start-a-focus
Skill1 starsChanged 18 days agoMITView on GitHub
Interview the user to start something new in the selected deployed vault: choose a Responsibility, Project, Topic or existing note, propose the smallest structure, then write it.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ingest-sourceSkill
- lint-vaultSkill
- process-inboxSkill
- process-ready-ingestion-inboxSkill
- review-vault-healthSkill
- update-project-next-actionsSkill
- update-project-summarySkill
- skill.mdSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Start something new in the Brain through a short interview: an ongoing area, a finite outcome, a subject to explore or a first item to keep.
- Distinctive: line 18
Read the vault rules and Procedure completely, and the Type notes the proposal uses, before acting.
- Distinctive: line 22
Ask one question at a time, at most about six.
- Distinctive: line 23
Search and reuse existing notes before proposing new ones.
- Very specific: line 25
Keep every belongs_to chain reaching a Responsibility.
- Distinctive: line 27
Verify retrieval from the entry note and report what was created, reused and left open.
≈ “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
Start a Focus
Start something new in the Brain through a short interview: an ongoing area, a finite outcome, a subject to explore or a first item to keep. A focus is the user's word, not a Type; the interview decides the Type.
For a single external item under existing work, use ingest-source directly.
Source of truth
- Vault rules:
AGENTS.md - Type contracts:
responsibility.md,project.md,topic.md - Complete workflow:
procedures/start-a-focus.md
Read the vault rules and Procedure completely, and the Type notes the proposal uses, before acting.
Guardrails
- Ask one question at a time, at most about six; skip what the request already answers.
- Search and reuse existing notes before proposing new ones.
- Propose notes, Types and parents in plain language and wait for agreement before writing.
- Keep every
belongs_tochain reaching a Responsibility; link existing material in place. - Hand technical workspaces to Initialize Project Memory; create no folders, connections, schedules or global-instruction changes here.
- Verify retrieval from the entry note and report what was created, reused and left open.
Select this package by the requested vault role, not its name alone. Reuse rules and the complete Procedure already read in this session while they remain current; reread after a relevant change.
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.

