writing-reference-docs

How to write a function/hook/action reference section, and how to write or rework a whole app's multi-page doc set (Overview/Features/Talk to the Agent/Cross-App Use/Developer Guide): plain-language signature, real arguments, escalating examples grounded in a real app, verified agent behavior, trimmed prose with no em dashes or semicolons. Use when writing or editing a packages/core/docs/content reference page, or reworking a template-<app>*.mdx doc set.

Quality

82%

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

71%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 well-structured, actionable instruction skill with strong workflow guidance and clean organization. Its main weakness is conciseness: several paragraphs of revision-history backstory inflate the body without adding guidance Claude can act on.

Suggestions

Cut or compress the origin-story openings (the 'This came out of rewriting client-data.mdx...' intro and the 'It came out of reworking Forms' / 'came out of reworking Slides' intro lines) to one sentence or remove them; the Rule and How sections already convey the shape.

Tighten the Why section: keep the concrete failure mode (hidden enabled/onSuccess needs, unconvincing hypothetical domain) but drop the narrative framing so the rationale reads as a bullet, not a retelling.

Promote the implicit validation checks into explicit pass/fail gates where a destructive path exists, e.g. frame 'verify the app actually has the underlying capability (grep for ExtensionSlot...)' as a 'Only if the grep hits: include the section. Otherwise omit.' checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable but carries repeated origin-story padding ('This came out of rewriting client-data.mdx's hook sections... with the user', 'It came out of reworking Forms' docs', 'came out of reworking Slides' Overview intro paragraph') that does not earn its tokens and could be trimmed without losing guidance.	3 / 5
Actionability	Provides concrete numbered steps, a markdown argument-list template, named source paths (packages/core/src/client/, the docs-slug-redirects.ts file), and runnable commands (pnpm guard:i18n-catalogs), with only minor gaps for an instruction-only skill.	4 / 5
Workflow Clarity	An explicit 8-step How sequence with real validation checkpoints (read source before listing args, grep sibling pages for the running domain, grep for a capability before copying its section, the Verify Agent-Driven Claims loop) and a redirect prerequisite before page deletion; a few checkpoints are implicit rather than framed as pass/fail gates.	4 / 5
Progressive Disclosure	No bundle files are needed and none are referenced; the single SKILL.md is organized into clear, navigable sections (Rule/Why/How/Don't/App Doc Format/Voice/Verify/Retiring/Localizing/Related Skills) with only one-level sibling-skill links, so structure is appropriate for its scope.	5 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that clearly states both the capability and the trigger conditions for a well-scoped internal docs skill. The only minor gap is trigger-term naturalness, which is constrained by the skill's inherently internal vocabulary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (write a function/hook/action reference section, write or rework a whole app's multi-page doc set) and enumerates the required shape (plain-language signature, real arguments, escalating examples, verified agent behavior, trimmed prose), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (how to write these reference sections and doc sets, including the required shape) and when (an explicit 'Use when writing or editing... or reworking...' clause with concrete triggers).	5 / 5
Trigger Term Quality	'writing or editing a packages/core/docs/content reference page, or reworking a template-<app>*.mdx doc set' provides good natural trigger coverage for this niche, though the terms are internal/technical and a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger is pinned to specific paths and file patterns (packages/core/docs/content reference pages, template-<app>*.mdx doc sets), giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	11 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/writing-reference-docs/SKILL.md
Commit: a941a2e

Reviewed: 9 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.