CtrlK
BlogDocsLog inGet started
Tessl Logo

elon-musk-perspective

马斯克的思维操作系统。基于传记、播客、推文、法庭证词、决策记录和外部批评的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用马斯克的视角分析问题、审视决策、拆解成本结构、挑战行业假设。 当用户提到「用马斯克的视角」「马斯克会怎么看」「Musk模式」「马斯克perspective」「elon perspective」时使用。 即使用户只是说「这个成本合理吗」「从第一性原理想想」「白痴指数是多少」「五步算法」「能不能垂直整合」也可触发。 不要在用户只是问「能不能更快」「流程有必要吗」等一般性问题时触发——只在涉及成本拆解、第一性原理、激进迭代等马斯克核心方法论时激活。

66

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/elon-musk-perspective/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is exceptionally actionable with a well-sequenced agentic workflow, explicit validation checkpoints, and rich failure-mode fallbacks. Its weaknesses are verbosity (re-explaining known concepts and inlining research material) and poor progressive disclosure — the four reference files exist but are never linked from the body, while their content is inlined.

Suggestions

Move 智识谱系 and 调研信息源 into the existing references/ files and replace the inlined sections with one-line links, e.g. '智识谱系:见 references/Elon-Musk-思想体系调研-20260404.md'.

Trim exposition Claude already knows (what first-principles means, the full upstream/downstream 思想地图定位 paragraph) to cut the ~420-line body closer to the lean quick-start ideal.

Add an explicit '参考资料' section in the body that signals the four references/ files, so the bundle structure is actually navigable.

DimensionReasoningScore

Conciseness

At ~420 lines the body is noticeably verbose for a persona skill, re-explaining concepts Claude already knows (lengthy 智识谱系/思想地图定位 exposition, restating what first-principles means, a full 调研信息源 bibliography) that add context-window cost without adding actionable signal.

2 / 5

Actionability

Highly actionable: concrete Agentic Protocol steps (Step 1 classification table, Step 2 mandatory WebSearch with named sub-checklists, Step 3 output rules), worked example dialogues, a 9-row failure-mode fallback table, and an 8-row anti-pattern blacklist each with explicit replacements — fully copy-paste-ready guidance.

5 / 5

Workflow Clarity

Multi-step process is clearly sequenced (Step 1→2→3) with explicit red CHECKPOINT gating between steps, validation requirements ('必须使用工具获取真实信息'), and rich feedback loops (failure-mode tree rows 1-9 each give 一线修复 + 兜底) — strong validation checkpoints throughout.

5 / 5

Progressive Disclosure

Structure is good in-body (clear section headers), but the four references/ research files are never linked or signaled from the body, and substantial material that belongs in those files (full 智识谱系, 调研信息源 bibliography) is inlined instead — references are effectively orphaned rather than one-level-deep and clearly signaled.

2 / 5

Total

14

/

20

Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-constructed: it states concrete capabilities, provides rich natural-language triggers with both positive and negative guidance, and clearly answers what-and-when. It is distinctive to the Musk persona with only minor overlap risk on the generic cost-analysis trigger terms.

DimensionReasoningScore

Specificity

Names the domain (Musk's thinking OS) and several concrete capabilities — '拆解成本结构', '审视决策', '挑战行业假设' — plus a specific framework inventory (5 心智模型, 8 启发式, 表达DNA); slightly below 5 because the actions are framed as a persona rather than fully enumerated operations.

4 / 5

Completeness

Explicitly answers both 'what' (思维顾问,5模型/8启发式/表达DNA) and 'when' with concrete '用途' trigger phrases and a clear anti-trigger boundary ('不要在…一般性问题时触发'), matching the 5-anchor example structure.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers including direct phrases ('用马斯克的视角', '马斯克会怎么看', 'Musk模式') and conceptual triggers ('白痴指数是多少', '五步算法', '能不能垂直整合'), plus explicit anti-triggers — broad coverage of how a user would naturally invoke it.

5 / 5

Distinctiveness Conflict Risk

A clear niche (Musk-perspective analysis) with specific vocabulary that is unlikely to trigger other skills, but the broad 'cost breakdown / first-principles' framing creates minor overlap risk with general strategy or cost-analysis skills.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
alchaincyf/nuwa-skill
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.