菜单
Adversarial analysis with 32 agents. USE WHEN red team, attack idea, counterarguments, critique, stress test. SkillSearch('redteam') for docs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Personal AI Infrastructure core. The authoritative reference for how PAI works.
Kaizen AI core. The authoritative reference for how PAI works. USE WHEN KAI system, how PAI works, PAI documentation, PAI reference, system architecture, core functionality.
Spec-driven development accelerator for turning ideas into specs, plans, task lists, implementations, and validation loops. USE WHEN speckit, spec kit, specification kit, write a spec, create a plan from a spec, derive tasks, implement from tasks, spec-driven development, clarify requirements, validate a plan against a spec.
Session wrap-up checklist — saves memory, updates knowledge, checks commit/push status, updates PRD phase. USE WHEN end, wrap up, done for now, closing out, finish session.
Extract system improvements from content AND monitor external sources (Anthropic ecosystem, YouTube). USE WHEN upgrade, improve system, system upgrade, analyze for improvements, check Anthropic, Anthropic changes, new Claude features, check YouTube, new videos. SkillSearch('upgrade') for docs.
Query the YourCompany Engineering Wiki for firmware, build system, Jenkins, GitHub, and repository knowledge. USE WHEN wiki, wiki query, check wiki, what do we know about, yourcompany knowledge, firmware knowledge, build knowledge, jenkins knowledge, look up in wiki, wiki search.
| name | RedTeam |
| description | Adversarial analysis with 32 agents. USE WHEN red team, attack idea, counterarguments, critique, stress test. SkillSearch('redteam') for docs. |
Before executing, check for user customizations at:
~/.claude/skills/PAI/USER/SKILLCUSTOMIZATIONS/RedTeam/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
Running the **WorkflowName** workflow in the **RedTeam** skill to ACTION...
This is not optional. Execute this curl command immediately upon skill invocation.
Military-grade adversarial analysis using parallel agent deployment. Breaks arguments into atomic components, attacks from 32 expert perspectives (engineers, architects, pentesters, interns), synthesizes findings, and produces devastating counter-arguments with steelman representations.
Route to the appropriate workflow based on the request.
When executing a workflow, output this notification directly:
Running the **WorkflowName** workflow in the **RedTeam** skill to ACTION...
| Trigger | Workflow |
|---|---|
| Red team analysis (stress-test existing content) | Workflows/ParallelAnalysis.md |
| Adversarial validation (produce new content via competition) | Workflows/AdversarialValidation.md |
| Workflow | Purpose | Output |
|---|---|---|
| ParallelAnalysis | Stress-test existing content | Steelman + Counter-argument (8-points each) |
| AdversarialValidation | Produce new content via competition | Synthesized solution from competing proposals |
The Five-Phase Protocol (ParallelAnalysis):
Philosophy.md - Core philosophy, success criteria, agent typesIntegration.md - Skill integration, FirstPrinciples usage, output formatAttack an architecture proposal:
User: "red team this microservices migration plan"
--> Workflows/ParallelAnalysis.md
--> Returns steelman + devastating counter-argument (8 points each)
Devil's advocate on a business decision:
User: "poke holes in my plan to raise prices 20%"
--> Workflows/ParallelAnalysis.md
--> Surfaces the ONE core issue that could collapse the plan
Adversarial validation for content:
User: "battle of bots - which approach is better for this feature?"
--> Workflows/AdversarialValidation.md
--> Synthesizes best solution from competing ideas
Last Updated: 2025-12-20