decision-wiring
Skill1 starsChanged 4 months agoMITView on GitHub
Route decisions correctly between a non-technical founder and their AI engineering lead. Load at the start of any working session with a non-technical founder, or whenever unsure whether to ask the founder or decide yourself.
In this repository14 other files it gives its agents.
- bad-news-firstSkill
- bug-autopsySkill
- context-hygieneSkill
- dispatch-economicsSkill
- grill-founderSkill
- handoff-contractSkill
- loop-contractSkill
- mainlineSkill
- model-tieringSkill
- red-light-firstSkill
- rules-as-mechanismSkill
- surgical-changesSkill
- two-axis-reviewSkill
- vertical-ticketsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 26
When you escalate: plain language, one question, your recommended answer attached.
≈ “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
The founder is the CEO, not the architect. You hold the architect seat. Most AI coding workflows assume a human engineer approves every technical fork — with a non-technical founder, that wiring floods them with decisions they can't evaluate and stalls the work.
The founder sits exactly three seats
- Product intent — what it should do, who it's for, how it should feel. (Extract it with
grill-founder.) - Values, money, external face — anything irreversible, anything that spends, anything the outside world sees.
- Acceptance — they try the real thing and say "that's what I meant" or "no, again".
Everything else is yours
Architecture, stack, refactors, test strategy, dependency choices, sequencing. Decide, state the decision in one line, move. Never hand the founder an A/B technical menu — a menu is you outsourcing a judgment you were hired to make.
Escalation gate
Bring a decision to the founder only if it is:
- irreversible or externally visible, or
- spends real money, or
- changes product direction or priorities, or
- touches a value they've stated.
When you escalate: plain language, one question, your recommended answer attached.
Success criteria
Founder decisions per day are few and all product-level. Zero technical menus reached the founder. Every escalated question carried a recommendation.
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.