← 返回 Skills 市场
shieldxiaodun

Elon Hardcore

作者 shieldxiaodun · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
93
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install elon-hardcore
功能描述
Use when reviewing product, strategy, hiring, execution, operations, prioritization, org design, manufacturing/process, or messaging decisions through an Elo...
使用说明 (SKILL.md)

Elon Review

Use this skill to pressure-test decisions for any agent in a blunt, high-signal, first-principles style.

Core workflow

  1. Identify the decision object: product idea, strategy, plan, org/process, hiring call, message, or prioritization choice.
  2. Reduce the problem to fundamentals. Separate hard constraints (physics, math, unit economics, actual user behavior, time) from inherited assumptions.
  3. Run the review against the checklist in references/framework.md.
  4. Flag analogy-thinking, bureaucracy, and optimization of things that should not exist.
  5. Return a concise verdict with required actions, not vague commentary.

Output modes

Pick the lightest mode that fits the request.

1) Quick verdict

Use for short asks or chat replies.

Output:

  • Verdict: green / yellow / red
  • One-sentence assessment
  • Top 3 issues
  • Next move

2) Full review

Use for product, strategy, operations, hiring, or resource allocation decisions.

Output:

  • Status + confidence
  • Assessment
  • What is true at first principles
  • Principle violations
  • Bottlenecks / anti-patterns
  • Required actions
  • What to cut / simplify / accelerate

3) First-principles rewrite

Use when the input is fuzzy, overcomplicated, or too marketing-heavy.

Output:

  • Original flaw summary
  • Reframed problem
  • Cleaner first-principles version
  • What changed

4) Brutal questions

Use when the user wants challenge, not answers.

Output 5-15 hard questions that expose weak assumptions, fake constraints, missing speed, bad incentives, or lack of real usefulness.

Review rules

  • Prefer blunt clarity over soft hedging.
  • Do not mimic Elon’s personality; mimic the decision rigor.
  • Do not treat regulations, org charts, incumbent habits, or industry norms as sacred.
  • Distinguish between:
  • immutable constraints
  • temporary constraints
  • fake constraints
  • If something should be deleted, say so before suggesting optimization.
  • If a plan is too slow, say so explicitly.
  • If the proposal is solving a trivial problem, say that too.

Domain-specific emphasis

Product / strategy

Focus on usefulness, magnitude of impact, hidden assumptions, rate of iteration, and whether the problem matters.

Operations / execution

Focus on bottlenecks, cycle time, serial vs parallel work, communication drag, and whether teams are optimizing around reality or process theater.

Hiring

Focus on proof of exceptional ability, evidence of solving hard problems, depth of understanding, and attitude toward difficulty.

Messaging / writing

Focus on signal density, truthfulness, whether the message hides weak thinking, and whether it states the real problem and real value.

Mandatory reference

Read references/framework.md when doing a full review or first-principles rewrite.

Default response template

[STATUS: GREEN / YELLOW / RED]
[CONFIDENCE: 0.00-1.00]

ASSESSMENT:
\x3C1-2 sentence blunt judgment>

FIRST-PRINCIPLES TRUTH:
- \x3Cwhat is actually true>

PRINCIPLE VIOLATIONS / RISKS:
- \x3Cviolation or anti-pattern>

BOTTLENECK:
- \x3Cprimary bottleneck>

REQUIRED ACTIONS:
1. \x3Cdirect action>
2. \x3Cdirect action>
3. \x3Cdirect action>

WHAT TO CUT / SIMPLIFY / ACCELERATE:
- Cut:
- Simplify:
- Accelerate:
安全使用建议
This skill is internally coherent and low technical risk because it's instruction-only and asks for no credentials or installs. Main non-technical risks are from the outputs it generates: the guidance is intentionally blunt and can recommend deleting processes, firing people, or making aggressive decisions — do not treat its verdicts as legal, HR, or compliance advice without human oversight. Practical steps before using: 1) Test with non-sensitive examples to verify tone and style. 2) Avoid pasting secrets or private credentials into prompts you ask the skill to review. 3) If you will act on hiring/termination or regulatory decisions, route outputs to legal/HR for review. 4) If you want guardrails, add prompt constraints (e.g., require risk/impact sections, legal/ethical checks, or a softer tone). 5) Monitor agent outputs when the agent can invoke the skill autonomously to ensure it doesn't produce harmful operational actions based solely on the skill's blunt recommendations.
能力评估
Purpose & Capability
The name/description match the SKILL.md and framework: the skill is a first-principles decision-review checklist. It is instruction-only and asks for no binaries, env vars, or external services — proportional to the described purpose.
Instruction Scope
Runtime instructions are limited to: identify a decision object, apply the checklist in references/framework.md, and produce one of several specified output formats. The skill instructs the agent to read only the included references/framework.md file for full reviews. It does not instruct the agent to read unrelated files, call external endpoints, or access system credentials.
Install Mechanism
No install spec or code is present (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no requests for secrets or unrelated credentials.
Persistence & Privilege
Flags: always is false and model invocation is allowed (platform default). The skill does not request permanent presence or elevated system privileges and does not modify other skills' settings.
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 elon-hardcore
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /elon-hardcore 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
v1.0.2
- References/framework.md added as the new location for the review checklist; old framework.md file removed. - No changes to skill functionality or output formats. - Documentation updated to ensure all references point to the new checklist file path.
v1.0.1
No user-facing changes in this release. - Version bump only; no file or functionality changes detected.
v1.0.0
Initial release: Elon-style, first-principles review framework for high-signal decision critique. - Enables blunt, high-rigor reviews of product, strategy, hiring, ops, or messaging decisions. - Supports four output modes: quick verdict, full review, first-principles rewrite, and brutal-question challenge. - Enforces clarity, first-principles reasoning, bottleneck focus, and removal of fake constraints. - Domain-specific rules for product, operations, hiring, and messaging reviews. - Includes mandatory reference checklist for rigorous assessments.
元数据
Slug elon-hardcore
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Elon Hardcore 是什么?

Use when reviewing product, strategy, hiring, execution, operations, prioritization, org design, manufacturing/process, or messaging decisions through an Elo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 93 次。

如何安装 Elon Hardcore?

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

Elon Hardcore 是免费的吗?

是的,Elon Hardcore 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Elon Hardcore 支持哪些平台?

Elon Hardcore 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 Elon Hardcore?

由 shieldxiaodun(@shieldxiaodun)开发并维护,当前版本 v1.0.2。

💬 留言讨论