菜单
Stress-tests an idea through adversarial analysis, steelmanning, and concrete counterarguments. Use when claims need pressure-testing, failure modes may be subtle, or security and robustness matter.
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
Pressure-tests a proposed design through research, architecture, engineering, and cold-reader review before implementation. Use when a non-trivial plan exists and you want to find weak assumptions before writing code.
Runs the hypothesis → benchmark → keep/discard protocol for an autoresearch iteration. Use when executing a `shaka autoresearch` loop; it is loaded automatically on each iteration.
Evaluates an external source (repo, tool, article, talk) against the current project and produces a report-only steal/adapt/reject decision table with named rejections. Use when mining another system for ideas worth adopting without copying its scope.
Creates the benchmark harness for a new autoresearch run from a natural-language objective. Use when starting an interactive `shaka autoresearch start` setup session.
Expands the solution space with structured creative exploration and divergent thinking. Use when the task benefits from novel options, brainstorming, or deeper exploration beyond the first obvious answer.
Surfaces stronger decisions through structured multi-agent debate across competing perspectives. Use when several plausible approaches exist and the tradeoffs need to be argued, not just listed.
| name | red-team |
| description | Stress-tests an idea through adversarial analysis, steelmanning, and concrete counterarguments. Use when claims need pressure-testing, failure modes may be subtle, or security and robustness matter. |
| key | redteam |
| include_when | Claims need stress-testing. Security implications. Could fail non-obviously. |
Pressure-test claims, plans, architectures, and security designs. Size the analysis to the task, preserve independent first passes when multiple perspectives add value, and prefer concrete evidence over vote counts. The core deliverables are a fair steelman, the strongest surviving counter-argument, and an explicit stop reason.
Route to the workflow that matches the requested outcome.
When executing a workflow, output this notification directly:
Running the **WorkflowName** workflow in the **red-team** 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 summary |
|---|---|---|
| ParallelAnalysis | Stress-test existing content | Steelman + counter-argument (8 points each) |
| AdversarialValidation | Produce new content via competition | Synthesized solution from competing proposals |
The output column is a routing summary. Follow the selected workflow and
Integration.md for its full contract.
ParallelAnalysis protocol:
Philosophy.md: Core philosophy, success criteria, and evidence standardsIntegration.md: Optional integrations and output contractStress-test an architecture proposal:
User: "red team this microservices migration plan"
--> Workflows/ParallelAnalysis.md
--> Returns the strongest steelman and surviving counter-argument
Compare competing approaches before creating a design:
User: "battle of bots - which approach is better for this feature?"
--> Workflows/AdversarialValidation.md
--> Synthesizes a solution from competing proposals
Last Updated: 2026-07-23