CtrlK
BlogDocsLog inGet started
Tessl Logo

api-development

FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。

61

Quality

72%

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/system/api-development/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The content is highly actionable with executable code, clear file locations, and a well-sequenced validated workflow, but it suffers from heavy repetition and a monolithic structure with no progressive disclosure to offload reference material. Basic-Zod and repeated examples inflate the token budget.

Suggestions

De-duplicate the API-declaration header block and zod meta pattern by defining them once and referencing the template; remove or trim the '常用 Zod 验证方法' section that re-teaches basic Zod Claude already knows.

Split the quick reference and the five common-problem error/correct pairs into a separate reference file (e.g. references/common-issues.md) and link to it one level deep, keeping SKILL.md as a lean overview.

Replace the non-portable absolute reference paths (e.g. '/Volumes/code/fastgpt-pro/FastGPT/...') with repository-relative paths so the references are usable outside the original machine.

DimensionReasoningScore

Conciseness

The guide is mostly concrete project-specific guidance, but it repeats the API-declaration header block and zod meta pattern 3-4 times and includes a '常用 Zod 验证方法' quick-reference that re-explains basic Zod methods (z.string(), .min(), z.array()) Claude already knows; it could be tightened considerably.

2 / 3

Actionability

Provides concrete file locations ('packages/global/openapi/[module]/[api].ts'), full executable TypeScript examples with real imports (NextAPI, authApp, MongoUser, APIError, CommonErrEnum.missingParams), and copy-paste-ready templates rather than pseudocode.

3 / 3

Workflow Clarity

A clear 4-step sequence (定义 Schema → 实现路由 → 权限验证 → 错误处理) with explicit 🔴 validation checkpoints (schema.parse on input and output), a try/catch→APIError recovery path, and a 审查检查清单 checklist for complex review.

3 / 3

Progressive Disclosure

Well-organized into clear sections, but it is a ~760-line monolith with no bundle files and content (quick reference, five common-problem pairs, full examples) that could be split out; the only references are external/local absolute paths rather than clearly-signaled one-level-deep bundle files.

2 / 3

Total

10

/

12

Passed

Description

67%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.

The description is specific and clearly scoped to FastGPT API development with zod/OpenAPI, but it omits any explicit 'Use when...' trigger guidance and leans on technical jargon over natural user phrasing. It answers 'what' well but not 'when'.

Suggestions

Add an explicit 'Use when...' clause in Chinese (e.g. 'Use when 开发新的 FastGPT Next.js API 路由、修改入参/出参、或编写 OpenAPI 文档时') so the trigger is explicit rather than only implied by the body's '何时使用此技能' section.

Broaden trigger terms with natural phrasings a user would actually say (e.g. 'API 路由', '接口开发', '参数校验') alongside the existing technical jargon.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '使用 zod schema 定义入参和出参', '声明路由信息', '编写对应的 OpenAPI 文档', '使用 schema.parse 进行验证' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers 'what' but lacks any 'Use when...' or equivalent explicit 'when' guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant domain keywords a FastGPT developer would say ('zod schema', 'OpenAPI 文档', 'schema.parse', '入参和出参') but is technical-jargon heavy and misses common natural variations and an explicit trigger phrase.

2 / 3

Distinctiveness Conflict Risk

The 'FastGPT API 开发规范' niche combined with zod schema + OpenAPI + schema.parse is a clear, distinctive domain unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (766 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
labring/FastGPT
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.