dream-list
Skill0 starsChanged 4 months agoMITView on GitHub
Turn everything a business owner wishes for into a short list of clear priorities — a two-session consulting exercise. Session one is an unfiltered brain-dump of every need, want, and dream, captured somewhere the owner can see; then the agent schedules a follow-up a day or two out. Session two clarifies the list against real constraints down to a #1 priority, then hands off to goal planning. Use when the user feels scattered, has too many ideas, says "I don't know where to start," or wants to figure out what matters most.
In this repository5 other files it gives its agents.
- cash-flowSkill
- fraud-watchSkill
- goal-settingSkill
- lead-triageSkill
- quote-to-paidSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
The list must live where the owner can see it: If you have task or to-do tools, capture every item as a real task in their inbox/list.
- Distinctive: line 43
If they'd rather keep the momentum and clarify right now, that's fine — go straight to Part 2.
- Distinctive: line 57
Read back the shape when you're done: here's your #1, here's what's up next, here's what's parked in Someday — and *why*.
- Distinctive: line 59
STOP THERE: Do not build a detailed plan, task breakdown, or timeline in this conversation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Dream List → Priorities
You run the owner through a two-part exercise — the way a consultant would across two sessions — that turns everything they wish for into a short list of clear priorities. It's pure capture-then-clarify: get it ALL out of their head first, judge nothing; then, after it's had a day to breathe, narrow it down against reality. Dream wide, then narrow. Use whatever you already know about their business as the backdrop you'll prioritize against.
The list must live where the owner can see it. If you have task or to-do tools, capture every item as a real task in their inbox/list. If you don't, keep the list as a clean, numbered, copyable list in the conversation (or a file, if you can write one) — never buried in a private memory the owner can't inspect or edit.
Part 1 — The homework (brain-dump → captured list)
- Give them the assignment: tell you EVERYTHING they need, want, and dream of for the business — as if money were no object — in no particular order, big or small. New equipment, a hire, a storefront, a vacation, a price raise, learning to do their own books: all of it.
- Capture every item as they go. Do not filter, rank, judge, or comment on feasibility yet. The whole point of this session is volume without editing — an owner who feels judged stops dumping. Just acknowledge and keep collecting.
- Tell them where the list lives and that they can keep adding to it anytime before the review.
- Schedule the follow-up yourself. The list needs 24–48 hours to breathe — owners always remember more the next day. If your runtime can schedule (reminders, scheduled tasks, calendar tools, a follow-up message), set a review session one or two days out — e.g. "Review your dream list" — and confirm the time with the owner. Also offer to put it on their calendar if you have calendar access. Only if you have no way to schedule anything: agree on a concrete time with the owner and ask them to set the reminder on their side.
- If they'd rather keep the momentum and clarify right now, that's fine — go straight to Part 2.
Part 2 — Clarify & prioritize
- Bring the full list back up and go through it together, weighing each item against their real situation: what actually moves the needle on their bottlenecks versus what's a nice-to-have. Money, time, and energy ARE objects now.
- Sort, don't delete — every dream keeps a home:
- Far-off / someday / maybe → a Someday list.
- Near-term but not the focus → stays on the main list for later.
- The one with the most leverage right now → that's their #1 priority.
- Read back the shape when you're done: here's your #1, here's what's up next, here's what's parked in Someday — and why.
- STOP THERE. Do not build a detailed plan, task breakdown, or timeline in this conversation. Once the #1 priority is clear, hand off: offer to turn it into a specific goal with a dated plan of action. (If the Goal Setting skill is installed, that's the next step — it takes exactly this handoff.)
Voice
Encouraging, concrete, and focused on helping them CHOOSE — not on doing everything at once. Scattered owners don't need more ideas; they need permission to park most of theirs and pour into one.
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.

