Self AssessmentCAUTION
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Interactive skill assessment tool that evaluates your Claude Code mastery and generates personalized learning paths.
Overview
This skill provides two assessment modes:
- Quick (5 min): 10 questions, one per topic, rapid skill check
- Comprehensive (20 min): 20 questions, two per topic, deep mastery analysis
After assessment, get:
- ✓ Your mastery profile (Beginner/Intermediate/Advanced)
- ✓ Per-topic score breakdown
- ✓ Identified gaps ranked by importance
- ✓ Personalized learning path (respects dependencies)
- ✓ 3 practice projects matched to your level
Usage
Quick Assessment
/self-assessment quick
Fast evaluation across all topics. Shows overall level + top 2-3 gaps.
Comprehensive Assessment
/self-assessment comprehensive
Deep dive into each topic. Shows detailed per-topic scores + full learning path + practice projects.
Options
/self-assessment quick --verbose # Show detailed explanations /self-assessment comprehensive --save # Save results to assessment-results.json
How It Works
Interaction Flow
- Choose mode: Quick or Comprehensive
- Answer questions: 4-option multiple choice (A-D)
- See feedback: Explanation + guide link for each answer
- Get profile: Mastery assessment across all topics
- Get learning path: Personalized sequence respecting dependencies
- Choose action: Learn, practice, retry, or deep-dive on specific topic
Scoring
Quick Mode:
- 10 points total (1 per topic)
- Levels: 0-3 (Beginner), 4-7 (Intermediate), 8-10 (Advanced)
Comprehensive Mode:
- 20 points total (2 per topic)
- Levels: 0-6 (Beginner), 7-13 (Intermediate), 14-20 (Advanced)
Topics Covered
- Quick Start — Installation and basic workflow
- Core Concepts — Interaction loop, context, sessions
- Memory & Settings — CLAUDE.md configuration
- Agents — Creating and using specialized agents
- Skills — Building reusable capabi
d90170da4369OBSERVED · 2026-10-07Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: self-assessment
version: 1.0.0
description: Interactive skill assessment with personalized learning path generation
trigger: /self-assessment
invocation: manual
profiles:
- name: junior
label: "Beginner"
min_score: 0
max_score: 6
- name: intermediate
label: "Intermediate"
min_score: 7
max_score: 13
- name: advanced
label: "Advanced"
min_score: 14
max_score: 20
topics:
- id: 01
name: "Quick Start"
guide_section: "guide/ultimate-guide.md#1-quick-start-day-1"
importance: "critical"
depends_on: []
- id: 02
name: "Core Concepts"
guide_section: "guide/ultimate-guide.md#2-core-concepts"
importance: "critical"
depends_on: [01]
- id: 03
name: "Memory & Settings"
guide_section: "guide/ultimate-guide.md#3-memory--settings"
importance: "high"
depends_on: [02]
- id: 04
name: "Agents"
guide_section: "guide/ultimate-guide.md#4-agents"
importance: "high"
depends_on: [02, 03]
- id: 05
name: "Skills"
guide_section: "guide/ultimate-guide.md#5-skills"
importance: "high"
depends_on: [02, 03]
- id: 06
name: "Commands"
guide_section: "guide/ultimate-guide.md#6-commands-user-invocable-skills"
importance: "medium"
depends_on: [02]
- id: 07
name: "Hooks"
guide_section: "guide/ultimate-guide.md#7-hooks"
importance: "medium"
depends_on: [02, 03]
- id: 08
name: "MCP Servers"
guide_section: "guide/ultimate-guide.md#8-mcp-servers"
importance: "medium"
depends_on: [02]
- id: 09
name: "Advanced Patterns"
guide_section: "guide/ultimate-guide.md#9-advanced-patterns"
importance: "low"
depends_on: [04, 05, 06, 07, 08]
- id: 10
name: "Security & Production"
guide_section: "guide/security/"
importance: "critical"
depends_on: [02, 03]
modes:
- id: quick
name: "Quick Assessment"
duration: "5 minutes"
questions_per_topic: 1
total_questions: 10
description: "Rapid assessment across core topics. Get a skill level + identify 2-3 immediate gaps."
- id: comprehensive
name: "Comprehensive Assessment"
duration: "20 minutes"
questions_per_topic: 2
total_questions: 20
description: "Deep dive into each topic. Get per-topic scores + detailed learning path + practice projects."
---
# 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: ATrust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
whitepapers/recap-cards/en/_extensions
whitepapers/recap-cards/fr/_extensions
Gates applied: no_behavioural_pass.
d90170da4369full audit observations/trust-audit/skill/florianbruniaux__self-assessment.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | d90170da4369 | CAUTION | B | 89 | first audit |
Questions
What does the Self Assessment skill do?
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
Is Self Assessment safe to install?
With care. The audit graded it B (89/100) and found 2 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Self Assessment access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Self Assessment work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (d90170da4369), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.