language-injection

LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息（message_code）时使用。

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/language-injection/SKILL.md

Quality

Content

82%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, highly actionable reference guide with copy-paste code examples and a useful anti-pattern table. It is token-efficient and points one level deep to an authoritative dev-guide, with only minor redundancy in the dev-guide pointer.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence with no padding about i18n basics; the only redundancy is the authoritative dev-guide pointer being restated in the prerequisites blockquote.	4 / 5
Actionability	Provides copy-paste-ready executable code covering the common cases — route injection, constructor injection (simple and marker variants), message_code with and without params, and frontend consumption.	5 / 5
Workflow Clarity	The 'Adding a New Language' section is a clear 4-step sequence ending in a confirmation ('No Agent code changes needed — picks up automatically'); the rest is reference-style rather than a linear workflow, so no validation cap applies.	4 / 5
Progressive Disclosure	Well-organized into Architecture, Core Modules, Code Examples, Anti-Patterns, and Adding a Language, with a single clearly-signaled one-level reference to the authoritative dev-guide; no bundle files are present to verify further splitting.	4 / 5
	Total	17 / 20 Passed

Description

75%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 solid, third-person description that pairs a clear domain label with an explicit 'use when' clause and three concrete trigger scenarios. It is concise and distinctive, with the only weakness being that the 'what' is a single noun phrase rather than an enumeration of capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('多语言注入规范') and lists several concrete trigger scenarios — modifying Agent prompts, adding Agent endpoints, handling backend messages — with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (multi-language injection spec) and when ('时使用' with three concrete triggers), but the 'what' is a terse label rather than a capability list, keeping it just below a 5.	4 / 5
Trigger Term Quality	Uses natural developer terms ('Agent 提示词', 'Agent 端点', '后端消息') that users would say, though 'message_code' is technical jargon and a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (LLM Agent language injection) with distinct triggers, with only minor overlap risk against a general i18n skill.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/data-formulator
Path: .cursor/skills/language-injection/SKILL.md
Commit: 5477f0e

Reviewed: 28 days ago

Table of Contents

Discovery Implementation Validation

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.