CtrlK
BlogDocsLog inGet started
Tessl Logo

naval-almanack

当用户询问《纳瓦尔宝典》这本书本身(书名/作者/章节/整书概览/术语),或涉及本书未独立成 Skill 的主题时调用: 幸福训练/欲望管理、接受与内耗、冥想与心猴、地位游戏与攀比、选朋友与圈子、打工vs创业(委托代理)、 诚实沟通、身份与自我形象、期望与愤怒、生命意义、该不该信玄学(理性验证)、长期复利与声誉、判断力训练。 以下意图优先使用同包独立 Skill: wealth-structure(致富/股权期权)、productize-yourself(职业定位/副业方向)、 decision-heuristics(重大选择纠结)、hourly-rate-time(时薪/外包/时间分配)、reading-metaskill(怎么读书学习)、screen-detox(刷手机上瘾)。 Triggers: 纳瓦尔/Naval/纳瓦尔宝典/幸福/冥想/内耗/攀比/圈子/复利/人生意义

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured router skill body: terse principles, an explicit intent-to-file routing table, and clear loading/boundary rules, with excellent progressive disclosure to real one-level-deep capability cards. The main room for improvement is tightening repeated delegation notes and making the workflow's fallback/validation more explicit.

Suggestions

Factor the repeated '已晋级为独立 Skill ... 本卡仅作原文与背景补充' note out of the six table rows into a single footnote to reduce token redundancy.

Add an explicit validation/feedback step in the loading rule, e.g. 'if the loaded card does not match the user's actual intent, re-query capability-index.md before answering'.

DimensionReasoningScore

Conciseness

The body is lean — six terse core principles, a structured routing table, and brief loading/boundary rules — with only minor redundancy such as the repeated '已晋级为独立 Skill ... 本卡仅作原文与背景补充' note across six table rows that could be factored out.

4 / 5

Actionability

The routing table maps concrete user intents to explicit file paths (e.g. references/capabilities/happiness-skill.md) and gives a clear 'load 1 card' instruction, but the actual executable guidance lives in the delegated capability cards rather than in this body itself.

4 / 5

Workflow Clarity

A clear sequence is given (read this file → route by intent → load 1 card, max 2 if cross-domain → answer) with an out-of-scope fallback and a medical/legal/safety stop, but there is no explicit validate-then-retry feedback loop, which keeps it just below a 5.

4 / 5

Progressive Disclosure

The SKILL.md is a pure overview/router pointing to 23 real, one-level-deep reference files (verified to exist), all clearly signaled in the routing table with explicit paths and intent columns — content is appropriately split and navigation is easy.

5 / 5

Total

17

/

20

Passed

Description

88%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.

A strong, book-scoped router description that clearly states when to invoke it, what it covers, and which sibling skills to prefer for overlapping intents. Its main weakness is a trigger-term list that omits several high-frequency natural phrases users would actually say.

Suggestions

Add high-frequency natural trigger terms currently missing from the Triggers line, e.g. 财富/赚钱/焦虑/朋友/选择, so the skill fires on the phrasings users actually use.

Consider adding a one-line English gloss of the book title (e.g. 'The Almanack of Naval Ravikant') to the trigger surface for bilingual users.

DimensionReasoningScore

Specificity

The description enumerates many concrete in-scope topics (幸福训练/欲望管理, 冥想与心猴, 地位游戏与攀比, 打工vs创业(委托代理), 长期复利与声誉, 判断力训练, etc.) plus 6 delegated independent skills, giving comprehensive coverage of the book's capability domains rather than vague language.

5 / 5

Completeness

It explicitly answers 'when' via '当用户询问《纳瓦尔宝典》...时调用' plus a concrete 'Triggers:' clause, and 'what' via the enumerated topic routing and delegation to independent skills — both what and when are explicit with concrete trigger phrases.

5 / 5

Trigger Term Quality

An explicit 'Triggers:' line lists natural user terms (纳瓦尔/Naval/幸福/冥想/内耗/攀比/圈子/复利/人生意义), but several common natural phrases a user would say (财富, 赚钱, 焦虑, 朋友) are absent from the trigger list, leaving a few gaps.

4 / 5

Distinctiveness Conflict Risk

The skill is anchored to a specific book and explicitly delegates overlapping topics (wealth-structure, productize-yourself, etc.) to other skills, but generic trigger terms like 幸福/冥想/复利 carry minor overlap risk with unrelated life-advice or mindfulness skills.

4 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

referenced_paths_exist

Referenced path issues: 43 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
kangarooking/cangjie-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.