Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
repair-or-replace
Try itDecide whether to fix, replace, or recycle a broken item. Takes item type, age, symptoms, and repair estimate, then produces a scored recommendation across cost, lifespan, sentimental value, and environmental impact.
What it does
is a skill that helps you decide whether to fix a broken item, buy a replacement, or recycle it. It builds a weighted decision matrix across five factors — repair cost, replacement cost, remaining lifespan, sentimental value, and environmental impact — then outputs a clear, score-backed recommendat…
The skill document
Repair or Replace
Don't guess. Score it.
Repair or Replace is a skill that helps you decide whether to fix a broken
item, buy a replacement, or recycle it. It builds a weighted decision matrix
across five factors — repair cost, replacement cost, remaining lifespan,
sentimental value, and environmental impact — then outputs a clear,
score-backed recommendation with reasoning.
When to Use
Activate this skill when:
- An appliance, device, or tool is broken and you're unsure whether to fix it
- You have a repair estimate and want to compare it against replacement
- You want to factor environmental impact into a purchasing decision
- You're helping someone else decide what to do with a broken item
- You want a structured, defensible decision rather than a gut call
How It Works
The script takes structured input about the item and its condition:
| Parameter | Description | Example |
|---|---|---|
--item | What the item is | "washing machine" |
--age | How old it is (years) | 8 |
--repair-cost | Estimated repair cost | 250 |
--replacement-cost | Cost of a new equivalent | 800 |
--expected-lifespan | Expected total lifespan of this item type (years) | 12 |
--symptoms | What's wrong (free text) | "won't spin" |
--sentimental | Sentimental value (1-10) | 3 |
--condition | Overall condition aside from the fault (1-10) | 6 |
It then scores the decision across five dimensions, applies weights, and produces a recommendation: Repair, Replace, or Recycle/Donate.
Decision Matrix
| Factor | Weight | Repair Favors | Replace Favors |
|---|---|---|---|
| Cost Ratio | 30% | Repair < 50% of replacement | Repair > 50% of replacement |
| Remaining Life | 25% | <50% of expected lifespan used | >50% of expected lifespan used |
| Condition | 15% | Good condition otherwise | Multiple issues, poor condition |
| Sentimental | 10% | High sentimental value | Low sentimental value |
| Environmental | 20% | Repair avoids e-waste | New item is more efficient |
See references/decision-matrix.md for the full scoring algorithm.
Quick Reference
| Need | Command |
|---|---|
| Basic decision | python3 scripts/repair_or_replace.py --item "laptop" --age 5 --repair-cost 300 --replacement-cost 1000 |
| With symptoms and condition | python3 scripts/repair_or_replace.py --item "fridge" --age 10 --repair-cost 200 --replacement-cost 900 --symptoms "not cooling" --condition 4 |
| Factor in sentiment | python3 scripts/repair_or_replace.py --item "watch" --age 20 --repair-cost 150 --replacement-cost 500 --sentimental 9 |
| JSON output | python3 scripts/repair_or_replace.py ... --format json |
| Interactive mode | python3 scripts/repair_or_replace.py --interactive |
Recommendations
The script outputs one of three recommendations:
- Repair — the item is worth fixing. Cost-effective, has remaining lifespan, or has sentimental/environmental value.
- Replace — buying new is the better choice. Repair cost is too high relative to replacement, or the item is near end-of-life.
- Recycle/Donate — the item is beyond economic repair. Dispose of it responsibly or donate if still partially functional.
Each recommendation includes a confidence score (0-100) and itemized reasoning.
Files
references/decision-matrix.md— full scoring algorithm and weight rationalereferences/item-lifespans.md— expected lifespan data for common itemsreferences/environmental-impact.md— e-waste and sustainability considerationsscripts/repair_or_replace.py— the main decision enginescripts/sample_run.sh— example invocations for different item types
Common Pitfalls
-
Ignoring hidden repair costs. The repair estimate often excludes diagnosis fees, shipping, or secondary issues discovered during repair. Add 15-20% to the estimate for a realistic comparison.
-
Overestimating remaining lifespan. An 8-year-old washing machine with a 12-year expected lifespan doesn't have 4 "good" years left — the last quarter of lifespan tends to have escalating failure rates.
-
Forgetting energy efficiency. A new appliance may be significantly more energy-efficient, saving money over time. Factor this into the replacement cost (see
references/environmental-impact.md). -
Sentimental bias. It's easy to over-value items with emotional attachment. Be honest with the
--sentimentalscore. -
Not considering safety. Some failures (gas appliances, electrical) carry safety risks if repaired poorly. If in doubt, replace.
Verification Checklist
- Repair estimate is realistic (includes diagnosis, parts, labor)
- Replacement cost reflects a comparable-quality item
- Expected lifespan matches the item type (see
references/item-lifespans.md) - Condition score accounts for wear beyond the current fault
- Environmental factor considered (especially for large appliances)
License
MIT © Denis Voronin
Related skills
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
Site audit, content writing, and competitor analysis for organic search rankings.
More from voronindenis5
Browse all skillsPryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, t...
Prepare salary negotiations with a structured toolkit: market-rate anchoring math, walk-away floor calculation, total-compensation evaluation (equity, bonuses, benefits), negotiation scripts for offers, raises, and counter-offers, and BATNA analysis. Use when the user has a job offer, is preparing a raise conversation, wants to know if their pay is competitive, or needs scripts and a strategy for negotiating compensation.
Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.
Use when you realize your photos/code/documents exist in exactly one place (or your 'backup' is a external drive in the same room as the computer) — audits your actual data-loss risk against the 3-2-1 rule (3 copies, 2 media, 1 offsite) asset by asset, scores blast radius (ransomware encrypts synced copies too), prices honest recovery (professional recovery lab $300-3000 vs $0), generates the minimum-cost redundancy plan for YOUR asset list, and produces a restore-test drill because an untested backup is a hope, not a backup.
Audit password vault exports (Bitwarden, 1Password, KeePass, Chrome, Firefox) for reuse, weakness, staleness, breach exposure, and 2FA gaps without ever storing or transmitting a plaintext password. Use when the user asks to audit passwords, check password strength/reuse, review vault health, or verify whether credentials appeared in breaches.
Use before any difficult phone call you're anxious about or that has stakes — calling customer service to dispute a fee, negotiating a bill, cold-calling a client, delivering bad news to a vendor, calling a landlord about repairs, insurance disputes, or handling collections calls — builds a branching call script from your situation (goal, leverage, fallback), generates objection→response trees for the specific counter-arguments you'll hear, produces a one-page printable cheat sheet, and includes a practice-drills mode that plays the other side and scores your responses.