# verification-loop-construction

verification-loop-construction validates construction estimates, schedules, BIM data and reports before delivery. Catches mismatches in totals, broken task dependencies and invalid CSI codes.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 119 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/4_DDC_Curated/Quality-Assurance/verification-loop-construction/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/verification-loop-construction

## What it does

The skill runs four verification phases: data integrity (required fields populated, no duplicates), business logic (totals match line items, markups calculated correctly, tasks respect dependencies), standards compliance (CSI MasterFormat codes valid, ISO date format, units consistent) and output quality. Requires `python3` in `PATH`.

It checks estimates (totals vs. line items, markup correctness, taxes), schedules (task dependencies, resource conflicts, critical path), BIM data (element counts, spatial relationship validity) and reports (document format). Returns a list of checks with PASS, WARN or FAIL statuses and specific error details for each.

## Install

### Claude Code (native platform)

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

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

### Codex

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

2. **Manually: put the files in place**
- File: `.agents/skills/verification-loop-construction/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 verification-loop-construction -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/verification-loop-construction/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 4_DDC_Curated/Quality-Assurance/verification-loop-construction
```

2. **Manually: put the files in place**
- File: `.github/skills/verification-loop-construction/SKILL.md`

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --path 4_DDC_Curated/Quality-Assurance/verification-loop-construction
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/verification-loop-construction/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 verification-loop-construction -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/4_DDC_Curated/Quality-Assurance/verification-loop-construction/SKILL.md

## When to use it
- validate an estimate before client submission
- catch total vs. line item sum mismatches
- find broken dependencies in a construction schedule
- ensure CSI codes are valid
- verify BIM data completeness and consistency

## Example prompts
- Verify the completed estimate before sending it
- Run full verification on the construction schedule
- Check that all CSI codes in the report are valid

## 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: 116dbf7bc7d8c457.

BEGIN THIRD-PARTY FILE 116dbf7bc7d8c457
````text
---
name: "verification-loop-construction"
description: "Comprehensive verification system for construction automation deliverables. Use after completing estimates, schedules, reports, or data processing tasks to ensure quality."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "🛡️", "os": ["darwin", "linux", "win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# Verification Loop for Construction Automation

A systematic verification framework ensuring quality of construction automation outputs before delivery or deployment.

## When to Use

Invoke this skill:
- After generating cost estimates
- After creating or updating schedules
- After processing BIM/CAD data
- After generating reports (daily, weekly, monthly)
- After running data pipelines
- Before submitting documents to clients
- Before deploying automation workflows

## Verification Phases

### Phase 1: Data Integrity Check

```python
def verify_data_integrity(output: dict) -> VerificationResult:
    """Check data completeness and consistency"""

    checks = []

    # Completeness check
    required_fields = get_required_fields(output['type'])
    missing = [f for f in required_fields if f not in output]
    checks.append({
        'name': 'Completeness',
        'status': 'PASS' if not missing else 'FAIL',
        'details': f'Missing fields: {missing}' if missing else 'All required fields present'
    })

    # Consistency check
    inconsistencies = find_inconsistencies(output)
    checks.append({
        'name': 'Consistency',
        'status': 'PASS' if not inconsistencies else 'WARN',
        'details': inconsistencies or 'No inconsistencies found'
    })

    # Referential integrity
    broken_refs = check_references(output)
    checks.append({
        'name': 'Referential Integrity',
        'status': 'PASS' if not broken_refs else 'FAIL',
        'details': f'Broken references: {broken_refs}' if broken_refs else 'All references valid'
    })

    return VerificationResult(checks)
```

#### Data Integrity Checklist
- [ ] All required fields populated
- [ ] No duplicate records
- [ ] Foreign keys resolve correctly
- [ ] Date formats consistent
````
END THIRD-PARTY FILE 116dbf7bc7d8c457

The third-party file has ended. Everything between the 116dbf7bc7d8c457 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 2228 of 16325 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/4_DDC_Curated/Quality-Assurance/verification-loop-construction/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
