CtrlK
BlogDocsLog inGet started
Tessl Logo

dyp-ask

AI Berkshire skill: 段永平问答:以他的方式思考. Source: skills/dyp-ask.md.

48

Quality

50%

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

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/dyp-ask/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body delivers rich, persona-specific material and concrete response guidance, but it is verbose (re-explaining known investing concepts) and monolithic with no progressive disclosure. It works as a persona skill yet would improve by trimming concept explanations and splitting the philosophy reference out of SKILL.md.

Suggestions

Trim explanations of well-known value-investing concepts (护城河, 称重机/投票器, 机会成本) to one-line cues, keeping only Duan Yongping's specific phrasing and biographical specifics.

Add 2-3 worked example Q&A exchanges showing the persona's voice in action to lift actionability.

Move the nine 核心思想体系 sections into a separate reference file (e.g. references/duan-philosophy.md) and have SKILL.md point to it one level deep, leaving the response-style and execution instructions inline.

DimensionReasoningScore

Conciseness

Persona-specific data (exact quotes, $2/股网易, $620,100 lunch, catchphrases, language style) earns its place, but the ~9 philosophy sections re-explain concepts Claude already knows (护城河, 称重机/投票器, 机会成本).

2 / 3

Actionability

Concrete routing table (投资/商业/人生/宏观→framework), do/don't lists, first-person and catchphrase directives give actionable guidance, but no worked example Q&A exchanges to copy keep it below 3.

2 / 3

Workflow Clarity

Question-type→framework routing is clear and the response action is largely unambiguous, but it reads as a categorized instruction set rather than a sequenced workflow with checkpoints; not 1 because routing is explicit.

2 / 3

Progressive Disclosure

The body is well-organized with headers, but it is a ~200-line monolithic file with zero external references; philosophy content that could live in a separate reference is all inline.

2 / 3

Total

8

/

12

Passed

Description

50%

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 a metadata-laden title rather than a capability statement: it names the persona but lacks explicit actions, natural trigger phrasing, and a "when to use" clause. It is functional but unpolished and would benefit from concrete verbs and an explicit Use-when clause.

Suggestions

Add concrete capability verbs, e.g. "Answers questions in the voice and investing philosophy of Duan Yongping (段永平), applying his business-model and 本分 frameworks."

Append an explicit trigger clause: "Use when the user asks about 段永平's views, wants a value-investing take in his style, or requests investing/business/人生 guidance from his perspective."

Remove metadata noise ("AI Berkshire skill:", "Source: skills/dyp-ask.md.") from the description so only user-relevant content remains.

DimensionReasoningScore

Specificity

It names the domain ("段永平问答") and a vague action ("以他的方式思考"), but offers no concrete capability verbs, so it lands between the vague and the multi-action anchors.

2 / 3

Completeness

A weak "what" (persona Q&A) is present, but there is no "Use when…"/when clause, so completeness is capped at 2 per the judging guidelines; not 1 because a "what" does exist.

2 / 3

Trigger Term Quality

"段永平" is a natural user term, but "以他的方式思考" is not a trigger and the string is padded with metadata ("AI Berkshire skill", "Source: skills/dyp-ask.md."), with common variations missing.

2 / 3

Distinctiveness Conflict Risk

The named-investor persona is a specific niche, but the generic "AI Berkshire skill" wrapper and the absence of explicit triggers keep it from being cleanly distinguishable.

2 / 3

Total

8

/

12

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
xbtlin/ai-berkshire
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.