analyse-problem — Claude Code skill: A3 problem analysis
This skill turns a problem into a one-page A3 document: background, current condition, goal, root cause and an action plan.
npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a claude-codeWhat analyse-problem does
The skill walks the agent through seven sections: background and impact, current condition with facts and metrics, a measurable goal, root cause analysis via 5 Whys or a fishbone diagram, countermeasures, an implementation plan with owners and dates, and follow-up. Output is a single-page document in markdown or plain text, named after the A3 paper format.
Invoke it with /analyse-problem [problem_description]. Leave the description out and the skill asks for it. OUTPUT_FORMAT controls the output, markdown by default.
It earns its place when an incident keeps coming back and you want the cause, not another patch on the symptom. The catch: the skill needs data. The current condition section is built on facts and metrics, so without logs, measurements or examples the agent fills it with platitudes.
What it helps with
- trace a recurring incident back to its root cause
- write up a problem on one page for the team
- separate facts and metrics from opinions when describing a failure
- build an implementation plan with owners and dates
- check that countermeasures target the cause, not the symptom
Example prompts for the agent
- /analyse-problem API goes down 2-3 times a week during peak hours
- /analyse-problem figure out why the build fails at the test stage
- /analyse-problem response times keep growing, OUTPUT_FORMAT: text
How to install analyse-problem
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a claude-code2Manually: put the files in place
~/.claude/skills/analyse-problem/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/analyse-problem/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a codex2Manually: put the files in place
.agents/skills/analyse-problem/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a cursor2Manually: put the files in place
.cursor/skills/analyse-problem/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NeoLabHQ/context-engineering-kit analyse-problem2Manually: put the files in place
.github/skills/analyse-problem/SKILL.md1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a gemini-cli2Platform CLI
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/analyse-problemManually: put the files in place
.devin/skills/analyse-problem/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about analyse-problem
How do I install analyse-problem in Claude?
Run npx skills add NeoLabHQ/context-engineering-kit --skill analyse-problem -a claude-code. The skill lands in ~/.claude/skills/analyse-problem/SKILL.md.
What does analyse-problem do?
It runs an A3 problem analysis: background, current condition, goal, root cause, countermeasures, implementation plan and follow-up. Everything fits on one page.
What input does the analysis need?
Facts and metrics about the problem: logs, measurements, examples. Without them the current condition section stays empty and the analysis turns generic.