诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
编程
car-maintenance-timeline
试用Use when the user asks what car maintenance is due or overdue, whether a service can wait, what a dealer 'recommended service' actually contains, or to build a maintenance schedule and budget from mileage, vehicle age, and service history. Computes dual-interval status (every N km OR M months, whichever first), applies a severe-service multiplier for city/short-trip/towing driving, projects a 24-month service timeline from annual mileage, and shows typical cost ranges and DIY difficulty so owners can challenge upselling.
它能做什么
"What's actually due on my car at 84,500 km?" Most owners answer this by guessing, ignoring it, or trusting a service advisor whose incentives are not aligned with their wallet. Result: missed safety services on one end, and $600 "premium packages" full of items that aren't due yet on the other.
技能文档
Car Maintenance Timeline 🔧
"What's actually due on my car at 84,500 km?" Most owners answer this by guessing, ignoring it, or trusting a service advisor whose incentives are not aligned with their wallet. Result: missed safety services on one end, and $600 "premium packages" full of items that aren't due yet on the other.
This skill treats the manufacturer maintenance schedule as what it is — a table of dual intervals (every N km OR M months, whichever comes first) — and computes, from your odometer, in-service date, and service history, what is genuinely OVERDUE, DUE SOON, or OK, what it typically costs, and how hard it is to do yourself.
Overview
One tool, three commands (scripts/car_maintenance.py):
tasks— the built-in task library: 13 generic services with km/month intervals, severe-service intervals, priority class (safety-critical / wear-item / standard), typical cost range, and DIY difficulty.status— per-task evaluation: last done (from--historyor in-service by default), km-due-at, date-due-at, status with reason string ("overdue by km (+2,400 km vs interval)"), sorted safety-critical and overdue first.--severeswitches to the severe-service column.--jsonfor agents.timeline— projects the next 24 months of services by extrapolating the odometer from annual mileage (explicit--annual-kmor derived from km ÷ age), repeating recurring tasks across the window.
When to Use
- "Is my car due for a service? It's at 84,500 km."
- "The dealer says I need the 90k package — what's actually due?"
- "I mostly do short city trips — does that change the schedule?" (yes:
--severe) - "What will maintenance cost me over the next two years?"
- "I changed the oil at 63,000 km in January — when is the next one?"
Don't use for:
- Diagnosing symptoms (noises, warning lights, leaks) — that's a mechanic.
- Model-specific intervals — the library is generic; your owner's manual always overrides (see Pitfall #1).
- Warranty compliance tracking (needs dealer-documented service records).
Quick Start
# 1. See the task library
python3 scripts/car_maintenance.py tasks
# 2. What's due right now? (84,500 km, registered 2021-03-10, mostly city driving)
python3 scripts/car_maintenance.py status \
--km 84500 --in-service 2021-03-10 --severe
# 3. Same, but you know the oil was done at 63,000 km on 2026-01-15
python3 scripts/car_maintenance.py status --km 84500 --in-service 2021-03-10 \
--history '[{"task":"oil","km":63000,"date":"2026-01-15"}]' --severe
# 4. Budget the next 24 months (~15,000 km/yr)
python3 scripts/car_maintenance.py timeline \
--km 84500 --in-service 2021-03-10 --annual-km 15000
# 5. Machine-readable output for agents
python3 scripts/car_maintenance.py status --km 84500 \
--in-service 2021-03-10 --json
How It Works
Dual intervals (whichever comes first). A task is due at
last_done_km + interval_km OR last_done_date + interval_months, whichever
event arrives first. A 12,000 km/year car hits the oil change's 10,000 km
before its 12 months; a retired driver's 4,000 km/year car hits the 12 months
first. Both are "due" — mileage is a proxy for engine hours and heat cycles,
time for chemistry (oil oxidation, brake fluid hygroscopy, coolant
inhibitors).
Severe service. Short trips, city driving, towing, dust, and extreme heat
are the manufacturer-defined "severe" conditions. --severe switches tasks
to their severe intervals (oil 10,000→5,000 km; transmission fluid
100,000→60,000 km) or applies a global 0.75 multiplier where no specific
value exists. Most urban commuting qualifies — this is the single most
commonly missed adjustment.
Due-soon band. DUE SOON = within 20% of the km interval remaining, or
within 30 days of the time deadline. Anything beyond is OK.
No-history default. Without --history, the model assumes each task was
last done at in-service @ 0 km — i.e. never. On a used car with unknown
history this deliberately over-reports: baseline everything cheap (fluids,
filters) and move on. Feed real history entries (task, km, date) as you
learn them.
Projection. timeline converts annual mileage to km-per-day and walks
each task's next event forward, repeating recurring services across the
24-month window, giving each event an estimated odometer reading and cost
range — the basis of a realistic maintenance budget.
Task Library (generic defaults)
| Task | km | months | severe km | priority | Typical cost | DIY |
|---|---|---|---|---|---|---|
| Engine oil & filter | 10,000 | 12 | 5,000 | wear | $40–90 | Easy |
| Tire rotation | 8,000 | 6 | — | safety | $20–50 | Easy |
| Engine air filter | 20,000 | 24 | — | wear | $15–40 | Easy |
| Cabin filter | 20,000 | 24 | — | standard | $20–60 | Easy |
| Brake fluid | 40,000 | 24 | — | safety | $80–150 | Moderate |
| Spark plugs | 60,000 | 48 | — | wear | $100–250 | Moderate |
| Coolant | 100,000 then 50,000 | 60/36 | — | wear | $90–180 | Moderate |
| Transmission fluid | 100,000 | 120 | 60,000 | wear | $150–350 | Hard |
| Drive belt (inspect) | 100,000 | 120 | — | wear | $0–120 | Moderate |
| Battery test | — | 48 (replace ~60) | — | wear | $0–30 test | Easy |
| Wiper blades | — | 12 | — | safety | $15–50 | Easy |
| Annual inspection/MOT | — | 12 | — | safety | $30–120 | — |
| Winter/summer tire swap | — | 6 | — | standard | $40–100 | Moderate |
Values are rounded generic conventions, not a substitute for the book for your exact model.
Workflow
- Gather inputs: current odometer, in-service/first-registration date, any known service history (from receipts or the dealer's printout).
- Decide severe vs normal: any of short trips <10 km, mostly stop-and-go,
towing, dusty/unpaved roads, extreme heat →
--severe. - Run
status. Read OVERDUE safety-critical items first (tires, brake fluid, wipers, inspection) — those are the ones that bite. - Cross-check against the owner's manual; the manual wins where they differ.
- Feed real history entries as you collect them; the report sharpens.
- Run
timelineonce a year to budget; runstatusmonthly or before trips.
Common Pitfalls
- Trusting generic intervals over the owner's manual. Intervals vary by engine, transmission, and market. Use this tool to understand structure and challenge upselling; use the manual for the numbers.
- Ignoring severe service. "Severe" sounds exceptional but describes most city commuting. Running normal intervals on a severe-duty car is how sludge and transmission failures happen.
- Assuming time-based items don't matter on a low-mileage car. Oil, brake fluid, and coolant age by chemistry, not just km. A 5-year-old 30,000 km car is overdue for fluid services.
- Reading a giant OVERDUE list as a literal work order on a used car with unknown history. It's a "baseline it" signal, not 13 simultaneous failures. Prioritize safety-critical, then fluids.
- Accepting a dealer's bundled "package" at face value. Compare its
contents against
statusoutput; items listed as OK are profit, not maintenance. - Forgetting units. The tool is km-based. For miles, convert first (×1.609) — mixing units silently shifts every interval.
Verification Checklist
-
python3 scripts/car_maintenance.py tasksruns and prints the library -
statuswith your km/date prints a sorted table + summary counts -
--severevisibly shortens oil (10,000 → 5,000 km) intasks -
--historyentries shift the oil due-at km/date -
timelinecovers 24 months and repeats recurring tasks -
--jsonoutput parses (meta+taskskeys) -
python3 scripts/test_car_maintenance.py→ ALL TESTS PASSED
Example: reading the output
Vehicle: 84,500 km | in service 2021-03-10 | ~15,463 km/yr | SEVERE SERVICE
! Tire rotation OVERDUE safety-critical 6,000 2021-07-10
! Brake fluid OVERDUE safety-critical 30,000 2022-09-10
! Engine oil & filter OVERDUE wear-item 68,000 2026-07-15
...
Summary: 13 OVERDUE, 0 DUE SOON, 0 OK
The oil row reflects the history entry (63,000 km + severe 5,000 = due at 68,000, and Jan 15 + 6 mo = Jul 15 — km wins, it's already past). The tire rows show why "the car feels fine" isn't evidence: the model surfaces what the odometer and calendar already know.
One-Shot Recipes
Used-car baseline audit (unknown history, 3 years, 60,000 km):
python3 scripts/car_maintenance.py status --km 60000 \
--in-service 2023-08-01 --severe --json
Read: safety-critical OVERDUE = do now; wear OVERDUE = baseline fluids & filters, ~$250–450 at an independent shop.
Challenge a dealer's 90k package:
python3 scripts/car_maintenance.py status --km 91000 --in-service 2019-05-02 \
--history '[{"task":"oil","km":85000,"date":"2026-03-01"},
{"task":"cabin_filter","km":85000,"date":"2026-03-01"},
{"task":"tire_rotation","km":85000,"date":"2026-03-01"}]'
Anything in the package marked OK here is upsell; anything OVERDUE, price it against the cost column before agreeing.
24-month budget:
python3 scripts/car_maintenance.py timeline --km 91000 \
--in-service 2019-05-02 --annual-km 14000 --json
Sum the cost ranges by quarter; expect roughly $500–900/yr for an aging commuter car, front-loaded if the list has OVERDUE entries.
Advisory tool. Generic intervals; your owner's manual and local law (e.g. mandatory inspection dates) always take precedence.
相关技能
把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
为自然搜索排名提供站点审计、内容撰写与竞品分析。
voronindenis5 的更多技能
浏览全部技能Pryamoy 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.
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.
Turn flat resume bullets ('Responsible for X') into quantified STAR-method achievement narratives, score resumes against job descriptions for ATS keyword coverage and weak-phrase hazards, and expand each bullet into interview-ready stories with likely follow-up questions. Use when the user is writing or updating a resume/CV, preparing bullets for a job application, tailoring a resume to a specific job posting, or preparing interview stories from their experience.
Agent self-awareness of cognitive states — context fatigue, attention drift, memory debt, confidence erosion, and skill staleness. Detect, report, and mitigate degrading conditions before they cause failures.