Agent skill

Codex Skill Self-Assessment

by FlorianBruniaux in FlorianBruniaux/claude-code-ultimate-guide

Runs an interactive quiz in a quick or comprehensive mode, scores your skill level by topic and generates a personalized learning path with practice projects.

CC-BY-SA-4.0Auto-check passedEducation

Install Codex Skill Self-Assessment

skills CLI
$ npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install FlorianBruniaux/claude-code-ultimate-guide self-assessment --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-ultimate-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/self-assessment .claude/skills/self-assessment && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
self-assessment
GitHub stars
6.1k
Token cost
~2.3k tokens
SKILL.md length
538 words
Files
4
Skills in repo
14
Repo updated
First seen
Licence
CC-BY-SA-4.0

At a glance

Runs an interactive quiz in a quick or comprehensive mode, scores your skill level by topic and generates a personalized learning path with practice projects.

  • Works in 4 steps: Choose Your Mode → Answer Questions → Get Your Profile → …
  • Finding out your current level with an AI coding agent
  • SKILL.md covers How It Works, Getting Started, What You Learn and After Your Assessment, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill offers two modes: a quick check with 10 questions across 10 topics that returns an overall profile (Beginner, Intermediate or Advanced) and the top two or three gaps, and a comprehensive mode with 20 questions, two per topic, that gives per-topic scores, a detailed learning path and 3 practice projects.

Questions cover practical usage, decision-making, architecture patterns and production practices. Each has four options, immediate feedback on the correct answer and a link to the matching guide section. The learning path orders topics by weakness and importance, shows prerequisites, gives time estimates and links templates and examples. It is started with /self-assessment quick or /self-assessment comprehensive, and a verbose option shows explanations.

When your agent uses it

  • Finding out your current level with an AI coding agent
  • Planning team training with a per-topic skill breakdown
  • Getting a prioritized learning path with practice exercises

Example prompts

  • “/self-assessment quick”
  • “Run the comprehensive self-assessment and give me a learning path for my weakest topics.”
  • “Do a quick assessment with explanations after each answer.”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Choose Your Mode
  2. Answer Questions
  3. Get Your Profile
  4. Get Your Learning Path

What it can do on your machine

Read from SKILL.md and the folder at commit 585c203. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Skill Self-Assessment loads about 2.3k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 538 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from FlorianBruniaux/claude-code-ultimate-guide at commit 585c203, republished under its CC-BY-SA-4.0 licence (© FlorianBruniaux). 538 words, ~2,284 tokens.

Download SKILL.mdSave it as .claude/skills/self-assessment/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
self-assessment
description
Interactive skill assessment with personalized learning path generation
version
1.0.0
trigger
/self-assessment
invocation
manual

Codex Self-Assessment

Master your Codex skills with a personalized learning journey.

This interactive assessment identifies your current expertise level and generates a custom learning path tailored to your gaps and goals.


How It Works

Step 1: Choose Your Mode

Quick Mode (5 min)

  • 10 questions across 10 topics
  • Best for: Quick skill check, understanding your general level
  • Output: Overall profile (Beginner/Intermediate/Advanced) + top 2-3 gaps

Comprehensive Mode (20 min)

  • 20 questions (2 per topic)
  • Best for: Detailed mastery assessment, planning team training
  • Output: Per-topic scores + detailed learning path + 3 practice projects
Step 2: Answer Questions

Questions cover:

  • Practical usage (how to do things)
  • Decision-making (when to use what)
  • Architecture patterns (why things work)
  • Production best practices (security, performance, scaling)

Each question has:

  • 4 options (A-D)
  • Immediate feedback on correct answer
  • Link to relevant guide section
Step 3: Get Your Profile

Quick Mode Output:

╔═══════════════════════════════════════════════╗
║ Your Profile: Intermediate Developer          ║
╠═══════════════════════════════════════════════╣
║ Overall Score: 14/20                          ║
║ Level: Intermediate (strong)                  ║
╠═══════════════════════════════════════════════╣
║ Immediate Gaps:                               ║
║  • MCP Servers (5/5 topics weak)              ║
║  • Advanced Patterns (4/5 weak)               ║
║  • Hooks (3/5 partially weak)                 ║
║                                               ║
║ → Recommended learning time: 4-6 hours        ║
╚═══════════════════════════════════════════════╝

Comprehensive Mode Output:

╔═══════════════════════════════════════════════════════════════╗
║ Detailed Mastery Profile                                      ║
╠═══════════════════════════════════════════════════════════════╣
║                                                               ║
║ 01 Quick Start          ████░░░░░░  8/10  Proficient         ║
║ 02 Core Concepts        ██████░░░░  6/10  Proficient         ║
║ 03 Memory & Settings    ██████░░░░  6/10  Proficient         ║
║ 04 Agents              ████░░░░░░  4/10  Basic               ║
║ 05 Skills              ████░░░░░░  4/10  Basic               ║
║ 06 Commands            ██████░░░░  6/10  Proficient          ║
║ 07 Hooks               ██░░░░░░░░  2/10  None                ║
║ 08 MCP Servers         ██░░░░░░░░  2/10  None                ║
║ 09 Advanced Patterns   ░░░░░░░░░░  0/10  None                ║
║ 10 Security            ███░░░░░░░  3/10  Basic               ║
║                                                               ║
║ OVERALL: Intermediate (14/100 points)                         ║
╚═══════════════════════════════════════════════════════════════╝
Step 4: Get Your Learning Path

Based on your scores, you get:

Prioritized learning sequence (respects dependencies):

  1. Topics ordered by weakness + importance
  2. Prerequisites shown (you can't skip foundations)
  3. Time estimates for each topic (sums only what you need)
  4. Templates and examples linked to each topic

Example path for Intermediate developer:

Phase 1: Hooks Fundamentals (2 hours)
  → Read: guide/ultimate-guide.md#7-hooks
  → Try: examples/hooks/event-driven-formatting.sh
  → Quiz: /lesson-quiz 07-hooks

Phase 2: MCP Integration (3 hours)
  → Read: guide/ultimate-guide.md#8-mcp-servers
  → Try: examples/mcp-configs/github-integration.json
  → Quiz: /lesson-quiz 08-mcp-servers

Phase 3: Advanced Patterns (4 hours)
  → Read: guide/ultimate-guide.md#9-advanced-patterns
  → Practice: 3 real-world projects (see below)
  → Quiz: /lesson-quiz 09-advanced-patterns

3 Practice Projects Based on your profile, you get targeted exercises:

  • Project 1: Combine 2-3 topics you're weak in
  • Project 2: Real-world workflow integration
  • Project 3: Team/production scenario

Getting Started

Quick Assessment
/self-assessment quick
Full Assessment
/self-assessment comprehensive
Options
/self-assessment quick --verbose      # Show explanations
/self-assessment comprehensive --save  # Save results to file

What You Learn

This assessment is designed to identify:

Fundamental Gaps
  • Core interaction loops you haven't tried
  • Essential features you've overlooked
  • Mental model misconceptions
Decision-Making Blind Spots
  • When to use agents vs skills vs commands
  • Which hook event to use for which problem
  • MCP server selection for your needs
Production Readiness
  • Security best practices
  • Performance optimization patterns
  • Scaling multi-agent systems
  • Team configuration and governance

After Your Assessment

Immediate Actions
  1. See your profile — Understand your current mastery level
  2. Identify gaps — Know exactly what to learn next
  3. Get a learning path — Personalized, dependency-aware sequence
  4. Practice — 3 targeted projects matching your level
Show full SKILL.md (201 more words)Show less
  • /lesson-quiz [topic] — Quiz yourself on specific topics
  • /audit-agents-skills — Audit your own config quality
  • /Codex-md — Manage your AGENTS.md configuration
Integration with Learning Path

After assessment, the /lesson-quiz skill provides per-module verification:

  • Answer 5 questions per module
  • Get instant feedback on weak areas
  • Unlock next module when ready

Scoring & Profiles

Junior Developer (0-6 points)
  • Just installed Codex
  • Know basic commands and workflows
  • Haven't touched memory/agents/hooks yet
  • Next step: Core Concepts + Memory module
Intermediate Developer (7-13 points)
  • Using Codex daily
  • Comfortable with AGENTS.md and basic agents
  • Exploring skills and commands
  • Some hook usage, no MCP servers
  • Next step: Deep MCP + Advanced Patterns
Advanced Developer (14-20 points)
  • Master multi-agent orchestration
  • Production-grade security and scaling
  • Custom skills and complex hooks
  • MCP server expertise
  • Next step: Team training, enterprise patterns

Tips for Better Results

  1. Answer honestly — Don't guess, skip unknown questions
  2. Review explanations — Each question has a guide link
  3. Revisit before level-up — Retake assessment after learning new topics
  4. Share results — Use your profile to coordinate with your team

Need Help?

  • Questions about the assessment? → Check /help self-assessment
  • Want to discuss results? → See guide/roles/learning-with-ai.md
  • Found an error? → Report it on GitHub Issues

Ready to master Codex? Start with /self-assessment quick now.

© FlorianBruniaux, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in .agents/skills/self-assessment of FlorianBruniaux/claude-code-ultimate-guide.

  • SKILL.md
  • README.md
  • comprehensive-assessment-prompt.txt
  • quick-assessment-prompt.txt

Open the folder on GitHubat commit 585c203

Compare with similar skills

Codex Skill Self-Assessment next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex Skill Self-Assessment compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Skill Self-Assessment this skillFlorianBruniaux/claude-code-ultimate-guide6.1k—~2.3kAutomated safety check: PassCC-BY-SA-4.0
Learn Law With Rohasrohasnagpal/legal-ai-skills178—~2.5kAutomated safety check: PassMIT
Interactive Course BuilderXiaomiMiMo/MiMo-Code14k—~2.9kAutomated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch66k—~2kAutomated safety check: PassMIT
Claude Certification Tutorrohitg00/ai-engineering-from-scratch66k—~3kAutomated safety check: PassMIT

Similar skills

  • Learn Law With Rohas

    rohasnagpal/legal-ai-skills

    Acts as an interactive legal tutor for learning a law, legal subject, doctrine, judgment, procedure, or legal concept.

    178 GitHub stars~2.5k tokensUpdated today
    EducationAuto-check passed
  • Interactive Course Builder

    XiaomiMiMo/MiMo-Code

    Turns a PDF, paper, document, URL or topic into a chapter-by-chapter course with exercises, feedback and review, and saves progress so you can resume later.

    14k GitHub stars~2.9k tokensUpdated yesterday
    EducationAuto-check passed
  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated 3 days ago
    EducationAuto-check passed
  • AI Engineering Placement Quiz

    rohitg00/ai-engineering-from-scratch

    Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

    66k GitHub stars~2k tokensUpdated today
    EducationAuto-check passed
  • Claude Certification Tutor

    rohitg00/ai-engineering-from-scratch

    Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.

    66k GitHub stars~3k tokensUpdated today
    EducationAuto-check passed
  • StudyVault Quiz Tutor

    bevibing/tutor-skills

    Quizzes you on the notes in an Obsidian StudyVault, tracks proficiency per concept and drills weak areas in four-question rounds.

    1.3k GitHub stars~1.4k tokensUpdated 7 mo ago
    EducationAuto-check passed

More from FlorianBruniaux/claude-code-ultimate-guide

All 14 skills in this repo
  • Changelog Social Recap

    FlorianBruniaux/claude-code-ultimate-guide

    Turns CHANGELOG.md entries for a release or a week into LinkedIn, Twitter/X, newsletter and Slack posts in French and English.

    6.1k GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check: notes
  • Whitepaper Bare Section Prose Filler

    FlorianBruniaux/claude-code-ultimate-guide

    Adds two to four sentences of intro prose before each bare heading in the French and English whitepapers, splitting the work across nine parallel agents.

    6.1k GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • Audit Whitepapers

    FlorianBruniaux/claude-code-ultimate-guide

    Audits version freshness, French and English parity and metadata of whitepapers and recap cards in the claude-code-ultimate-guide repo, with optional fix suggestions.

    6.1k GitHub stars~3.8k tokensUpdated 3 days ago
    Auto-check passed
  • Methodology Advisor

    FlorianBruniaux/claude-code-ultimate-guide

    Reads a codebase silently, asks only what it cannot infer, and recommends one AI-assisted development methodology stack with a contextual quick start.

    6.1k GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed
  • Guide and Landing Sync Check

    FlorianBruniaux/claude-code-ultimate-guide

    Check guide/landing synchronization status

    6.1k GitHub stars~692 tokensUpdated 3 days ago
    Auto-check passed
  • Track Online Mentions

    FlorianBruniaux/claude-code-ultimate-guide

    Searches the web for new mentions of the Claude Code Ultimate Guide or its author's public projects, checks them against YAML trackers and reports or adds the new ones.

    6.1k GitHub stars~2.4k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Codex Skill Self-Assessment

What does Codex Skill Self-Assessment do?

Runs an interactive quiz in a quick or comprehensive mode, scores your skill level by topic and generates a personalized learning path with practice projects. The skill offers two modes: a quick check with 10 questions across 10 topics that returns an overall profile (Beginner, Intermediate or Advanced) and the top two or three gaps, and a comprehensive mode with 20 questions, two per topic, that gives per-topic scores, a detailed learning path and 3 practice projects.

When should I use Codex Skill Self-Assessment?

Codex Skill Self-Assessment fits situations like: finding out your current level with an AI coding agent; planning team training with a per-topic skill breakdown; getting a prioritized learning path with practice exercises.

How do I install Codex Skill Self-Assessment in Claude Code?

Run `npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a claude-code`. Or copy the skill folder (.agents/skills/self-assessment in FlorianBruniaux/claude-code-ultimate-guide) into .claude/skills/self-assessment in your project. Claude Code loads it when a task matches its description.

How do I install Codex Skill Self-Assessment in Codex?

Run `npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a codex`. Or copy the skill folder (.agents/skills/self-assessment in FlorianBruniaux/claude-code-ultimate-guide) into .agents/skills/self-assessment in your project. Codex loads it when a task matches its description.

Can I use Codex Skill Self-Assessment in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill self-assessment -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/self-assessment, .gemini/skills/self-assessment, .github/skills/self-assessment and .opencode/skills/self-assessment in your project.

What does Codex Skill Self-Assessment need to run?

SKILL.md names no scripts, command-line tools or credentials: Codex Skill Self-Assessment is instructions for the agent only.

Does Codex Skill Self-Assessment access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codex Skill Self-Assessment safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Codex Skill Self-Assessment use?

Codex Skill Self-Assessment is published under the CC-BY-SA-4.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Skill Self-Assessment use?

About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Codex Skill Self-Assessment?

Skills that share tags, products or a category with Codex Skill Self-Assessment: Learn Law With Rohas (rohasnagpal/legal-ai-skills, 178 stars), Interactive Course Builder (XiaomiMiMo/MiMo-Code, 14k stars), DeepTutor CLI (HKUDS/DeepTutor, 41k stars) and AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Skill Self-Assessment?

FlorianBruniaux (a GitHub user) maintains it in FlorianBruniaux/claude-code-ultimate-guide, which has 6,136 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

Source: FlorianBruniaux/claude-code-ultimate-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.