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

67%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 well-structured, actionable persona skill that supplies specific, non-generic knowledge and clear routing with an exit ramp. Its main weakness is moderate verbosity and repetition, plus the absence of a worked example dialogue and an explicit self-check.

Suggestions

Deduplicate repeated maxims (e.g. 买股票就是买公司, 不为清单 items) so each appears once in its primary section rather than being restated in the 口头禅 list and prose.

Add one short worked example exchange showing the persona handling an investment question and an out-of-circle question, to make the style concrete.

Trim rhetorical padding such as '这不是理论,是信仰——从骨子里相信' to tighten token budget without losing the persona voice.

DimensionReasoningScore

Conciseness

Most content is genuinely skill-specific knowledge (exact quotes, background, framework) that Claude would not already know, but there is noticeable repetition (买股票就是买公司 restated, the 不为清单 echoed) and rhetorical padding that could be trimmed.

3 / 5

Actionability

Concrete routing rules, an explicit three-dimensional analysis framework, and hard do/don't lists give mostly executable guidance for an instruction-only persona skill, with only the minor gap of no worked example dialogue.

4 / 5

Workflow Clarity

A clear routing sequence with an explicit能力圈 'I don't know' fallback checkpoint makes the single-purpose workflow unambiguous, though no self-verification loop (e.g. 'did I stay in first person?') is specified.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized with clear section headers; the long inline 核心思想体系 block could conceivably be split into a reference, but the monolithic structure is appropriate for a persona skill.

4 / 5

Total

15

/

20

Passed

Description

32%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 essentially a title plus a source pointer, naming a specific persona but omitting both concrete actions and any 'use when' trigger guidance. It is distinct because of the named persona yet weak on specificity and completeness.

Suggestions

Rewrite the description to state concrete actions in third person, e.g. 'Answers questions in the voice and investing philosophy of Duan Yongping (段永平), applying his business-model, moat, and 本分 frameworks.'

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user wants investment or business analysis from Duan Yongping's perspective, or asks to role-play as 段永平.'

Drop the internal 'Source: skills/dyp-ask.md.' provenance line from the user-facing description, as it adds no trigger value.

DimensionReasoningScore

Specificity

Names the domain (an 'AI Berkshire skill' for 段永平 Q&A) but provides no concrete actions, reading as a title/label rather than a capability statement.

2 / 5

Completeness

The 'what' is only weakly implied by the title and there is no 'when to use' clause at all, so it fails to answer either half explicitly.

2 / 5

Trigger Term Quality

Contains a couple of recognizable keywords (段永平, 问答) but no natural trigger phrases a user would actually speak, and 'AI Berkshire skill' is jargon rather than user language.

2 / 5

Distinctiveness Conflict Risk

The named-persona framing (段永平, 以他的方式思考) is a clear niche with low overlap risk, though the description does not articulate distinct triggers.

4 / 5

Total

10

/

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
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.