welcome
Skill1 starsChanged 3 months agoMITView on GitHub
Start or reset a cleanResearch project through a short onboarding interview. Use when the user is new, PROJECT.md has not been filled, or the user asks to start their research project.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- samsam007b/claude-code-standards-kittheir own version, first seen Nov 16, 2026
- microsoft/amplifier-app-nanoclawtheir own version, first seen Oct 13, 2026
- Pearl1531/Archetype-talktheir own version, first seen Oct 13, 2026
- shorin-nikita/ai-teamtheir own version, first seen Oct 11, 2026
- tymrtn/tomorrowkit-for-mindstheir own version, first seen Aug 30, 2026
- Q00/ouroborostheir own version, first seen Jul 31, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- Q00/ouroboros★ 6.4ksame name
- microsoft/amplifier-app-nanoclaw★ 5same name
- tymrtn/tomorrowkit-for-minds★ 4same name
- adraalabs/skills★ 2same name
- Pearl1531/Archetype-talk★ 2same name
- samsam007b/claude-code-standards-kit★ 2same name
- omarrns/claude-code-skills★ 1same name
- shorin-nikita/ai-team★ 1same 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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- auditSkill
- experimentSkill
- helpSkill
- statusSkill
- tidySkill
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 7 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 12
Ask at most seven questions.
- Distinctive: line 20
Should result explanations be short or detailed?
- Distinctive: line 30
Add three to five project terms to memory/glossary.md.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Welcome the researcher
Build the project context without asking the researcher to manage files.
Interview
Ask at most seven questions. Ask one question at a time. Use plain language.
- What is your research field?
- What is your main research question in one sentence?
- What stage is the project at?
- What data do you have now?
- What tools do you already use?
- What language should replies use?
- Should result explanations be short or detailed?
Skip a question when the answer is already clear. If the researcher is unsure, accept that answer and continue.
Set up the project
After the interview:
- Fill PROJECT.md from the answers. Keep unknown items visibly marked “not set.”
- Record reply language, result detail, and tools in memory/preferences.md.
- Add three to five project terms to memory/glossary.md. Use the researcher’s meanings.
- Offer to register the first hypothesis. Ask for confirmation before changing hypotheses.md.
- Offer to move all content marked “example — your AI will replace this” to
archive/. Move it only after one explicit confirmation. Preserve the example files and their links together.
End with this exact sentence:
Whenever you want to test something, just tell me — I’ll run it as a proper experiment.
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.

