Install any skill in seconds. Free to start, no credit card required.
Get Started Free →datadrivenconstruction/retention-tracker
Track construction retainage/retention amounts. Monitor held amounts by subcontractor, track release conditions, and manage retainage billing.
Passed 21 of 21 test cases with the skill, and 12 of 21 without it.
and 10 more in the full report
9 fixed13 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Electrical Trade Services had $15,000 in balance held after partial release. At final completion, we disburse the full remaining $15,000 balance. What status is assigned to Electrical Trade Services once the balance held reaches zero?
| Checked | Without skill | With skill |
|---|---|---|
| The final status is released. | Missed | Passed |
The instructions your model reads when the skill loads.
Track retainage (retention) amounts held and released throughout construction projects. Monitor amounts by subcontractor, track release milestones, and ensure proper documentation for retention release.
┌─────────────────────────────────────────────────────────────────┐
│ RETAINAGE LIFECYCLE │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Progress Billing → Substantial → Final Release │
│ ──────────────── ─────────── ───────────── │
│ 10% withheld 50% released 50% released │
│ Each pay app At punch list At final │
│ Cumulative completion completion │
│ │
│ Owner holds from GC → GC holds from subs → Flow-down │
│ │
└─────────────────────────────────────────────────────────────────┘
from dataclasses import dataclass, field
from typing import List, Dict, Optional
from datetime import datetime, timedelta
from enum import Enum
class RetentionStatus(Enum):
HELD = "held"
PARTIAL_RELEASE = "partial_release"
PENDING_RELEASE = "pending_release"
RELEASED = "released"
class ReleaseMilestone(Enum):
SUBSTANTIAL_COMPLETION = "substantial_completion"
test cases passed, vs 12 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.