against the project benchmark total.

## 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: 1ec09b7349b51a54.

BEGIN THIRD-PARTY FILE 1ec09b7349b51a54
````text
---
name: "cwicr-bid-analyzer"
description: "Analyze contractor bids against CWICR benchmarks. Identify pricing anomalies, compare bid components, and support bid evaluation decisions."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "🗄️", "os": ["darwin", "linux", "win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# CWICR Bid Analyzer

## Business Case

### Problem Statement
Evaluating contractor bids requires:
- Comparing against market benchmarks
- Identifying unusual pricing
- Understanding cost composition
- Documenting evaluation rationale

### Solution
Analyze contractor bids against CWICR-based benchmarks to identify anomalies, compare components, and support objective bid evaluation.

### Business Value
- **Objective evaluation** - Data-driven bid analysis
- **Risk identification** - Spot unrealistic pricing
- **Fair comparison** - Normalized bid analysis
- **Documentation** - Audit trail for decisions

## Technical Implementation

```python
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from datetime import datetime
from enum import Enum
from collections import defaultdict


class BidStatus(Enum):
    """Bid evaluation status."""
    COMPLIANT = "compliant"
    NON_COMPLIANT = "non_compliant"
    UNDER_REVIEW = "under_review"
    RECOMMENDED = "recommended"
    NOT_RECOMMENDED = "not_recommended"


class PriceFlag(Enum):
    """Price anomaly flags."""
    NORMAL = "normal"
    LOW = "low"              # >20% below benchmark
    HIGH = "high"            # >20% above benchmark
    VERY_LOW = "very_low"    # >40% below - potential front-loading
    VERY_HIGH = "very_high"  # >40% above - potential profiteering


@dataclass
class BidLineItem:
    """Single line item from bid."""
    item_code: str
    description: str
    quantity: float
    unit: str
    unit_rate: float
    total_price: float
    benchmark_rate: float
    benchmark_total: float
    variance_pct: float
    price_flag: PriceFlag


@dataclass
class BidAnalysis:
    """Complete bid analysis."""
````
END THIRD-PARTY FILE 1ec09b7349b51a54

The third-party file has ended. Everything between the 1ec09b7349b51a54 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 2168 of 15544 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/CWICR-Database/cwicr-bid-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
