CtrlK
BlogDocsLog inGet started
Tessl Logo

settings-guide-skill

当用户问 OpenLoaf 桌面端产品内的设置、偏好、API key、模型切换、主题 / 语言 / 快捷键 / 代理 / 备份、或相关故障(key invalid、model not found)该在哪配置、怎么配置时触发。**不用于**:项目里的代码配置文件如 tsconfig / .env(→直接用 Read/Edit)、一般编程问题(→直接回答)、系统级 OS 设置。

77

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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, lean, and highly actionable settings-guidance skill that uses tables and a decision tree efficiently and gives concrete UI paths and example contrasts. Workflow clarity sits just below the top because it lacks explicit feedback/recovery loops, though none are required for this non-destructive guidance task.

Suggestions

Consider adding an explicit 'verify the fix worked' loop at the end of the troubleshooting decision tree (e.g., re-test the failing operation and fall back to the search-first fallback if the issue persists) to push workflow_clarity toward 5.

The 配置地图 table and the 故障排查决策树 overlap slightly on proxy/network and project-path entries; a one-line cross-reference could reduce duplication without adding tokens.

DimensionReasoningScore

Conciseness

Lean and token-efficient — content is carried by tables, a decision tree, and contrast examples rather than prose; it assumes Claude's competence and avoids explaining concepts Claude already knows.

5 / 5

Actionability

Highly concrete guidance for an instruction-only skill: exact UI paths ('设置 → AI 模型 → Provider 管理 → 点击对应 Provider → 编辑 API Key'), a concrete proxy example (http://127.0.0.1:7890), and explicit wrong-vs-right answer contrasts covering common cases.

5 / 5

Workflow Clarity

The 4-step answering strategy and the troubleshooting decision tree give a clear sequence with branching checkpoints, but there are no explicit validate→fix→retry feedback loops — appropriate for a non-destructive guidance skill but one notch below the top anchor.

4 / 5

Progressive Disclosure

Self-contained single-purpose guidance doc with well-organized sections (工具清单, 配置地图, 故障排查决策树, 安全原则, 隐私说明, 常见错误示范, 回答策略) and no nested or missing external references — fits the simple-skill exception for scoring 5 with well-organized sections.

5 / 5

Total

19

/

20

Passed

Description

100%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 highly specific, well-triggered, and clearly bounded description that covers a comprehensive range of concrete config areas and failure phrases while explicitly demarcating what the skill is not for.

DimensionReasoningScore

Specificity

Names the domain (OpenLoaf desktop settings) and multiple concrete config areas and failure types ('API key、模型切换、主题 / 语言 / 快捷键 / 代理 / 备份', 'key invalid、model not found'), giving comprehensive concrete coverage.

5 / 5

Completeness

Explicitly answers what (guide to where/how to configure desktop settings) and when (the trigger clause '当用户问…该在哪配置、怎么配置时触发'), plus an explicit '不用于' exclusion list.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms users would actually say — '设置', '偏好', 'API key', '模型切换', '主题', '语言', '快捷键', '代理', '备份' — plus error phrases 'key invalid' / 'model not found'.

5 / 5

Distinctiveness Conflict Risk

Bounded to the OpenLoaf desktop product with explicit exclusions (code config files → Read/Edit, general programming → answer directly, OS settings), giving a clear niche with minimal conflict risk.

5 / 5

Total

20

/

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
itsablabla/openloaf-web
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.