Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Browser & automation

ceos-process

Use when documenting core processes or reviewing process followability

bradfeld · AI review on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add bradfeld/ceos --skill ceos-process

About this skill


name: ceos-process description: Use when documenting core processes or reviewing process followability file-access: [data/processes/, templates/process.md, data/vision.md, data/accountability.md] tools-used: [Read, Write, Glob]

ceos-process

Document, simplify, and audit core company processes — the 6th EOS component. Every company has a handful of core processes that must be documented as checklists, simplified to their essential steps, and followed by all.

When to Use

  • "Document our sales process" or "create a new process"
  • "Show our processes" or "what processes do we have?"
  • "Audit process FBA scores" or "how well are we following our processes?"
  • "Simplify the hiring process" or "reduce this process to essentials"
  • "Update the onboarding process" or "add a step to the deployment process"
  • Any conversation about documenting how work gets done

Context

Finding the CEOS Repository

Search upward from the current directory for the .ceos marker file. This file marks the root of the CEOS repository.

If .ceos is not found, stop and tell the user: "Not in a CEOS repository. Clone your CEOS repo and run setup.sh first."

Sync before use: Once you find the CEOS root, run git -C <ceos_root> pull --ff-only --quiet 2>/dev/null to get the latest data from teammates. If it fails (conflict or offline), continue silently with local data.

Key Files

FilePurpose
data/processes/Process documentation files
data/vision.mdV/TO document (Core Focus and Proven Process for alignment)
templates/process.mdTemplate for creating new process files
data/accountability.mdAccountability Chart (seat owners for process-owner alignment)

Process File Format

Each process is a markdown file with YAML frontmatter:

id: process-001
title: "Customer Onboarding"
owner: "brad"
fba_score: 85
last_audited: "2026-02-14"
status: active          # draft | active | deprecated
created: "2026-01-15"

Status values:

  • draft — being documented, not yet in use
  • active — documented and in use, subject to FBA audits
  • deprecated — no longer followed (kept for historical reference)

File naming: process-NNN-slug.md where NNN is a zero-padded ID and slug is the title slugified (lowercase, hyphens, no special chars).

FBA (Followed-By-All) score: A percentage from 0-100 representing how consistently the team follows the documented process. Target: 80%+.

Process

Mode: Document

Use when creating a new process or updating an existing one.

Step 1: Determine New or Update

Check the user's request:

  • If they name a specific existing process → load it for editing
  • If they want a new process → continue with creation

For updates, read the existing process file, display the current content, and discuss what needs to change.

Step 2: Review Context

Before creating a new process, read and briefly reference:

  • The Core Focus and Proven Process from data/vision.md — processes should align with how the company operates
  • Any existing processes in data/processes/ — avoid duplicates and ensure coverage

Display a quick summary: "You currently have N documented processes: [titles]."

Step 3: Collect Process Details

For a new process, collect:

  1. Title — short, specific name (e.g., "Customer Onboarding", "Sales Process", "Deployment Pipeline")
  2. Owner — one person who is accountable for this process (never shared)
  3. Purpose — why does this process exist? What outcome does it ensure?
  4. Steps — the numbered checklist of actions

For the steps, guide the user:

  • Each step should start with an action verb ("Send", "Review", "Schedule", "Create")
  • Aim for 5-20 steps. If more than 20, suggest the process might need to be split
  • Steps should be specific enough that someone new could follow them
  • Nested steps (1.1, 1.2) are allowed for complex steps, but maximum 2 levels deep

Step 4: Validate

  • 3-7 core processes. Count existing active processes. If adding this one would exceed 7, warn: "EOS recommends 3-7 core processes. You'll have N. Is this a core process or a supporting one?" Don't block — just flag.
  • One owner. If the user tries to assign multiple owners, explain: "Each process has one owner — the person accountable for it being documented, simplified, and followed. Who should own this?"
  • Step count. If more than 30 steps, warn: "This process has 30+ steps. Consider splitting into sub-processes or simplifying."
  • Duplicate check. If a process with a similar title already exists, ask: "A process called '[title]' already exists. Update that one, or create a new one?"
  • Seat alignment. Cross-reference the process owner against data/accountability.md. The owner should hold the seat whose responsibilities align with the process's domain. Flag mismatches: "This process falls under [Seat] responsibilities. Should [Seat Owner] own it?"

Step 5: Generate the ID

Read existing process files in data/processes/. Find the highest process-NNN ID and increment. If no files exist, start at process-001.

Step 6: Write the File

Use templates/process.md as the template. Substitute:

  • Frontmatter fields (id, title, owner, fba_score=0, last_audited=today, status=draft, created=today)
  • Body sections (purpose, steps, owner name)

Write to data/processes/process-NNN-slug.md.

Show the user the complete file before writing. Ask: "Create this process?"

Step 7: Repeat or Finish

Ask: "Create another process, or are we done for now?"

When finished, display a summary table of all documented processes:

ProcessOwnerStatusFBA
Customer Onboardingbradactive85%
Sales Processdanieldraft—

Mode: Audit

Use for reviewing FBA scores across all documented processes.

Step 1: Read All Processes

Read all process files from data/processes/. Pa

Read the complete source ↗