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

77%Weight 40%Scale 1-3

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-sequenced skill body with concrete code and clear workflows. The main weaknesses are redundancy between protocol sections and heavy inline reference/detail content that would benefit from being split into bundle files.

Suggestions

Deduplicate the streaming error pattern: the Protocol Snapshot table, the 'Streaming endpoint' code block, and the 'Frontend Stream Parsing Pattern' section all restate the {type:'error'} contract — keep one canonical statement and cross-reference it.

Move the 'Migrated Endpoints Reference' tables and 'Key Files' index into a reference bundle file (e.g. references/endpoints.md) and link to it, reducing inline historical detail and improving progressive_disclosure.

Tighten the Log Sanitization section by collapsing the two utility examples and the 'When to Use What' table, or by moving the detailed filter pattern list into the referenced docs/dev-guides/2-log-sanitization.md.

Dimension	Reasoning	Score
Conciseness	The body is dense and project-specific without explaining basic concepts, but it carries redundancy — the Protocol Snapshot table overlaps the HTTP Status Code Policy, the streaming pattern is restated in 'Frontend Stream Parsing Pattern', and the Migrated Endpoints Reference tables are historical detail that could be trimmed.	2 / 3
Actionability	Executable Python and TypeScript examples with real imports, concrete function names, and exact JSON shapes make the guidance copy-paste ready (e.g. AppError raising, streamRequest consumption).	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with checkpoints — the numbered 'Adding a New Error Code' flow, the 'Empty Catch Policy' decision tree, and the 'Debugging Error Propagation' diagnostic feedback loop.	3 / 3
Progressive Disclosure	Sections are well-organized and the two dev-guide references are one-level-deep and clearly signaled, but ~380 lines of reference-style detail (Migrated Endpoints tables, Key Files, Log Sanitization layers) live inline rather than in separate bundle files, and no references/ scripts/ or assets/ bundles exist.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 answers both what and when with explicit, natural trigger terms and a distinct niche. Its only weakness is that the 'what' is a system name rather than a list of concrete actions.

Dimension	Reasoning	Score
Specificity	The phrase '统一错误处理系统' names the domain as a system rather than listing concrete actions the skill performs, while the trigger clause enumerates concrete scenarios; it names domain and some actions but is not comprehensive.	2 / 3
Completeness	It states what the skill is ('统一错误处理系统') and gives an explicit '在…时使用' trigger clause covering multiple scenarios, answering both what and when.	3 / 3
Trigger Term Quality	Natural developer phrasings are covered — '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' — which a user would plausibly say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The unified error-handling niche for this codebase with specific triggers (API endpoints, error handling, frontend API calls, error tests) is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: 5d4f7b3

Reviewed: 8 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.