error-handling

统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用。

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

The body is a dense, actionable reference with executable code and clear file-level navigation. It is strong on actionability but carries some inline reference bulk that could be offloaded, and a few risky workflows omit explicit validation feedback loops.

Suggestions

Move the Migrated Endpoints Reference tables into a separate bundled reference file and link to it from SKILL.md to improve progressive disclosure and token efficiency.

Add an explicit validate/retry feedback loop (e.g., confirm the new error code appears in ERROR_CODE_HTTP_STATUS only for auth codes, re-run failing test) to the Adding a New Error Code workflow.

Trim explanatory paragraphs around legacy formats and special-case rules into terse bullets to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense tables and executable code blocks, though the Migrated Endpoints Reference tables and some explanatory paragraphs could be trimmed for token economy.	4 / 5
Actionability	Provides fully executable, copy-paste-ready code for backend endpoints, streaming, frontend consumption, and log sanitization, with concrete file paths and function names covering common cases.	5 / 5
Workflow Clarity	Sequenced workflows exist (Adding a New Error Code, New Module Checklist, Debugging steps) with checkpoints, but the destructive/error-path workflows lack explicit validate-then-retry feedback loops.	4 / 5
Progressive Disclosure	Well-organized sections with a Key Files table pointing to real source files and Prerequisites naming specific dev-guide docs; bulk reference material is mostly inline rather than split into bundle files, which keeps it slightly below a 5.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

The description is concise, third-person, and answers both what and when with concrete trigger phrases. It is well-scoped to a unified error-handling domain with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('统一错误处理系统') and lists several concrete trigger actions ('添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试'), with only minor coverage gaps.	4 / 5
Completeness	Clearly states what the skill is ('统一错误处理系统') and an explicit 'when' trigger clause ('在...时使用') covering multiple concrete scenarios.	5 / 5
Trigger Term Quality	Natural phrases like '添加 API 端点' and '修改错误处理' map to things a user would actually say, with good keyword coverage though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Scoped to a specific error-handling system with distinct triggers; minor overlap risk only with closely related backend/logging skills.	4 / 5
	Total	17 / 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/error-handling/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.