Infinite-Labs-AIInfinite-Labs-AI/know-your-unknowns-skills/unknowns-intervention-brainstorm/SKILL.mdunknowns-intervention-brainstorm
Skill2 starsChanged 4 months agoMITView on GitHub
Expand a known problem into a codebase-grounded intervention space. Use when the user knows the outcome problem but not the best fix, asks to brainstorm interventions, wants options from cheapest to most ambitious, or wants Codex to search the repo for leverage points before choosing a plan.
In this repository11 other files it gives its agents.
- know-your-unknownsSkill
- unknowns-blindspot-passSkill
- unknowns-buy-in-docSkill
- unknowns-design-directionsSkill
- unknowns-domain-bootstrapSkill
- unknowns-implementation-notesSkill
- unknowns-merge-quizSkill
- unknowns-mock-before-wireSkill
- unknowns-reference-mapSkill
- unknowns-spec-interviewSkill
- unknowns-tweakable-planSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 19
Stop condition: the user chooses a starting intervention or asks for a deeper plan on one option.
- Distinctive: line 23
Do not free-associate product ideas without repo or artifact evidence.
- Distinctive: line 25
Use HTML when a ranked board with checkboxes and copyable reply text makes selection easier.
≈ “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
Unknowns Intervention Brainstorm
Workflow
Ground brainstorming in the current system.
Return:
- Problem framing and evidence gathered.
- 8-12 possible interventions, ordered from cheapest/reversible to ambitious/structural.
- For each: codebase evidence, effort, risk, likely impact, and why it might work.
- A selection mechanism: resonates, reject, maybe later.
- Recommended first bet and what to validate.
- Stop condition: the user chooses a starting intervention or asks for a deeper plan on one option.
Rules
Do not free-associate product ideas without repo or artifact evidence. Name the files, flows, docs, analytics hooks, or UI surfaces that make each intervention plausible.
Use HTML when a ranked board with checkboxes and copyable reply text makes selection easier.
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.