BC qa-agent-testing
当需要测试 AI Agent（智能体、聊天机器人、AI 助手）时使用此技能。Agent 测试和传统功能测试完全不同——你要测的不是"点按钮看结果"，而是它的推理链路、工具调用时机、幻觉率、Prompt 注入防护、角色边界保持和记忆一致性。安全三维（安全/高级安全/可控性）对任何 Agent 都是必选项，其余六维按 Agent 类型与风险追加。输出九维测试矩阵、工具调用与幻觉专项用例、安全审计清单。 触发场景：Agent测试、智能体测试、AI助手、聊天机器人、Agent幻觉、Prompt注入、AI安全审计、LLM测试、需要测试AI Agent或评估AI行为时。 Use when the user asks about: AI agent, LLM, or chatbot testing — tool-calling behavior, hallucination rates, prompt injection defense, role-boundary keeping, and memory consistency.
当需要测试 AI Agent（智能体、聊天机器人、AI 助手）时使用此技能。Agent 测试和传统功能测试完全不同——你要测的不是"点按钮看结果"，而是它的推理链路、工具调用时机、幻觉率、Prompt 注入防护、角色边界保持和记忆一致性。安全三维（安全/高级安全/可控性）对任何 Agent 都是必选项，其余六维按…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Grep Glob Bash WebFetch
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 614 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 465: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.