BD red-team
对抗性方案审查工作流。专门扮演最挑剔的反对者，系统性地攻击任何方案、决策、 计划或论点——找漏洞、列风险、提反例、暴露盲区。 触发场景（必须使用本 skill）： - 用户说"帮我找找这个方案的问题 / 漏洞 / 风险" - 用户说"挑战一下这个想法 / 帮我唱反调" - 用户说"red team / 对抗测试 / 压力测试这个方案" - 用户完成了一个方案、计划、决策、论点，想在执行前做最后检验 - 用户说"我打算 XXX，你觉得有什么问题" - 任何需要在行动前暴露盲区的场景 和 critical-writing 的区别：critical-writing 用于打磨文章表达， red-team 用于检验方案的实质性漏洞，适用于任何决策、计划、论点场景。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
low Risky intent
intent-offensive-securityexamples/example-startup-plan.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)# 示例：创业方案 Red Team
fixture -
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Red Team Pro guides an agent through a Chinese adversarial review workflow that challenges plans, decisions, and arguments through logic, execution, and worst-case risk rounds. <br>
-
low Risky intent
intent-offensive-securitySKILL.md:10Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- 用户说"red team / 对抗测试 / 压力测试这个方案"
quoted -
low Risky intent
intent-offensive-securitySKILL.md:36Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team — 对抗性方案审查工作流
-
low Risky intent
intent-offensive-securitySKILL.md:87Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## 本次 Red Team 阵型
-
low Risky intent
intent-offensive-securitySKILL.md:177Offensive-security / dual-use content (legitimate for authorised testing; review intended use)📋 Red Team 综合评估
-
low Risky intent
intent-offensive-securitySKILL.md:199Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Red Team 的目标是**暴露问题**，不是帮用户完善方案——保持攻击性
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 334 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "difficulty"
Process rating: all ten parameters 49/100
- 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
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (red-team) differs from the folder (red-team-pro)
- 100Tools and files. No external tools needed
- 100Steps. 5 steps
- 100Execution cost. Instruction body is 548 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
- +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
- +5Description quotes 4 example trigger phrases
- +3Description length 333: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.
External checks
ClawHub: clean
This is a disclosed Chinese red-team review skill that may be blunt or over-eager, but it does not show hidden access, execution, data theft, or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026