CtrlK
BlogDocsLog inGet started
Tessl Logo

designing-apis

Designs REST and GraphQL APIs including endpoints, error handling, versioning, and documentation. Use when creating new APIs, designing endpoints, reviewing API contracts, or when asked about REST, GraphQL, or API patterns.

64

Quality

80%

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 ./skills/designing-apis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers a clear, checklist-driven design workflow with a genuine validation feedback loop, but it spends significant tokens restating standard HTTP/REST knowledge and its single progressive-disclosure pointer is broken. Fixing the missing OPENAPI-TEMPLATE.md file and trimming textbook boilerplate would raise both actionability and conciseness.

Suggestions

Add the referenced OPENAPI-TEMPLATE.md to the bundle (or remove the reference) — the link in the 'OpenAPI Specification Template' section currently points to a nonexistent file, breaking the skill's only external navigation path.

Cut or relocate textbook material Claude already knows, such as the full HTTP status-code table, the JWT/API-key header examples, and the X-RateLimit header block, into a single reference file or trim them to only the project-specific conventions.

Complete the abbreviated examples — the GraphQL schema's omitted input/connection/error types and the list response's "data": [...] placeholder — so the templates are fully usable without guessing.

DimensionReasoningScore

Conciseness

The body is compact in form (tables and code blocks, no prose padding), but several sections restate knowledge Claude already has: the full HTTP status-code table, "Authorization: Bearer eyJhbGciOiJIUzI1NiIs...", and the X-RateLimit header block are textbook material. This fits the mostly-efficient-with-unnecessary-explanation anchor; it is not a 2 because there is no verbose prose, but not a 4 because the boilerplate sections are genuinely skippable.

3 / 5

Actionability

The URL structure, response format, and GraphQL examples are concrete templates, but there are real gaps: the list response uses "data": [...], the GraphQL schema explicitly omits input/connection/error types "for brevity", and the OpenAPI template — the section that would make designs directly executable as documentation — lives in a referenced file that does not exist in the bundle. This lands between the incomplete-guidance and mostly-executable anchors; the broken reference and placeholder ellipses keep it below 4.

3 / 5

Workflow Clarity

The 7-step copyable progress checklist, the dedicated validation checklist, and the explicit feedback loop ("If validation fails, return to the relevant design step and address the issues") give a clear sequence with explicit validation and error recovery. This matches the anchor for clear sequencing with explicit validation steps, feedback loops, and checklists.

5 / 5

Progressive Disclosure

Sections are well-labeled, but the only external reference — "See [OPENAPI-TEMPLATE.md](OPENAPI-TEMPLATE.md)" — points to a file that is absent from the bundle (no references/ directory exists), leaving a dead navigation path. Additionally, 200+ lines of status-code and response-format reference material that could live in separate files are inlined. This fits the some-structure-but-could-be-better-organized anchor rather than the good-structure anchor, whose references actually resolve.

3 / 5

Total

14

/

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.

A strong description in third person that explicitly pairs concrete capabilities with natural "Use when…" triggers, closely matching the rubric's good examples. The only weaknesses are minor: a few missing trigger synonyms (OpenAPI, Swagger) and slightly broad trigger phrasing that creates small overlap risk.

DimensionReasoningScore

Specificity

"Designs REST and GraphQL APIs including endpoints, error handling, versioning, and documentation" lists several specific concrete actions, matching the anchor for several specific actions with minor gaps. It stops short of a 5 because coverage the skill actually provides (authentication, rate limiting, pagination) is omitted from the description.

4 / 5

Completeness

The description clearly answers both questions: "Designs REST and GraphQL APIs including endpoints, error handling, versioning, and documentation" states what it does, and "Use when creating new APIs, designing endpoints, reviewing API contracts, or when asked about REST, GraphQL, or API patterns" gives explicit, concrete trigger phrases. This matches the anchor for clearly and explicitly answering both what and when.

5 / 5

Trigger Term Quality

Triggers like "creating new APIs", "designing endpoints", "reviewing API contracts", "REST, GraphQL, or API patterns" give good natural keyword coverage, but common user phrases such as "OpenAPI", "Swagger", or "API spec" are missing. This fits the good-coverage-with-a-few-missing-terms anchor rather than the comprehensive synonym/extension coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

REST/GraphQL API design is a clear niche with mostly distinct triggers, but "reviewing API contracts" overlaps with code-review skills and "API patterns" is broad enough to catch general architecture requests. Minor overlap risk with closely related skills fits the 4 anchor; it is not the minimal-conflict profile of a 5.

4 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
CloudAI-X/claude-workflow-v2
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.