wang-lao-shi-demo

蒸馏王老师的指导方式与核心教诲。用于延续导师的教学智慧与指导风格，辅助学习与回顾。

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/mentor-demo/SKILL.md

Quality

Content

72%

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

This is a well-structured, concise skill that effectively serves as a routing document to deeper reference files. Its main weakness is the lack of concrete, actionable examples—there are no sample interactions, response templates, or specific behavioral patterns shown inline, making it hard to act on without the referenced files. The progressive disclosure and conciseness are strong points.

Suggestions

Add 1-2 brief inline examples showing the expected Socratic questioning style or a sample interaction snippet, so Claude has actionable guidance even before reading sub-files.

Include a fallback instruction for when a referenced file (e.g., conflicts.md) is missing or empty, to improve workflow robustness.

Dimension	Reasoning	Score
Conciseness	Very lean content. Every line serves a purpose—no unnecessary explanations of what a professor is, what Socratic method means, or how distributed systems work. Assumes Claude's competence throughout.	3 / 3
Actionability	Provides a clear ordered list of files to read and rules to follow, but the guidance is entirely referential—there are no concrete examples of how to respond, what tone to use, or sample interactions. The actionability depends entirely on the referenced files.	2 / 3
Workflow Clarity	The numbered steps provide a clear reading sequence, and rule 5 addresses conflict resolution. However, there's no guidance on what to do when referenced files are missing, no validation checkpoint for whether the persona is being applied correctly, and no feedback loop for error cases beyond conflicts.	2 / 3
Progressive Disclosure	Excellent progressive disclosure structure: the SKILL.md serves as a concise overview and router, pointing to five clearly-named one-level-deep reference files (interaction.md, procedure.md, memory.md, personality.md, conflicts.md) with clear descriptions of each file's purpose.	3 / 3
	Total	10 / 12 Passed

Description

25%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is too abstract and lacks concrete actions, specific trigger terms, and clear usage scenarios. While it references a specific teacher (王老师) which provides some distinctiveness, the description reads more like a mission statement than a functional skill description. It fails to communicate what the skill concretely does or when a user would naturally invoke it.

Suggestions

Add specific concrete actions the skill performs, e.g., '以王老师的风格解答数学问题、提供学习建议、批改作业反馈' (answers math questions in Teacher Wang's style, provides study advice, gives homework feedback).

Include natural trigger terms users would actually say, such as specific subjects taught, types of questions, or phrases like '王老师怎么说', '按照王老师的方法'.

Make the 'when to use' clause explicit with concrete scenarios, e.g., '当用户需要以王老师的教学方法获得[具体学科]指导时使用' (Use when the user needs guidance in [specific subject] using Teacher Wang's teaching methods).

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like '蒸馏王老师的指导方式与核心教诲' (distill Teacher Wang's guidance methods and core teachings). No concrete actions are listed - it doesn't specify what the skill actually does (e.g., answer questions in a certain style, provide feedback, explain concepts).	1 / 3
Completeness	The description attempts to answer both 'what' (distill Teacher Wang's guidance and teachings) and 'when' (用于延续导师的教学智慧与指导风格，辅助学习与回顾 - for continuing the mentor's teaching wisdom, assisting learning and review). However, the 'when' clause is vague and lacks explicit triggers. It has a 'Use when' equivalent but it's too abstract to be actionable.	2 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like '蒸馏' (distill), '核心教诲' (core teachings), and '指导风格' (guidance style) are abstract and unlikely to match user queries. There are no concrete trigger terms like specific subjects, teaching scenarios, or common user phrases.	1 / 3
Distinctiveness Conflict Risk	The mention of a specific person '王老师' (Teacher Wang) provides some distinctiveness, but the overall framing around 'teaching wisdom' and 'guidance style' is generic enough to overlap with any teaching or mentoring skill. The niche is somewhat defined by the specific teacher but the functional scope is unclear.	2 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	9 / 11 Passed

Repository: agenmod/immortal-skill
Path: examples/mentor-demo/SKILL.md
Commit: cdab91b

Reviewed: about 14 hours 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.