CtrlK
BlogDocsLog inGet started
Tessl Logo

create-setting-item

指导如何在 Project Graph 项目中创建新的设置项。当用户需要添加新的设置项、配置选项或需要了解设置系统的实现方式时使用此技能。

64

Quality

75%

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 ./.agents/skills/create-setting-item/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A highly actionable, well-structured procedural skill with concrete code at real paths. Its main weaknesses are a duplicated worked example that hurts conciseness and the absence of a validation checkpoint for the batch translation-editing step.

Suggestions

Add an explicit verification checkpoint after step 3 (e.g. confirm each locale .yml file contains the new key and the app builds/types-checks) to lift workflow clarity for the batch translation edit.

Trim or cross-reference the 完整示例 section instead of re-stating all five steps, since it largely repeats the per-step guidance above.

Expand the description's trigger terms with a few more natural phrasings (e.g. '配置项', '设置页面', '添加设置') to broaden recall.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's knowledge of Zod/React, but the complete worked example (完整示例) re-walks the same five steps already detailed above, adding verbosity that could be tightened.

2 / 3

Actionability

Every step ships executable, copy-paste-ready code at concrete file paths (e.g. app/src/core/service/Settings.tsx), with real Zod/YAML/TSX examples — matching the fully-executable anchor.

3 / 3

Workflow Clarity

The five steps are clearly sequenced, but step 3 (editing every locale file) is a batch operation with no explicit validate/checkpoint to confirm translations were added correctly, capping the score at 2 per the batch-operations guidance.

2 / 3

Progressive Disclosure

Sections are well-organized and the manage-translations reference is cleanly signaled, but no bundle files exist and the inline full example duplicates content; organization is good but not optimally separated.

2 / 3

Total

9

/

12

Passed

Description

85%

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 concise third-person description that clearly states both what the skill does and when to use it, scoped to a distinct niche. Trigger-term coverage is good but could include a broader range of natural phrasings.

DimensionReasoningScore

Specificity

Names the domain (Project Graph 设置项) and several concrete actions: 添加新的设置项、配置选项、了解设置系统的实现方式 — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers 'what' (指导如何在 Project Graph 项目中创建新的设置项) and 'when' (当用户需要添加新的设置项、配置选项或需要了解设置系统的实现方式时使用此技能), matching the clear what-and-when anchor.

3 / 3

Trigger Term Quality

Includes natural terms like 设置项 and 配置选项, but coverage of common phrasings a user might say is moderate and missing some variations, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

Scoped to the Project Graph settings system with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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
graphif/project-graph
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.