CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-api-reference

Produces API reference documentation for Next.js APIs: functions, components, file conventions, directives, and config options. **Auto-activation:** User asks to write, create, or draft an API reference page. Also triggers on paths like `docs/01-app/03-api-reference/`, or keywords like "API reference", "props", "parameters", "returns", "signature". **Input sources:** Next.js source code, existing API reference pages, or user-provided specifications. **Output type:** A markdown (.mdx) API reference page with YAML frontmatter, usage example, reference section, behavior notes, and examples.

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 high-quality instruction skill: it provides a complete page template, per-category guidance, mechanical rules with Don't/Do examples, and a workflow ending in an explicit review checklist. The content is lean and actionable with only minor redundancy and a single-file structure that is acceptable at this size.

DimensionReasoningScore

Conciseness

The body is dense, instructional, and free of concept-teaching padding: a full page template, 13 numbered rules, Don't/Do tables, and a 7-step workflow with almost every token earning its place. It stays at 4 rather than 5 because of minor redundancy between the template's inline comments and the "Category-specific notes" section, and some rules could be tightened.

4 / 5

Actionability

The guidance is fully executable: a copy-paste-ready .mdx template with placeholders, per-category variants (e.g., "Functions: Lead with the function signature and `await` if async"), explicit mechanical rules ("Use `switcher` for tsx/jsx pairs", "No em dashes"), and Don't/Do example pairs that concretely disambiguate each rule. The References section points to real exemplar pages for each category.

5 / 5

Workflow Clarity

The Workflow section gives a clear 7-step sequence (gather context, categorize, read source, check e2e tests, check related docs, write, review) culminating in an explicit validation checklist: "Review against the rules. Verify: one sentence opener, immediate code example, correct `switcher`/`filename` usage, tables vs subsections, 'Good to know' format, no em dashes, mechanical language." This is document-writing, not a destructive or batch operation, so no cap applies.

5 / 5

Progressive Disclosure

Sections are well organized (Goal, Structure, Rules, Workflow, References) and the References section is one level deep, clearly signaling what each exemplar demonstrates ("cookies.mdx - Function with methods table, options table, and behavior notes"). No bundle files exist, so all guidance lives inline in a ~148-line body; that is appropriate for a writing-style skill but keeps it at "good structure with minor organization gaps" rather than a fully split overview.

4 / 5

Total

18

/

20

Passed

Description

87%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: it defines what the skill produces, scopes the five API categories, specifies input sources and the output format, and gives an explicit auto-activation clause with concrete keywords and paths in third-person voice. The only gaps are minor missing keyword synonyms (e.g., "API docs", ".mdx").

DimensionReasoningScore

Specificity

The description names the domain and enumerates concrete scope ("functions, components, file conventions, directives, and config options") plus a specific output format ("markdown (.mdx) API reference page with YAML frontmatter, usage example, reference section, behavior notes, and examples"). It stays at 4 rather than 5 because the core capability is a single action (producing reference pages) rather than multiple distinct actions; it is above 3 because the scope enumeration and output specification go well beyond 1-2 generic actions.

4 / 5

Completeness

It explicitly answers both questions: "what" ("Produces API reference documentation for Next.js APIs...") and "when" ("**Auto-activation:** User asks to write, create, or draft an API reference page. Also triggers on paths... or keywords...") with concrete trigger phrases. Voice is third-person throughout ("Produces", "triggers"), matching the guideline.

5 / 5

Trigger Term Quality

Explicit natural keywords are listed: "'API reference', 'props', 'parameters', 'returns', 'signature'" plus path triggers like "docs/01-app/03-api-reference/" and verbs ("write, create, or draft"). Good coverage, but common variations like "API docs", "documentation page", or ".mdx" are missing, so it does not reach the comprehensive-with-synonyms level of 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Next.js API reference pages) with distinct triggers (specific paths and doc-writing keywords); it would not plausibly fire for unrelated skills, and the scoped enumeration removes overlap risk with general Next.js skills.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

vercel/next.js

Path

.agents/skills/write-api-reference/SKILL.md

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.