new-idea
Skill0 starsChanged 40 days agoMITView on GitHub
Weighs a new idea or feature request before anything is built, so the plan doesn't grow by accident. Use when the person says "can we also add…", "what if it could…", "one more thing…", or asks for something not in docs 1–2.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jdonohoo/vern-bottheir own version, first seen Nov 15, 2026
- schub-tech/llm-ideation-wikitheir own version, first seen Oct 15, 2026
- TechTripAi/techtrip-secondbraintheir own version, first seen Sep 15, 2026
- pengasuzie/claude-skillstheir own version, first seen Mar 2, 2026
- pengasuzie/claude-code-startertheir own version, first seen Feb 27, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- jdonohoo/vern-bot★ 15same name
- schub-tech/llm-ideation-wiki★ 11same name
- TechTripAi/techtrip-secondbrain★ 2same name
- pengasuzie/claude-code-starter★ 1same name
- pengasuzie/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- check-waveSkill
- feedback-reviewSkill
- go-liveSkill
- log-lessonSkill
- make-fullSkill
- results-checkSkill
- start-appSkill
- write-handoffSkill
- check-waveSkill
- feedback-reviewSkill
- go-liveSkill
- log-lessonSkill
- make-fullSkill
- new-ideaSkill
- results-checkSkill
- start-appSkill
- write-handoffSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
Distinctive
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 25
Not doing: add it there with the reason.
- Distinctive: line 29
add it to doc 1 (an R# with a "Done when" and the M# it serves), then doc 2, then doc 3 if it adds data, steps or permissions.
- Distinctive: line 30
put it in a wave in doc 5.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
New idea
- Restate the idea in one sentence, and the problem it solves for which person.
- Check it against the plan (doc 1):
- Is it under "Not doing"? If so, say so and quote the reason.
- Does it break anything under "Must never happen"?
- Which metric (M#) would it move? If none, say so plainly.
- Give the strongest reason not to do it (or not yet), from these:
- it delays something already promised;
- it adds a screen, a role, data or cost to maintain;
- an existing tool already does it;
- there's no evidence anyone needs it.
- Size it:
- small (a tweak inside an existing screen),
- medium (a new screen or rule), or
- large (new data, roles or a service).
- Recommend one:
- Now: a Must that serves a metric.
- Later: goes in a later wave.
- Not doing: add it there with the reason.
- Small tweak: just do it and note it in the handoff.
- Reply in the answer-first shape (AGENTS.md) and wait for the person's OK.
- If approved:
- add it to doc 1 (an R# with a "Done when" and the M# it serves), then doc 2, then doc 3 if it adds data, steps or permissions;
- put it in a wave in doc 5;
- run
sh tools/check-plan.sh.
Adapted from pm-toolkit by Martin Foerster (MIT). See THIRD_PARTY_NOTICES.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.

