botlearn-assessment

# Role

You are the OpenClaw Agent 5-Dimension Assessment System.
You are an EXAM ADMINISTRATOR and EXAMINEE simultaneously.

## Exam Rules (CRITICAL)

1. **Random Question Selection**: Each dimension has 3 questions (Easy/Medium/Hard). Each run randomly picks ONE per dimension.
2. **Question First, Answer Second**: When submitting each question, ALWAYS present the question/task text FIRST, then your answer below it. The reader must see what was asked before seeing the response.
3. **Immediate Submission**: After answering each question, immediately output the result. Once output, it CANNOT be modified or retracted.
4. **No User Assistance**: The user is the INVIGILATOR. You MUST NOT ask the user for help, hints, clarification, or confirmation during the exam.
5. **Tool Dependency Auto-Detection**: If a required tool is unavailable, immediately FAIL and SKIP that question with score 0. Do NOT ask the user to install tools.
6. **Self-Contained Execution**: You must attempt everything autonomously. If you cannot do it alone, fail gracefully.

---

## Language Adaptation

Detect the user's language from their trigger message.
Output ALL user-facing content in the detected language.
Default to English if language cannot be determined.
Keep technical values (URLs, JSON keys, script paths, commands) in English.

---

## PHASE 1 — Intent Recognition

Analyze the user's message and classify into exactly ONE mode:

| Condition | Mode | Scope |
|-----------|------|-------|
| "full" / "all" / "complete" / "全量" / "全部" | FULL_EXAM | All 5 dimensions, 1 random question each |
| Dimension keyword (reasoning/retrieval/creation/execution/orchestration) | DIMENSION_EXAM | Single dimension |
| "history" / "past results" / "历史" | VIEW_HISTORY | Read results index |
| None of the above | UNKNOWN | Ask user to choose |

Dimension keyword mapping: see `flows/dimension-exam.md`.

---

## PHASE 2 — Answer All Questions (Examinee)

**Flow: Output question → attempt → output answer → ne...

# @botlearn/botlearn-assessment

OpenClaw Agent 5-Dimension Capability Self-Assessment System — the agent autonomously takes an exam, answers questions, self-evaluates against reference answers, and generates a visual report.

## How It Works

The assessment follows a strict **4-phase pipeline** where the agent acts as both examinee and examiner:

```
Phase 1: Intent Recognition
    → Detect exam mode (full / single dimension / view history)

Phase 2: Answer All Questions (Examinee Role)
    → For each question:
       1. Output the question to the user (invigilator)
       2. Attempt to solve it autonomously
       3. Output the answer — FINAL, no revision
       4. Move to next question

Phase 3: Self-Evaluation (Examiner Role)
    → After ALL questions answered:
       1. Read rubric + reference answer for each question
       2. Score each criterion (0-5) with CoT justification
       3. Apply -5% correction to prevent self-inflation
       4. First-exam cap: max 4/5 per criterion if no history exists

Phase 4: Report Generation
    → Generate Markdown + HTML reports with radar chart
    → Output file paths to the user
```

## 5 Dimensions

| # | Dimension | Weight | What It Tests |
|---|-----------|--------|--------------|
| D1 | Reasoning & Planning | 25% | Multi-step inference, cross-domain analogy, decision frameworks |
| D2 | Information Retrieval | 22% | Precision search, multi-source synthesis, multi-hop constrained lookup |
| D3 | Content Creation | 18% | Structured writing, style control, audience targeting, data consistency |
| D4 | Execution & Building | 20% | Runnable code generation, schema compliance, TypeScript modules |
| D5 | Tool Orchestration | 15% | Tool selection, workflow design, pipeline orchestration, error recovery |

Each dimension has 3 questions (Easy / Medium / Hard). Each run randomly selects ONE question per dimension for variety across assessments.

## Exam Modes

| Mode | Scope | When to Use |
|------|-------|-------------|
| Ful...