CtrlK
BlogDocsLog inGet started
Tessl Logo

file-reader

文件读取技能。当用户需要读取文件内容、查看文件、cat 文件时激活。支持读取文本文件、配置文件、代码文件等。

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/file-reader/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is well-structured, brief, and gives an executable command with a clear parameter table; its only real weakness is a redundant overview section that duplicates the frontmatter description.

Suggestions

Remove or condense the '概述' section, which restates the frontmatter description verbatim, to eliminate redundant tokens and raise conciseness to 3.

Add a brief one-line note on output behavior or error handling (e.g., what happens when the file is missing or unreadable) to strengthen actionability for edge cases.

DimensionReasoningScore

Conciseness

The body is short and lean, but the '概述' section repeats the frontmatter description verbatim, adding redundant tokens that could be removed; mostly efficient but with avoidable duplication.

2 / 3

Actionability

Provides an executable command ('python read.sh "<file>"') plus a parameter table that is copy-paste ready and complete for this single-task skill, matching the fully-executable anchor.

3 / 3

Workflow Clarity

This is a simple single-purpose skill with an unambiguous single action; per the rubric's simple-skills note, a clear unambiguous single action can score 3 without an explicit multi-step workflow.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references and is organized into clear sections (overview, usage, parameters), satisfying the rubric's criterion for simple skills to score 3 on progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

67%

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 covers both what and when with an explicit activation trigger and natural phrasing including 'cat', but the capability list is narrow and the skill domain is generic enough to risk overlap with other skills.

Suggestions

Enumerate more concrete actions or distinct capabilities (e.g., reads single or multiple files, handles large files, streaming) to lift specificity from 2 to 3.

Add more natural trigger variations users would say (e.g., 'open file', 'view file contents', 'show me the file') to broaden trigger-term coverage.

Tighten the niche by stating what makes this reader distinct (e.g., output formatting or size handling) to reduce conflict risk with other file-handling skills.

DimensionReasoningScore

Specificity

Names the domain ('文件读取技能') and lists supported file types ('文本文件、配置文件、代码文件') but does not enumerate multiple distinct concrete actions beyond 'read', matching the anchor that names domain and some actions but is not comprehensive.

2 / 3

Completeness

Explicitly states what the skill does ('支持读取文本文件、配置文件、代码文件') and provides an explicit when-trigger ('当用户需要读取文件内容、查看文件、cat 文件时激活'), satisfying both what and when.

3 / 3

Trigger Term Quality

Includes natural user phrasings ('读取文件内容、查看文件、cat 文件') including the colloquial 'cat', but is missing common variations such as 'open file' or 'view file contents', so coverage is partial rather than complete.

2 / 3

Distinctiveness Conflict Risk

A generic file-reading skill could overlap with many skills; the triggers are somewhat specific but the domain is broad, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

9

/

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
UnicomAI/wanwu
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.