CtrlK
BlogDocsLog inGet started
Tessl Logo

user-guide

HanaAgent 用户说明书。解答用户关于软件使用方法、功能介绍、常见问题和实用技巧的疑问。 MANDATORY TRIGGERS: 怎么用, 使用方法, 说明书, 帮助文档, 新手指南, 怎么设置, 功能介绍, how to use, user guide, help, getting started, 教程, tutorial, 这是什么功能, 怎么操作

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills2set/user-guide/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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 well-structured, actionable user guide that benefits from clear sectioning, concrete UI paths, and named commands. Its main weaknesses are notable verbosity from repeated coverage of the same features across sections and the absence of validation checkpoints in destructive/security workflows.

Suggestions

Consolidate duplicated material: 电脑控制, 视觉桥接, 访问模式, and owner/visitor mode are each explained in multiple sections — keep one canonical explanation and cross-reference it to cut length.

Add explicit validation/checklist steps to destructive and security workflows (e.g., 'after enabling Owner, verify by sending a test message and confirming full tool access') so workflow clarity can exceed 3.

Move the 常见问题 entries that restate earlier content into brief cross-references to the relevant section, and reserve the FAQ for genuinely new troubleshooting steps.

DimensionReasoningScore

Conciseness

The ~560-line body is noticeably verbose for a user guide, with several sections restating the same information (e.g., 电脑控制 appears both in 九、安全与隐私 and 十四、实用技巧 and the FAQ; vision bridge and 访问模式 are each explained two or three times). While accurate, much of the repetition and conversational padding could be trimmed, placing it below the efficient midpoint.

2 / 5

Actionability

Most guidance is concrete and executable: specific UI paths (设置 → 助手 → 经验), named slash commands (/compact, /xing, /rc), and exact steps for enabling features. It is mostly actionable with minor gaps such as 'use cron 工具' without syntax, so just short of fully copy-paste ready.

4 / 5

Workflow Clarity

Multi-step processes like 首次打开 and 电脑控制开启 are numbered and sequenced, but they lack validation checkpoints. The destructive/batch-relevant operations (清空记忆 with confirmation, owner/visitor security model) are described without explicit validate-then-act feedback loops, which caps clarity at 3 per the destructive-operation guideline.

3 / 5

Progressive Disclosure

The content is well-organized into clearly numbered top-level sections (一 through 十四 plus 常见问题) with consistent sub-headings, making navigation easy. There are no external bundle files and content is one level deep, but the inlined FAQ repeats earlier-section material rather than being split, leaving a minor organization gap.

4 / 5

Total

13

/

20

Passed

Description

88%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.

A strong description that clearly states its purpose and provides an explicit, comprehensive trigger list in both Chinese and English. It is specific and complete with minor overlap risk only because generic help/tutorial keywords are broadly shared.

DimensionReasoningScore

Specificity

Description names the domain (HanaAgent user guide) and a concrete set of capabilities (software usage, feature introduction, FAQs, practical tips), with several specific concrete topics rather than a single vague action. It falls slightly short of comprehensive multi-action coverage and lacks granularity of individual features, so a 4 rather than 5.

4 / 5

Completeness

It explicitly states what it does (解答用户关于软件使用方法、功能介绍、常见问题和实用技巧的疑问) and provides an explicit 'Use when...' trigger clause (MANDATORY TRIGGERS), clearly answering both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

It includes a comprehensive MANDATORY TRIGGERS list of natural phrases users would actually say (怎么用, 使用方法, 说明书, how to use, user guide, tutorial, etc.), covering synonyms, Chinese and English variations, and question forms — matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

The triggers are fairly specific to user-guide/usage questions for this particular app, giving a clear niche, but the generic help/tutorial terms could still overlap with other general help or documentation skills, leaving minor conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (568 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
liliMozi/openhanako
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.