مجالات الاختبار الخمسة

Why Domains Matter

The Five Domains at a Glance

domains = {
    "D1 Agent Architecture & Orchestration": 27,
    "D2 Tool Design & MCP": 18,
    "D3 Claude Code Config & Workflows": 20,
    "D4 Prompt Engineering & Structured Output": 20,
    "D5 Context Management & Reliability": 15,
}
assert sum(domains.values()) == 100

D1 — Agent Architecture (27%)

resp = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    tools=tools,
    messages=messages,  # full history every turn
)
if resp.stop_reason == "tool_use":
    results = run_tools(resp.content)
    messages.append({"role": "user", "content": results})
    # loop again until stop_reason == "end_turn"

D1 — Multi-Agent & Hooks

AgentDefinition(
    name="refund_specialist",
    description="Handles verified refund requests",
    system_prompt="...full context, since history is NOT inherited...",
    allowed_tools=["get_customer", "process_refund"],  # least privilege
)
# Coordinator's allowedTools MUST include "Task" to delegate

D2 — Tool Design & MCP (18%)

{
  "name": "lookup_order",
  "description": "Fetch an order by ID. Input: order_id like 'ORD-1234'. "
                 "Returns status, items, total. Returns isError if the ID "
                 "is unknown. Use only after the customer is verified.",
  "input_schema": {"type": "object",
      "properties": {"order_id": {"type": "string"}},
      "required": ["order_id"]}
}

D2 — MCP Primitives & Errors

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": { "GITHUB_TOKEN": "${GITHUB_TOKEN}" }
    }
  }
}

D3 — Claude Code Config (20%)

---
paths:
  - "src/payments/**"
---
# Payment module rules
- Never log full card numbers.
- All refunds over $500 require a hook-enforced approval.

# (Loads only when editing files under src/payments/)

D3 — Workflows & CI/CD

claude -p "Review the diff for correctness bugs only" \
  --output-format json \
  --append-system-prompt "Report only NEW or UNFIXED issues"

D4 — Prompting & Structured Output (20%)

schema = {
    "type": "object",
    "properties": {
        "category": {"enum": ["bug", "feature", "other"]},
        "detail": {"type": "string"},  # free text for 'other'
        "severity": {"type": "integer"},  # optional, may be absent
    },
    "required": ["category"],  # only the always-present field
}

D4 — Validation & Retry

def retry_with_feedback(doc, bad_output, error):
    return client.messages.create(
        model="claude-sonnet-4-5",
        max_tokens=1024,
        messages=[{"role": "user", "content":
            f"Document:\n{doc}\n\nYour previous output:\n{bad_output}\n"
            f"\nValidation error:\n{error}\nReturn corrected JSON."}],
    )

D5 — Context & Reliability (15%)

case_facts = {            # kept VERBATIM, never summarized
    "order_id": "ORD-1234",
    "refund_amount": 540.00,
    "order_date": "2026-05-02",
}
summary = summarize(long_history)  # vague over time
prompt = f"CASE FACTS (authoritative):\n{case_facts}\n\nSummary:\n{summary}"

Quick Check

Recap — The Five Domains