CtrlK
BlogDocsLog inGet started
Tessl Logo

i18n-development

国际化 (i18n) 开发指南。在添加新文本、创建物品/事件、修改翻译或管理 PO/MO 文件时使用。

76

Quality

93%

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

87%

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

The body is lean, actionable, and well-structured with concrete commands and code, and no bundle files are needed or broken. The main gap is workflow_clarity: the build-heavy workflows lack an explicit validation/verification feedback loop after compilation.

Suggestions

Add an explicit verification step after build_mo.py (e.g. confirm the .mo was regenerated and spot-check that new strings render in-game) to turn the rebuild into a validate->fix->retry loop.

For the CSV and JSON/effect workflows, add a short validation checkpoint (run a PO linter or verify msgfmt compiles the module cleanly) before declaring the change done.

Consider a one-line note on how to detect a failed/stale build so the 'always rebuild' rule has a corresponding 'confirm it worked' check.

DimensionReasoningScore

Conciseness

Lean and token-efficient with no padding or explanations of concepts Claude already knows; every line earns its place. Not score 2 because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Provides fully executable commands ('python tools/i18n/build_mo.py', 'python tools/i18n/extract_csv.py') and a real, copy-paste-ready Python example with the t() call. Not score 2 because guidance is complete and executable rather than pseudocode.

3 / 3

Workflow Clarity

Steps are clearly sequenced (numbered CSV workflow, emphasized rebuild step), but the build/compile operations lack an explicit validation or verify-the-output feedback loop. Per the rubric, missing verification in batch/compile operations caps this at 2 rather than 3.

2 / 3

Progressive Disclosure

A single well-organized file with clear sections and no external references; per scoring_notes a short single-purpose skill with no needed bundle files scores 3 on well-organized sections. Not score 2 because organization is clear, not monolithic or under-organized.

3 / 3

Total

11

/

12

Passed

Description

100%

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 is concise yet complete: it names several concrete i18n actions, supplies natural trigger terms, and explicitly states when to use the skill in third-person voice. It is distinctive within the PO/MO translation domain with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '添加新文本', '创建物品/事件', '修改翻译', '管理 PO/MO 文件' — matching the 'multiple specific concrete actions' anchor; not score 2 because it goes beyond naming a domain and a couple of actions.

3 / 3

Completeness

Explicitly answers both what (i18n dev guide) and when via the clause '在...时使用', satisfying the explicit-trigger requirement that prevents a cap at 2.

3 / 3

Trigger Term Quality

Natural keywords a user would say are well covered: '翻译', 'PO/MO 文件', '新文本', '物品/事件'; not score 2 because common variations are present rather than missing.

3 / 3

Distinctiveness Conflict Risk

The PO/MO translation niche with i18n-specific triggers is clearly distinct from other skills and unlikely to fire for the wrong skill; not score 2 because it is not merely 'somewhat specific'.

3 / 3

Total

12

/

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
4thfever/cultivation-world-simulator
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.