agentleFS
runxhqrunxhq/runx/skills/chief-of-staff/SKILL.md

chief-of-staff

Skill97 starsChanged 36 days agoApache-2.0View on GitHub

Convert bounded mailbox and calendar evidence into a reviewable executive action packet.

38 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, loop-me and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 11 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 12 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 10 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 11 projects that use this

  • LesaniSkill

    writing-fragments

    Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.

    Also in 11 projects that use this

  • jddeliaSkill

    software-factory

    Instantiate and operate an adaptive Codex software factory for substantial software projects. Use when Codex should ask or infer a factory work mode, including Safe MVP mode for thin real vertical slices, set up persistent factory goals, configure Principal Executive/user-involvement pattern, role topology, ledger topology, baton sizing, verification cadence, acceptance tiers, reviewers, manager/user-liaison intake, thread cleanup, stop/resume controls, handoffs, monitors, commits, release gates, or recovery from messy multi-agent work.

    Also in 3 projects that use this

  • +1 more from Lesani

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use chief-of-staff for an executive or operator review pass over a known set of threads, events, and availability.

    line 21
  2. Very specific:

    Do not use it as an always-on mailbox agent, as permission to answer on someone's behalf, or to infer missing conversation context.

    line 26
  3. Distinctive:

    Never propose a time absent from the admitted availability snapshot.

    line 68
  4. Distinctive:

    Do not invent prior conversation, commitments, owners, deadlines, or provider state.

    line 69
  5. Distinctive:

    Keep sensitive categories under manual review even when the next action seems obvious.

    line 71
  6. Distinctive:

    Do not send, schedule, reschedule, accept, decline, or delete anything.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Chief of Staff

Turn a bounded view of mail and calendar context into an operator-ready action packet: what deserves attention, which replies are worth drafting, where time can be offered, and which risks need a human decision. The point is not to summarize an inbox. It is to reduce it to the few decisions and follow-ups that matter.

This skill works over context that another product or provider reader has already hydrated and redacted. It does not fetch a mailbox, send a reply, accept an invitation, or change a calendar. Those are separate provider actions with their own authority and approval.

When to use it

Use chief-of-staff for an executive or operator review pass over a known set of threads, events, and availability. It is useful when priorities must remain traceable to source items and when proposed actions need to be handed to a human or a later provider skill.

Do not use it as an always-on mailbox agent, as permission to answer on someone's behalf, or to infer missing conversation context. If the supplied snippets cannot support a safe recommendation, the correct result is needs_context.

How it works

  1. Supply redacted threads, events, and availability with stable source digests and observation times.
  2. Deterministic admission rejects duplicate, missing, malformed, or stale evidence and indexes the exact source references available to the review.
  3. The synthesis ranks actions, drafts unsent replies, proposes only supplied available times, and surfaces risks instead of retelling every item.
  4. Finalization rejects invented thread or event references and any proposed time outside the supplied availability snapshot.
  5. Legal, billing, HR, security, and account-access matters always retain a manual-review flag; model judgment cannot downgrade that boundary.

The packet labels upstream digests as caller-supplied provenance. A digest proves stable binding, not that Runx fetched or independently verified the provider record.

Inputs and result

  • objective says what the operator needs from this pass.
  • as_of and max_age_days define the freshness boundary.
  • mail_context.threads and calendar_context.events carry unique ids, digests, observation times, redacted summaries, and sensitivity when known.
  • Calendar availability includes its own evidence object, not merely a list of times.
  • constraints narrow tone, ownership, scheduling, and allowed actions.

The result contains a ranked priority queue, unsent draft replies, scheduling proposals, risks, missing questions, and mandatory-review flags. It always records delivery_status: not_sent and calendar_mutated: false. A consumer may route an accepted reply or calendar proposal to the appropriate provider skill, but must preserve its source binding and obtain the relevant approval there.

Stop conditions

  • Return needs_context for stale, unprovenanced, duplicated, or insufficient source material.
  • Never propose a time absent from the admitted availability snapshot.
  • Do not invent prior conversation, commitments, owners, deadlines, or provider state.
  • Keep sensitive categories under manual review even when the next action seems obvious.
  • Do not send, schedule, reschedule, accept, decline, or delete anything.

Example

A thread asks for a launch call and the calendar snapshot offers two times. The packet can rank the request, draft an unsent reply, and propose one of those times. It cannot offer a third time from model intuition, claim the reply was sent, or book the event. If the thread concerns a billing dispute, the draft may still be useful but the item remains marked for human review.

Agent task contract

chief-of-staff-synthesize

Rank only admitted source references. Return priorities, unsent drafts, scheduling proposals, and risks. Every item must use an exact source reference, and every proposed time must come from the supplied availability. Never mutate mail or calendars, invent provider state, or downgrade sensitive review.

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.