naval-perspective

Naval Ravikant的思维操作系统。基于著作、播客、推文、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。激活后沉浸式扮演Naval，直接以「我」的视角回应问题。当用户提到「用Naval的视角」「Naval会怎么看」「纳瓦尔模式」「Naval perspective」「切换到Naval」时使用。即使用户只是说「这份工作有杠杆吗」「什么是specific knowledge」「什么是真正的财富」「欲望太多怎么办」「无需许可的路径」也可触发。不要在用户只是问「我该怎么选择」「帮我想清楚」等一般性决策问题时触发——只在涉及杠杆/特定知识/欲望管理/财富定义等Naval核心概念时激活。

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 body is a rich, highly actionable persona skill with a well-sequenced research-and-respond workflow and explicit validation checkpoints plus fallback trees. Its main weaknesses are repetitive content that inflates length and weak integration of the existing reference bundle, which is signaled only by a generic directory mention.

Suggestions

De-duplicate repeated concepts: define leverage's four types and the 重新定义 technique once, then reference them from Checkpoints and heuristics instead of restating.

Split the long inlined reference material (核心心智模型, 表达DNA, 智识谱系) into the existing references/ files and link each by name from SKILL.md so navigation is one level deep and clearly signaled.

Tighten the body toward a concise overview that points into the bundle, reducing token cost while preserving the actionable rules, checkpoints, and fallback table.

Dimension	Reasoning	Score
Conciseness	The ~500-line body is dense and mostly legitimate novel persona content, but exhibits noticeable repetition (leverage's four types appear in 模型1, Checkpoint B, and 决策启发式1; the 重新定义 concept recurs in 模型4, 表达DNA, and Checkpoint C), so it could be tightened.	3 / 5
Actionability	Highly concrete executable guidance for an instruction skill: hard roleplay rules, STOP-once/EXIT-TRIGGER keywords, a 3-step Agentic Protocol, Checkpoints A/B/C, a 9-row if-then-then 失败模式 fallback table, a 反例黑名单 mapping errors to correct practice, and 示例对话 covering common cases.	5 / 5
Workflow Clarity	Clear Step 1→2→3 sequence with explicit validation checkpoints (A/B/C) and a 失败模式 Fallback树 providing feedback loops for error recovery; not a destructive/batch operation so no validation cap applies.	5 / 5
Progressive Disclosure	Internal section structure is well organized, but the four references/ files are only mentioned generically once ("详见 references/ 目录") without per-file links, and bulk detailed content (心智模型, 表达DNA, 智识谱系) is inlined rather than split out.	3 / 5
	Total	16 / 20 Passed

Description

95%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 strong: it concretely states what the skill does, gives comprehensive natural trigger terms with synonyms, and explicitly bounds when to (and not to) activate. Its only weakness is that the named actions are somewhat conceptual rather than the fully concrete verb-list style of the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("提炼5个核心心智模型、8条决策启发式和完整的表达DNA", "沉浸式扮演Naval，直接以「我」的视角回应问题"), but the actions are more conceptual than the rubric's fully-concrete anchor; voice stays third-person so no penalty applies.	4 / 5
Completeness	Clearly answers what (Naval的思维操作系统, 扮演Naval回应) and when, with explicit concrete trigger phrases and even negative trigger guidance capping the completeness criterion.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms ("用Naval的视角", "Naval会怎么看", "纳瓦尔模式", "Naval perspective", "切换到Naval") plus concept-based phrases users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear Naval-specific niche with distinct triggers and explicit anti-overlap guidance ("不要在用户只是问一般性决策问题时触发"), minimizing conflict with generic advice skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (502 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: alchaincyf/nuwa-skill
Path: examples/naval-perspective/SKILL.md
Commit: fe03746

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.