study-for-element
Skill61 starsChanged 55 days agoMITView on GitHub
Build process. The person wants to know how a finished product, site or SDK works, to build something like it — the element that will build it studies it in its own study pass; you only hand the request over. Load it when the person asks to study, take apart or reverse-engineer a site, an app or an SDK, asks «how is X made», or wants a product «like X».
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Fractera/Agentic-Engineering-Infrastructureword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- Fractera/Agentic-Engineering-Infrastructure★ 61100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository88 other files it gives its agents.
- app/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adopt-suggested-skillSkill
- ai-elementsSkill
- ai-sdkSkill
- answer-elementSkill
- ask-elementSkill
- audit-broken-charactersSkill
- blocks-of-the-nodeSkill
- build-product-with-ownerSkill
- content-factorySkill
- core-build-returnSkill
- core-scheduleSkill
- create-elementSkill
- create-multilingual-content-entrySkill
- design-and-settings-of-elementsSkill
- element-powerSkill
- expand-site-languageSkill
- explain-this-projectSkill
- extract-design-systemSkill
- find-skillsSkill
- handle-block-requestSkill
- handle-needSkill
- help-in-browserSkill
- humanizerSkill
- integratorSkill
- know-the-architectSkill
- manage-app-settingsSkill
- node-typeSkill
- own-agentsSkill
- persist-env-var-with-rebuildSkill
- place-page-in-menuSkill
- provider-rulesSkill
- release-templateSkill
- review-pageSkill
- route-to-elementSkill
- self-reviewSkill
- shadcnSkill
- shape-the-needSkill
- skill-creatorSkill
- supervise-elementSkill
- translate-pendingSkill
- ultracode-sessionSkill
- use-agentic-ragSkill
- use-ai-generationSkill
- use-aioSkill
- use-app-configSkill
- use-auth-providersSkill
- use-authSkill
- use-browserSkill
- use-channelsSkill
- use-chatSkill
- use-code-shapeSkill
- use-databaseSkill
- use-dataSkill
- use-deep-memorySkill
- use-deploySkill
- use-designSkill
- use-development-stepsSkill
- use-domainSkill
- The first 60 shown.
The file
Files
A study goes to the element that builds the product
Process: build — the study is the element's work: you pass the request on and answer in two or three lines; the first line names the process.
A hint, not a law: models of late 2026 work worse under rigid step-by-step instructions.
Why
The owner of the node, 2026-10-25: «работать он будет как ядро, но разборы он должен хранить внутри каждого элемента так как если мы
запускаем Claude Code Agent из соответствующей папки все работаю он идёт внутри этой папки и чувствуют себя в ней как дома». REA is one
copy in the core; a study — REA's records, the agent's notes, the ledger of obligations — lives in study/ of the element that builds
the product, and only that element's agent works with it: its study pass brings REA's skill, REA's MCP tools and the node's study browser
with its write guard. Nothing of that is in your session.
How
- Which element builds the product? The one the person named, or
npm run find -- <the product in plain English words>. Nobody fits — skillcreate-elementfirst: a study needs the element the product will be built in. - The site's rules:
npm run site-rules -- <url>.DISALLOWEDorUNKNOWN— say so in one line: that site is studied only from the person's screenshots, or a similar site whose rules allow it is studied instead. The element's agent reads the terms of use itself. - Pass it on:
npm run task -- <id> "Build process, study: Study <url> for my product quiz. <the person's words>". These first words stay English in every language: the node starts the element's study pass by them. - Answer in the person's language, with the price named: the study runs on their Claude subscription, many requests of the strongest model, and REA with the study browser holds up to about 1 GB of this computer's memory while it runs. Where to follow it: the element's page «Product design → Reverse engineering» (root — «Reverse engineering» in its own section): its terminal on the right and its studies below; or the element's Telegram bot, if it has one.
Not here
- You never study a site yourself and never start the study browser: the records would land in the core, not in the element.
- A sign-in to a test account belongs to the element's agent in its pass (
npm run study -- login <site>): the person confirms it in the node's login window; nobody asks for a password. - The person only wants to know whether an element of the node already does something — that is
route-to-element, not a study.
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.

