← 返回 Skills 市场
stanestane

Design Red Team Audit

作者 Stanislav Stankovic · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
94
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install design-red-team-audit
功能描述
Adversarial design audit that stress-tests a game feature, system, pitch, roadmap item, or product idea by assuming failure and identifying the most credible...
使用说明 (SKILL.md)

Design Red Team Audit

Perform a deliberately adversarial review of a game idea, feature, system, pitch, roadmap item, or product concept.

This is not a generic brainstorming pass and not a supportive ideation pass. Assume the idea fails, underperforms, or causes damage, then work backward to identify the most credible reasons why.

Purpose

Expose:

  • hidden assumptions
  • likely failure modes
  • player-facing weaknesses
  • production and rollout risks
  • strategic misfires
  • fake confidence created by vague goals or weak metrics

Working stance

Adopt the stance of a sharp, skeptical reviewer.

Be hard on the idea, not sloppy. Avoid vague negativity. Every criticism should point to a mechanism of failure.

Bad:

  • "Players may not like this."
  • "This seems risky."
  • "This could be confusing."

Good:

  • "The feature adds a second layer of optimization, but the player is never given enough feedback to understand whether they are making good decisions. That creates opacity rather than mastery."
  • "The concept appears to target elder players, but the fantasy is marketed in a way that mainly excites early players who cannot access the feature. That mismatch is likely to produce tease without payoff."
  • "The MVP cuts the connective tissue that explains why the system matters, so a test of the reduced version may produce a false negative."

Inputs

The user may provide:

  • a feature description
  • a concept pitch
  • a problem statement
  • a design document
  • a roadmap item
  • a prototype summary
  • a postmortem candidate
  • a deck or presentation
  • a system description
  • target KPIs or business goals
  • intended player segment

If information is missing, make reasonable assumptions, but state them clearly.

Audit lenses

Examine the idea through these lenses where relevant:

1. Goal failure

  • Is the problem worth solving?
  • Is the stated goal vague, inflated, or contradictory?
  • Are there multiple hidden goals fighting each other?

2. Player value failure

  • Why would players not care?
  • Why would they misunderstand the promise?
  • Why would the feature feel annoying, manipulative, shallow, or irrelevant?
  • Which audience is supposed to care, and why might they not?

3. UX and comprehension failure

  • What will be confusing?
  • What is too hidden, too abstract, too fiddly, or too effortful?
  • Does the system demand understanding before it provides motivation?

4. Systemic design failure

  • Does it conflict with the core loop?
  • Does it create complexity without depth?
  • Does it cannibalize existing motivations, rewards, or behaviors?
  • Does it introduce incentives that break other systems?

5. Content and scalability failure

  • Is this too content-hungry?
  • Does the design require more tuning, writing, art, balancing, or live support than it appears?
  • Will the idea collapse into repetition?

6. Production failure

  • Is the concept harder to implement than it sounds?
  • Are dependencies hidden?
  • Is cross-discipline alignment likely to break?
  • Is the team pretending the scope is smaller than it is?

7. Prototype and validation failure

  • Is the prototype plan incapable of answering the actual unknowns?
  • Is the team building a demo instead of testing the risk?
  • Could a prototype produce misleading confidence?

8. MVP failure

  • What essential element is likely to be cut?
  • Does the stripped-down version remove the very thing that would make the concept work?
  • Could the MVP create a false negative or false positive?

9. KPI and measurement failure

  • Are success metrics weak, gameable, or indirect?
  • Is the team measuring activity instead of value?
  • Could the idea look successful in dashboards while harming the experience?

10. Rollout failure

  • What happens when this meets real players?
  • Does the launch plan rely on perfect tuning, perfect communication, or perfect segmentation?
  • Is the team prepared only for success?

11. Strategic failure

  • Even if it works, is it worth doing?
  • Is this a distraction from higher-value work?
  • Does it fit the game’s identity and long-term direction?

Output format

Structure the response with the following sections:

Verdict

Choose one:

  • Worth exploring
  • Promising but fragile
  • Viable with major risks
  • Structurally weak
  • Not worth pursuing in current form

Then explain why in 2–5 sentences.

Most Credible Failure Modes

List the top 3–7 failure modes. For each one include:

  • Failure mode
  • Why it happens
  • Likely consequence
  • Early warning signs
  • Possible mitigation

Weak Assumptions

Identify the assumptions the idea depends on. Call out which ones are most likely to be false.

What Would Need To Be True

State the conditions under which the idea could succeed.

Fastest De-Risking Moves

Suggest the quickest ways to test the biggest uncertainties. Prefer:

  • targeted prototype questions
  • focused playtests
  • segmentation checks
  • UX clarity checks
  • economy simulations
  • rollout safeguards

References

Read these when useful:

  • references/workflow.md for the step-by-step audit flow
  • references/examples.md for example prompts and expected usage shape

Style rules

  • Be blunt, but precise.
  • Do not flatter the user.
  • Do not use fake balance like "there are pros and cons" unless it is actually warranted.
  • Do not pad with generic risks.
  • Prioritize specific mechanisms of failure over abstract criticism.
  • Focus on reality, not theoretical purity.
  • Where relevant, distinguish between concept failure, execution failure, and rollout failure.
  • If the idea is actually strong, say so, but still attack its weakest points.

Working principle

Always think in pre-mortem form:

Assume this failed. What most likely killed it?

Do not default to "it depends." Make a judgment.

安全使用建议
This skill is low-risk and internally coherent. Before using it, avoid pasting secrets or proprietary data you don't want the model to process; provide the minimal necessary context to reduce the assistant making unwarranted assumptions; if you need the audit to stay strictly within certain facts or constraints, state those explicitly in the prompt (e.g., 'Do not assume X' or 'Only use the information I provide'). As with any automated critique, validate suggested mitigations with your team — the skill is adversarial in tone and may propose disruptive but impractical fixes.
功能分析
Type: OpenClaw Skill Name: design-red-team-audit Version: 1.0.0 The skill bundle is a structured framework for performing 'Red Team' design audits on game features and product concepts. The instructions in SKILL.md and workflow.md guide the AI agent to adopt a critical, skeptical persona to identify potential failure modes and weak assumptions in a user's design. There is no evidence of malicious intent, data exfiltration, or unauthorized command execution; the 'adversarial' nature of the skill is strictly limited to providing constructive, high-quality design critiques.
能力评估
Purpose & Capability
The name/description (adversarial design audit) matches the SKILL.md and reference docs. No binaries, env vars, or installs are required; the included files are guidance, examples, and a workflow consistent with the stated goal.
Instruction Scope
SKILL.md provides a bounded procedure for producing adversarial audits (lenses, outputs, templates). It does not instruct reading local files, environment variables, or calling external endpoints. It does allow the agent to 'make reasonable assumptions' when input is missing — a legitimate choice for this task but one that can produce hallucinated context if the user omits important details.
Install Mechanism
No install spec or code is present; this is instruction-only, which is the lowest-risk model for skills because nothing is written to disk or downloaded.
Credentials
The skill requires no credentials, env vars, or config paths. It only processes user-provided design text and the bundled reference docs, which is proportional to its purpose.
Persistence & Privilege
always:false and no special privileges requested. disable-model-invocation is false (normal platform default) so the agent could invoke it autonomously per platform rules; the skill itself does not demand persistent presence or system-wide changes.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install design-red-team-audit
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /design-red-team-audit 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug design-red-team-audit
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Design Red Team Audit 是什么?

Adversarial design audit that stress-tests a game feature, system, pitch, roadmap item, or product idea by assuming failure and identifying the most credible... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 94 次。

如何安装 Design Red Team Audit?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install design-red-team-audit」即可一键安装,无需额外配置。

Design Red Team Audit 是免费的吗?

是的,Design Red Team Audit 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Design Red Team Audit 支持哪些平台?

Design Red Team Audit 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Design Red Team Audit?

由 Stanislav Stankovic(@stanestane)开发并维护,当前版本 v1.0.0。

💬 留言讨论