ceos-ids
Use when identifying, discussing, or solving issues using the EOS IDS process
bradfeld · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add bradfeld/ceos --skill ceos-ids技能说明
name: ceos-ids description: Use when identifying, discussing, or solving issues using the EOS IDS process file-access: [data/issues/, templates/issue.md] tools-used: [Read, Write, Glob]
ceos-ids
Run the IDS (Identify, Discuss, Solve) process — the EOS method for resolving issues systematically. Every issue gets a root cause, a focused discussion, and at least one To-Do with an owner and due date.
When to Use
- "We have an issue" or "add to the issues list"
- "IDS this" or "let's identify discuss solve"
- "What are our open issues?" or "show the issues list"
- "Solve [issue]" or "discuss [issue]"
- "Close this issue" or "mark [issue] as solved"
- During L10 meetings when the IDS section begins
- Any time the team needs structured problem-solving
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
| File | Purpose |
|---|---|
data/issues/open/ | Open issues awaiting resolution |
data/issues/solved/ | Resolved issues (archive) |
templates/issue.md | Template for new issue files |
Issue File Format
Each issue is a markdown file with YAML frontmatter:
id: issue-001
title: "Slow customer onboarding"
priority: 1 # 1 (highest) - 5 (lowest)
category: process # people | process | data | vision | traction
ids_stage: identified # identified | discussed | solved
created: "2026-02-06"
Priority levels:
1— Critical, solve first2— High, solve soon3— Medium, solve when time allows4— Low, solve if capacity allows5— Nice-to-have, backlog
Categories (the 5 EOS issue types):
people— right person, right seat issuesprocess— systems, workflows, efficiencydata— metrics, reporting, information gapsvision— alignment with V/TO, Core Focustraction— execution, accountability, follow-through
IDS stages:
identified— root cause found, not yet discusseddiscussed— perspectives captured, not yet solvedsolved— To-Dos created, file moved todata/issues/solved/
File naming: issue-NNN-slug.md where NNN is a zero-padded ID and slug is the title slugified.
Process
Mode: List Issues
When the user asks to see the issues list.
- Read all files in
data/issues/open/. - Parse frontmatter for priority, category, and IDS stage.
- Display sorted by priority (1 first):
Open Issues (6 total):
━━━━━━━━━━━━━━━━━━━━
P1 issue-003 Slow customer onboarding [process] identified
P1 issue-007 Key account churning [people] discussed
P2 issue-001 Reporting gaps in dashboard [data] identified
P3 issue-005 Misaligned marketing spend [vision] identified
P4 issue-002 Office Wi-Fi unreliable [process] identified
P5 issue-008 Update team photo on website [process] identified
If no open issues exist: "No open issues. Nice work! Use 'ceos-ids' to create one when a new issue surfaces."
Mode: Create Issue (Identify)
Use when a new issue surfaces.
Step 1: Name the Issue
Ask: "What's the issue? Give it a short title."
Step 2: Dig for Root Cause (5 Whys)
Don't accept the first answer at face value. The stated problem is usually a symptom.
Walk through the 5 Whys:
- "Why is this happening?" → [answer]
- "And why is that?" → [answer]
- "What's causing that?" → [answer]
- Continue until you reach a root cause (usually 3-5 rounds)
Record both the stated problem and the root cause.
Step 3: Classify
- Priority — How urgent? (1/2/3/4/5)
- Category — Which EOS type? (people/process/data/vision/traction)
If the user isn't sure about category, help with examples:
- "Is this about having the right people?" → people
- "Is this about how work gets done?" → process
- "Is this about missing information?" → data
- "Is this about our direction?" → vision
- "Is this about executing the plan?" → traction
Step 4: Generate the ID
Read existing issue files in data/issues/open/ and data/issues/solved/. Find the highest issue-NNN ID across both directories and increment. If no files exist, start at issue-001.
Step 5: Write the File
Use templates/issue.md as the template. Fill in:
- Frontmatter: id, title, priority, category, ids_stage=identified, created=today
- Identify section: stated problem and root cause from 5 Whys
Write to data/issues/open/issue-NNN-slug.md.
Show the file before writing. Ask: "Create this issue?"
Mode: Discuss
Use when an identified issue needs discussion (often during L10).
Step 1: Open the Issue
Read the issue file. Show the current Identify section.
Step 2: Capture Perspectives
For each participant:
- "What's your perspective on this?"
- Record each person's view in the Discuss section
Rules for discussion:
- Everyone speaks. No one dominates.
- Stay focused on this issue — no tangents.
- No solving yet — just understanding.
Step 3: Update the File
- Update
ids_stagetodiscussedin frontmatter - Fill in the Discuss section with perspectives
- Show the diff, ask for approval, write
Mode: Solve
Use when a discussed issue is ready for resolution.
Step 1: Open the Issue
Read the issue file. Show the Identify and Discuss sections for context.
Step 2: Determine the Solution
Ask: "What's the solve? What specific actions will resolve this?"
For each action:
- Action — what needs to be done (specific and verifiable)
- Owner — one person (not "the team")
- Due date — when will this be done