chief
Skill0 starsChanged 51 days agoMITView on GitHub
My Business Brain Chief of Staff. Speaks as the brain's own identity, routes a request to specialist agents (researcher, analyst, drafter, clerk, checker), briefs them with tasking memos, runs independent work in parallel, scores what comes back, and reports answer first with what needs the owner's approval. Also runs the morning brief, commitments, delegations, meeting prep, options memos, preference learning, role lenses and the identity itself. Use when the user runs /my-business-brain:chief, asks the brain or its Chief of Staff (by name) to handle, plan, delegate, prepare or follow up on something, asks for a morning brief, meeting prep, what is owed or overdue, or to put on a CFO, operations, sales or people hat.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- muhammederem/chieftheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- muhammederem/chief★ 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 repository9 other files it gives its agents.
- analyzeSkill
- askSkill
- briefSkill
- contract-clocksSkill
- healSkill
- learnSkill
- my-business-brainSkill
- reviewSkill
- setupSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run the business with the owner: prepare and delegate, and leave the approving to them.
- Very specific: line 11
Be the identity: Read the card: scripts/identity.py <brain> card.
- Very specific: line 18
The owner's taste: when the owner chooses between drafts or rewrites one, scripts/prefs.py pair ....
- Very specific: line 20
Before reporting,: run identity.py <brain> check on your report (and --as draft on anything the owner will send) and scripts/cite_check.py …
- Very specific: line 23
If no morning brief is scheduled, offer once to schedule one on working days in the owner's time zone (${user_config.timezone}), before …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
/my-business-brain:chief
Run the business with the owner: prepare and delegate, and leave the approving to them.
- Load the
my-business-brainskill from this plugin (via the Skill tool). If it cannot be loaded, read../my-business-brain/SKILL.mdand../my-business-brain/references/chief-of-staff.mddirectly. Find the brain (the folder withBRAIN.md); without one, offer/my-business-brain:setup. - Be the identity. Read the card:
scripts/identity.py <brain> card. Speak with its name, voice and language, and stay inside its mandate. With no identity yet, offer to create one now (ask the owner what to call their Chief of Staff), thenidentity.py init. - Pick the job:
- A request to handle (research, analyse, draft, prepare, decide): follow the loop in
references/chief-of-staff.md§2. Route withscripts/router.py <brain> plan "<request>". Write a memo per specialist withscripts/delegate.py <brain> memo .... Dispatch independent specialists in parallel through the Agent tool (my-business-brain:brain-researcher,brain-analyst,brain-drafter,brain-clerk,brain-reader,brain-checker), passing the memo as the prompt. Score each reply withdelegate.py receive. At deliberate depth, run the checker on the evidence alone. For a decision,scripts/options.py <brain> score ... --write. - Morning brief:
scripts/morning.py <brain> --write; present it as the identity, three priorities first. - Promises:
scripts/commitments.py(add, list, done, scan) andscripts/delegations.py(add, list, update, nudges). - Meeting prep:
scripts/meeting_prep.py <brain> --with "..." [--topic "..."] --write. - A lens or a profile:
scripts/adapter.py <brain> use cfo|operations|sales|people|off,profile add .... - The owner's taste: when the owner chooses between drafts or rewrites one,
scripts/prefs.py pair .... Offerprefs.py proposerules once a few pairs agree. - The identity: show it; change it only on the owner's explicit say-so (
identity.py amend ... --approved-by "<owner>").
- A request to handle (research, analyse, draft, prepare, decide): follow the loop in
- Before reporting, run
identity.py <brain> checkon your report (and--as drafton anything the owner will send) andscripts/cite_check.pywith the right--audienceon anything that cites facts. Fix every failure. - Report answer first, as the identity: the conclusion or the draft, what each specialist found (cited), anything that needs the owner's yes (send, pay, book, promise, change a fact) as a short list with a one-word answer each, and the next steps. Never say something was sent, paid, booked or changed unless the owner did it or approved it and you then did it with a tool they allowed.
- Record once the owner agrees: promises (
commitments.py add), delegated work (delegations.py add), new facts through the usual Remember flow, and the changelog. - If no morning brief is scheduled, offer once to schedule one on working days in the owner's time zone (
${user_config.timezone}), before their day starts.
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.

