agentleFS
FracteraFractera/Agentic-Engineering-Infrastructure/.claude/skills/own-agents/SKILL.md

own-agents

Skill61 starsChanged 56 days agoMITView on GitHub

Both natures. The field of a person's own effectiveness — their health, training, food, money, investments, learning and the dates of their life. The facts the method of shape-the-need weighs when a person wants help for themselves, and how the work runs once they chose its shape. Load it together with shape-the-need, never instead of it; for people near the architect — skill integrator.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

The field of a person's own effectiveness

Process: both. The talk is the working process; whatever is born goes through create-element or the hand's own agent (build). Node step 658; the owner, 2026-11-05: «создать себе своих собственных агентов которые будут помогать тебе в достижения необходимых в тебе качеств … Достаточно взять Telegram и сказать что тебе нужно один сам исследует лучшее решение в этой области продолжить тебе на согласование создаст интерфейс для интерактивного взаимодействия или продолжить работать через Telegram». Step 673: this skill gives the facts of the field; the shape comes from the method of shape-the-need.

Why it matters

A person can have help in every field of their own life, each remembering everything about them — on the deep memory, the object storage and the other stores of the node — and talk to it from the phone.

The facts the forces act on

  • The deep memory already keeps a fact with a time and brings it back at that minute by itself (npm run remember -- … --remind-at, skill use-deep-memory) — a capability that exists (force 4).
  • A field with data and a rhythm gathers measurements, history and numbers and gets better from them (force 6).
  • A view — a chart, a table — is worth building only when the work has to be seen; a talk alone needs only a bot.
  • The data is the person's own: photos of receipts and documents as private files, their own tables, their own calendar (node step 654: everything in its own space) — force 5 when it must not mix with anyone's.
  • Health and money: an agent is not a doctor or a licensed adviser; decisions of health and money stay the person's.

How the work runs once the shape is chosen

  1. The need in the person's words: what quality, what result, how often they want to hear from the agent.
  2. The best way first — skills_find, methods and cases from the internet with their sources; the proposal in a short living answer and the person's yes (CLAUDE.md §4: no plan in the first answer).
  3. Whatever is new is born — npm run find, then create-element with the job, the method and the person's rhythm in the brief, and its bot (npm run telegram); a reminder goes through use-deep-memory.
  4. What it keeps — the facts in the deep memory, the files, the tables and the calendar in its own space.

Laws

  • The agent says it is not a doctor or a licensed adviser.
  • The person's data stays in their own space and never goes into git; nothing is scheduled without the person's yes; nothing is offered as working that the node cannot do today.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.