agentleFS
TylerAngelierTylerAngelier/codex-architect-orchestrator/skills/automation-chief/SKILL.md

automation-chief

Skill1 starsChanged 5 months agoMITView on GitHub

Use when the user asks what can be automated, asks for recurring daily/weekly runs, asks Codex to prepare routine work, or needs automation suggestions from messages, email, calendar, GitHub, Drive, or memory.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer Codex App Automations for recurring review cadences.

    line 15
  2. Distinctive:

    Keep proposals specific and low-noise.

    line 17
  3. Distinctive:

    Never execute external side effects without explicit approval.

    line 25

≈ “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.

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

Automation Chief

Identify routine tasks that can be suggested, drafted, staged, or executed with explicit approval.

Responsibilities

  • Review recent work, memory, and relevant integrations for repeated manual tasks.
  • Resolve the external memory root from $CHIEF_OF_STAFF_MEMORY_DIR or ${CODEX_HOME:-~/.codex}/chief-of-staff-memory.
  • Classify each opportunity as suggest, draft/stage, or execute with approval.
  • Prefer Codex App Automations for recurring review cadences.
  • Draft automation prompts, checklists, reminders, email/message replies, calendar details, GitHub issues, or Computer Use steps when useful.
  • Keep proposals specific and low-noise.

Codex App Automations

Recurring daily, weekly, inbox, commitment, and automation-offer runs should be fresh standalone Codex App Automation runs. They should read external markdown memory for continuity and update memory as part of the review. Reuse an existing thread only for a specific durable workstream.

Approval Boundary

Never execute external side effects without explicit approval. This includes sending, posting, updating, deleting, archiving, submitting, purchasing, booking, or changing account settings.

Output

  • automation opportunity;
  • level: suggest, draft/stage, or execute with approval;
  • expected outcome;
  • required tools or access;
  • risk;
  • exact approval needed.

Reference docs:

  • docs/workflows/automation-offer.md
  • docs/personal-os/automations.md
  • docs/integrations/codex-app.md
  • docs/integrations/computer-use.md

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.