CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

munger-perspective

芒格的视角:逆向思考、认知偏误、跨学科分析、投资决策审视。说「用芒格的视角」「逆向思考一下」「这有什么认知偏误」「Lollapalooza效应」「能力圈之外」「激励结构是什么」时触发。泛泛的「这个决策靠谱吗」不要触发。

Quality

95%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 mature, unusually well-sourced persona skill: concrete behavioral rules, a case-routing index, honest limitations and declared research blind spots, and a clean body-to-bundle split. Its only weakness is repetition of a few flagship cases across sections and an inline source list that partly belongs in the research bundle.

Suggestions

Consolidate the Belridge (C06) and Alibaba (C15) retellings into the casebook and cross-reference by case ID from the 招式/启发式/误读 sections to cut repeated narrative tokens.

Move most of the inline 来源 URL list into references/research/ (e.g., a sources.md), keeping only the top handful in the body.

Trim the 申报 section's method narrative to the bullets that affect answering behavior (research date, known blind spots, falsification triggers).

DimensionReasoningScore

Conciseness

The body is dense with skill-specific material — dates, dollar amounts, case IDs, sourced quotes — and almost never explains things Claude already knows. However, cases like Belridge (C06) and Alibaba (C15) recur across the 招式, 启发式, 误读, and 张力 sections, and the lengthy 来源 list could mostly live in references/research/, so minor trimming is possible.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: exact fallback phrases (「这件事我手头没有记录,下面是按我的思路推的」), a 17-entry case-index table routing question types to casebook IDs, a 5-item company-check checklist with an explicit cutoff rule (「五样里有两样查不到,就进『太难』」), and a list of banned pseudo-quotes with the real wording given instead.

5 / 5

Workflow Clarity

The numbered 「怎么用我」 protocol is clearly sequenced with decision checkpoints — bucket the question against the boundary table, route to the casebook, search for current facts before judging — and includes self-correction loops (「别滑回助手腔」 → re-read the voice samples) plus a falsification section (「什么会推翻现在的结论」).

5 / 5

Progressive Disclosure

The body is a genuine overview with well-signaled, one-level-deep references that all exist on disk: the case index routes to references/casebook.md by case ID, the bias list points to references/25-biases.md, voice samples extend into references/voice.md, and references/research/ is explicitly declared as source material.

5 / 5

Total

19

/

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.

An exemplary description: it states what the skill covers, gives multiple natural trigger phrases, explicitly excludes a near-miss phrasing, and occupies a distinct niche with minimal overlap risk. The only nit is that capabilities are framed as topic labels rather than actions.

DimensionReasoningScore

Specificity

The description names the domain and lists four concrete capability areas —「逆向思考、认知偏误、跨学科分析、投资决策审视」— which is specific and multi-part, but they are stated as topics rather than the concrete actions the skill performs, leaving minor gaps versus a fully comprehensive action list.

4 / 5

Completeness

Both questions are answered explicitly: the 「what」 is the four named analysis capabilities of Munger's perspective, and the 「when」 is a concrete 「说…时触发」 clause with specific trigger phrases — matching the top anchor exactly.

5 / 5

Trigger Term Quality

Six natural trigger phrases a user would actually say (「用芒格的视角」「逆向思考一下」「这有什么认知偏误」「Lollapalooza效应」「能力圈之外」「激励结构是什么」) plus an explicit anti-trigger (「泛泛的『这个决策靠谱吗』不要触发」) give comprehensive coverage including variations.

5 / 5

Distinctiveness Conflict Risk

Charlie Munger's perspective is a clear niche with distinctive trigger terms (Lollapalooza 效应, 能力圈), and the explicit negative trigger prevents firing on generic decision-review questions, minimizing conflict risk.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alchaincyf/nuwa-skill

Path

examples/munger-perspective/SKILL.md

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.