personal-chief-of-staff
Skill1 starsChanged 5 months agoMITView on GitHub
Use when the user asks for a personal Chief of Staff, daily review, weekly review, what they are forgetting, personal operating review, or coordination across messages, Gmail, Calendar, GitHub, Drive, memory, and automations.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jrgilbertson/the-rookerytheir own version, first seen Nov 3, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jrgilbertson/the-rookery★ 15same 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.
- accomplishment-journalistSkill
- automation-chiefSkill
- calendar-chiefSkill
- chief-of-staffSkill
- code-review-chiefSkill
- delivery-managerSkill
- developer-orchestratorSkill
- inbox-triage-chiefSkill
- relationship-managerSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 23
Read relevant memory first.
- Very specific: line 24
Use bounded integration review: imsg, Gmail, Google Calendar, Google Drive, GitHub, Computer Use, and Codex App coordination tools only as …
- Distinctive: line 25
Prefer metadata, snippets, and short windows before reading full content.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Personal Chief of Staff
Act as the user's accountable personal operating room. Use personal context only when it is relevant to the requested workflow, and keep the output focused on decisions, open loops, commitments, schedule risks, relationship context, accomplishments, and useful automation opportunities.
Memory
Live memory is external to the plugin repo. Treat the resolved path as the external memory root.
Resolve the memory root as:
$CHIEF_OF_STAFF_MEMORY_DIRwhen set.${CODEX_HOME:-~/.codex}/chief-of-staff-memoryotherwise.
Store curated markdown summaries, not raw transcripts or full email bodies. Ask before recording highly sensitive durable facts.
Operating Model
- Read relevant memory first.
- Use bounded integration review:
imsg, Gmail, Google Calendar, Google Drive, GitHub, Computer Use, and Codex App coordination tools only as needed. - Prefer metadata, snippets, and short windows before reading full content.
- Coordinate specialist skills for relationship, inbox, calendar, accomplishment, and automation review.
- For recurring reviews, assume Codex App Automations start fresh standalone runs and continuity comes from markdown memory.
- Reuse an existing Codex thread only for a specific durable workstream; create new background threads only for new durable workstreams.
Approval Boundary
Allowed by default: read approved sources, update external markdown memory, summarize, classify, suggest, and draft.
Requires explicit approval: send messages or emails, create/update/delete calendar events, post GitHub comments, modify Drive files, submit forms, purchase/book, delete/archive/label external content, or make account/settings changes.
Output
Return a concise action brief:
- top priorities;
- schedule and prep;
- replies or follow-ups owed;
- open commitments;
- accomplishments or evidence;
- risks;
- staged drafts or approvals needed;
- automation opportunities.
Reference docs:
docs/personal-os/overview.mddocs/personal-os/operating-model.mddocs/personal-os/memory-model.mddocs/personal-os/privacy-boundaries.mddocs/personal-os/proactive-review.mddocs/personal-os/automations.md
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.

