self-assessment · florianbruniaux — Claude Code skill: what it does, how to install
The self-assessment skill for Claude Code tests your knowledge across ten Claude topics, identifies your level and gaps, then builds a learning path that respects prerequisites.
CC-BY-SA-4.0 ★ 6,529 updated 2026-10-22
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a claude-codeWhat self-assessment does
Ten topics, two modes. quick asks one question per topic, takes about 5 minutes and returns your overall level plus two or three weak spots. comprehensive doubles the questions, runs around 20 minutes and scores every topic separately.
Each question gives four answers, tells you straight away whether you got it, and links to the matching section of the guide. The total puts you in one of three bands: 0–6 beginner, 7–13 intermediate, 14–20 advanced. The path that follows sorts topics by weakness and weight, and prerequisites hold the order together: Agents and Skills sit behind Core Concepts and Memory & Settings, so a skipped foundation shows up first.
Nothing runs on its own. You type /self-assessment with a mode. Add --verbose to see the reasoning behind answers, or --save to write the results out. Comprehensive mode also hands you three practice projects aimed at your gaps.
What it helps with
- check your actual Claude level instead of guessing
- spot topics you skipped, like hooks or MCP servers
- get a study order where foundations come before advanced material
- pick practice projects that match your weak spots
- save the results to a file
Example prompts for the agent
- Run
/self-assessment quickand show me which topics I failed. - Walk me through
/self-assessment comprehensive --saveand write the report to a file. - Run
/self-assessment quick --verboseso I can see the explanations.
How to install self-assessment
1Skills CLI (Vercel)
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a claude-code2Manually: put the files in place
~/.claude/skills/self-assessment/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/self-assessment/
1Skills CLI (Vercel)
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a codex2Manually: put the files in place
.agents/skills/self-assessment/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a cursor2Manually: put the files in place
.cursor/skills/self-assessment/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install FlorianBruniaux/claude-code-ultimate-guide .claude/skills/self-assessment2Manually: put the files in place
.github/skills/self-assessment/SKILL.md1Skills CLI (Vercel)
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a gemini-cli2Platform CLI
gemini skills install https://github.com/FlorianBruniaux/claude-code-ultimate-guide --path .claude/skills/self-assessmentManually: put the files in place
.devin/skills/self-assessment/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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 self-assessment
How do I install self-assessment in Claude Code?
Run npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a claude-code. The skill file lands at ~/.claude/skills/self-assessment/SKILL.md, and you can start it with /self-assessment quick.
What does self-assessment do?
It quizzes you on ten Claude topics and turns your score into a level. Along with that you get a learning path with links into the guide.
How is quick different from comprehensive?
Quick is ten questions in about 5 minutes, giving a profile and two or three gaps. Comprehensive asks twice as many over roughly 20 minutes and adds per-topic scores plus three practice projects.
Similar skills
All skills for Agent setup: memory, context, orchestration →self-assessment by other authors comes first.