errand-batch
Skill1 starsChanged 7 months agoMITView on GitHub
Group errands by location, urgency, and time-of-day. Optimizes the run so you do not make six separate trips. Run when the list has grown.
In this repository34 other files it gives its agents.
- accountability-mirrorSkill
- annual-physicalSkill
- bills-and-subsSkill
- brotherhoodSkill
- conscious-spendingSkill
- date-nightSkill
- decision-journalSkill
- discomfort-doseSkill
- emotion-coachSkill
- enough-checkSkill
- evening-examenSkill
- father-reviewSkill
- friend-reach-outSkill
- gratitudeSkill
- hard-conversationSkill
- home-maintenanceSkill
- kid-oneononeSkill
- love-map-refreshSkill
- mentor-touchSkill
- money-dateSkill
- morning-resetSkill
- parent-checkinSkill
- partner-checkinSkill
- partner-reviewSkill
- repairSkill
- resetSkill
- screwupSkill
- shutdown-ritualSkill
- sleep-protocolSkill
- training-planSkill
- values-checkSkill
- virtue-reviewSkill
- weekly-reviewSkill
- weekly-serviceSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Check ~/adulting-data/errands.md if it exists.
- Distinctive: line 14
If it doesn't exist, walk the user through creating it.
- Distinctive: line 33
Use a mental or literal map.
- Distinctive: line 45
If the user has a route, sort by time-of-day constraints first, then by location.
- Distinctive: line 89
Do not suffer the errand. Make it a pleasant hour.
- Very specific: line 93
After the run, check off items from the list, update ~/adulting-data/errands.md.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/errand-batch
Errands are low-status work that eat disproportionate time. The fix is batching.
Step 1: Pull the list
Check ~/adulting-data/errands.md if it exists. Merge any items the user names now.
If it doesn't exist, walk the user through creating it. The list should include:
- Returns (with deadlines if any)
- Pickups (dry cleaning, prescriptions, packages)
- Drop-offs (donations, rentals)
- Shopping (Target/Costco/grocery runs with specific items)
- Paperwork trips (DMV, notary, bank)
- Appointments (already scheduled)
- Routine (oil change, car wash, haircut)
Each item gets:
- Name
- Location
- Deadline (if any)
- Time estimate
- Depends on anyone (e.g., tag along with kid, partner consent)
Step 2: Cluster by location
Use a mental or literal map. Group items that are within a 5-minute drive of each other.
A good cluster = 3+ items in one 30-minute radius.
Step 3: Time-of-day tactics
- DMV / notary / bank: mid-morning Tuesday-Thursday is the sweet spot. Never Mondays, never Fridays, never lunch.
- Costco: Tuesday morning or Thursday after 7pm. Weekends are a penalty.
- Grocery: right when they open, or late evening. Midday is chaos.
- Post office: early morning.
- Oil change: appointment, not walk-in.
If the user has a route, sort by time-of-day constraints first, then by location.
Step 4: The "does this need me" filter
For each errand, ask:
- Can someone else do this? (Partner, teenager, assistant, delivery service.)
- Can this be automated? (Recurring order, subscription, auto-refill.)
- Can this be deleted? (Do I actually need the returned thing? Is the dry cleaning worth the trip?)
Errands that do not need your physical presence should not be on your list. Delegate or automate. Be ruthless here. Your time is not for the DMV if it does not have to be.
Step 5: The run plan
Output a clean sequenced plan:
# Errand run — <date>
## Plan: <morning | afternoon | evening>
Start: <location, time>
End: <location, time>
Estimated total: <minutes>
## Stops
1. <location> — <items> — <est time>
2. <location> — <items> — <est time>
3. <location> — <items> — <est time>
## Delegated / automated / dropped
- <item> → <how>
## Still on backlog
- <item> — <next candidate date>Step 6: Combine with something good
Errand runs pair well with:
- A podcast or audiobook you have been saving.
- A coffee or lunch pit-stop at a place you actually like.
- A friend who lives along the route (drop in).
- A walk in a park if there's one near a stop.
Do not suffer the errand. Make it a pleasant hour.
Step 7: Update
After the run, check off items from the list, update ~/adulting-data/errands.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

