Self AssessmentSAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

graph TD
A["Choose assessment mode"] --> B["Answer quiz questions"]
B --> C["Score per-topic proficiency"]
C --> D["Generate personalized learning path"]
D --> E["Start learning or deep dive"]
style A fill:#4CAF50,color:#fff
style E fill:#2196F3,color:#fff

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: 2.5.1
description: Comprehensive Claude Code self-assessment and learning path advisor. Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path with prioritized next steps. Use when asked to "assess my level", "take the quiz", "find my level", "where should I start", "what should I learn next", "check my skills", "skill check", or "level up".
---

# Self-Assessment & Learning Path Advisor

Comprehensive interactive assessment that evaluates Claude Code proficiency across 10 feature areas, identifies specific skill gaps, and generates a personalized learning path to level up.

## Instructions

### Step 1: Welcome & Choose Assessment Mode

Present the user with a choice of assessment depth:

Use AskUserQuestion with these options:
- **Quick Assessment** — "8 questions, ~2 minutes. Determines your overall level (Beginner/Intermediate/Advanced) and gives a learning path."
- **Deep Assessment** — "5 categories with detailed questions, ~5 minutes. Gives per-topic skill scores, identifies specific gaps, and builds a prioritized learning path."

If user chooses **Quick Assessment**, go to Step 2A.
If user chooses **Deep Assessment**, go to Step 2B.

---

### Step 2A: Quick Assessment

Present TWO multi-select questions (AskUserQuestion supports max 4 options each):

**Question 1** (header: "Basics"):
"Part 1/2: Which of these Claude Code skills do you already have?"
Options:
1. "Start Claude Code and chat" — I can run `claude` and interact with it
2. "Created/edited CLAUDE.md" — I have set up project or user memory
3. "Used 3+ slash commands" — e.g., /help, /compact, /model, /clear
4. "Created custom command/skill" — Written a SKILL.md or custom command file

**Question 2** (header: "Advanced"):
"Part 2/2: Which of these advanced skills do you have?"
Options:
1. "Configured an MCP server" — e.g., GitHub, database, or other external data source
2. "Set up hooks" — Configured hooks in ~/.claude/settings.json
3. "Created/used subagents" — Used .claude/agents/ for task delegation
4. "Used print mode (claude -p)" — Used `claude -p` for non-interactive or CI/CD use

**Scoring:**
- 0-2 total = Level 1: Beginner
- 3-5 total = Level 2: Intermediate
- 6-8 total = Level 3: Advanced

Go to Step 3 with the level result, listing which specific items were NOT checked as gaps.

---

### Step 2B: Deep Assessment

Present 5 rounds of questions, one AskUserQuestion call per round. Each round covers 2 related feature areas. Use multi-select for all rounds.

**IMPORTANT**: AskUserQuestion supports max 4 options per question. Each round has exactly 1 question with 4 options covering 2 topics (2 options per topic).

---

**Round 1 — Slash Commands & Memory** (header: "Commands")

"Which of these have you done? Select all that apply."
Options:
1. "Created a custom slash command or skill" — Written a SKILL.md file with frontmatter, or created .claude/commands/ files
2. "Used dynamic context in commands" — Used `$ARGUMENTS`, `$0`/`$1`, backtick `!command` syntax, or `@file` references in skill/command files
3. "Set up project + personal memory" — Created both a project CLAUDE.md and personal ~/.claude/CLAUDE.md (or CLAUDE.local.md)
4. "Used memory hierarchy features" — Understand how the 7 memory locations are concatenated into context (loaded root-down, CLAUDE.local.md appended after CLAUDE.md at each level, subdirectory files loaded on demand), used .claude/rules/ directory, path-specific rules, or @import syntax

**Scoring for Round 1:**
- Options 1-2 map to **Slash Commands** (0-2 points)
- Options 3-4 map to **Memory** (0-2 points)

---

**Round 2 — Skills & Hooks** (header: "Automation")

"Which of these have you done? Select all that apply."
Options:
1. "Installed and used an auto-invoked skill" — A skill that triggers automatically based on its description, without manual /command invocation
2. "Controlled skill invocation behavior" — Used `disable-model-invocation`, `user-invocable`, or `context: fork` with agent field in SKILL.md frontmatter
3. "Set up a PreToolUse or PostToolUse hook" — Configured a hook that runs before/after tool execution (e.g., command validator, auto-formatter)
4. "Used advanced hook features" — Configured prompt-type hooks, component-scoped hooks in SKILL.md, HTTP hooks, or hooks with custom JSON output (updatedInput, systemMessage)

**Scoring for Round 2:**
- Options 1-2 map to **Skills** (0-2 points)
- Options 3-4 map to **Hooks** (0-2 points)

---

**Round 3 — MCP & Subagents** (header: "Integration")

"Which of these have you done? Select all that apply."
Options:
1. "Connected an MCP server and used its tools" — e.g., GitHub MCP for PRs/issues, database MCP for queries, or any external data source
2. "Used advanced MCP features" — Project-scope .mcp.json, OAuth authentication, MCP resources with @mentions, Tool Search, or `claude mcp serve`
3. "Created or configured custom subagents" — Defined agents in .claude/agents/ with custom tools, model, or permissions
4. "Used advanced subagent features" — Worktree isolation, persistent agent memory, background tasks with Ctrl+B, agent allowlists with `Agent(agent_type)` (the `Task(...)` form is a back-compat alias), or agent teams

**Scoring for Round 3:**
- Options 1-2 map to **MCP** (0-2 points)
- Options 3-4 map to **Subagents** (0-2 points)

---

**Round 4 — Checkpoints & Advanced Features** (header: "Power User")

"Which of these have you done? Select all that apply."
Options:
1. "Used checkpoints for safe experimentation" — Created checkpoints, used Esc+Esc or /rewind, restored code and/or conversation, or used either Summarize option (summarize from here / summarize up to here)
2. "Used planning mode or extended thinking" — Activated planning via /plan, Shift+Tab, or --permission-mode plan; toggled extended thinking with Alt+T/Option+T
3. "Configured permission modes" — Used an

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.