Name: doc-author
Rating: 60.8 (1 reviews)
Author: InsForge

doc-author

Write, edit, and maintain documentation. Use for collaborative drafting, autonomous writing, or improving existing docs. Defaults to collaborative mode where the human makes final decisions. Built by Mintlify.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/doc-author/SKILL.md

Quality

Content

63%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 is a well-structured, actionable instruction skill with a clear workflow and self-review checkpoint, but it is longer than necessary and inlines reference-style content (Mintlify components, examples) that would be better split into bundle files. The dangling ./INSFORGE.md reference is a concrete progressive-disclosure defect.

Suggestions

Move the Mintlify component reference and the worked examples into separate reference files (e.g. references/mintlify-components.md, references/examples.md) and link to them from the body to improve progressive disclosure.

Trim the style-guardrails section ('Voice and structure', 'What to avoid', 'AI-typical patterns') which restates knowledge Claude already has, keeping only Mintlify-specific deviations.

Either create ./INSFORGE.md or remove the reference to it from the header comment so the skill does not signal a file that is absent.

Dimension	Reasoning	Score
Conciseness	The ~440-line body is mostly efficient and contains genuinely useful Mintlify-specific guidance, but it also restates concepts Claude already knows (second-person/active-voice rules, lists of filler words like 'moreover, furthermore') and includes padded dialogue examples that could be tightened, placing it above 'noticeably verbose' but with more than minor over-explanation.	3 / 5
Actionability	It gives concrete, executable guidance including an exact MDX frontmatter template, real Mintlify component usage, root-relative link and TODO formats, worked good/poor examples, and a self-review checklist, with only minor gaps such as the abstract treatment of git/PR mechanics.	4 / 5
Workflow Clarity	A clear numbered six-step Workflow includes an explicit self-review validation checkpoint before submit and an autonomous-mode 'always open a PR, never commit directly' guardrail, but it lacks an explicit fix-and-revalidate retry loop tied to that checklist.	4 / 5
Progressive Disclosure	Section structure is well organized, but the skill is ~440 lines (well over the 50-line simple-skill threshold), inlines content like the Mintlify component reference and examples that could live in separate files, and the one signaled reference (./INSFORGE.md in the header comment) points to a file that does not exist with no bundle files present.	3 / 5
	Total	14 / 20 Passed

Description

80%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.

The description is specific, answers both what and when with a 'Use for...' trigger clause, and is mostly distinct from adjacent skills. Its main weakness is trigger-term breadth and the fact that the Mintlify/MDX specialization lives in the compatibility field rather than the description, slightly limiting distinctiveness and trigger coverage.

Suggestions

Add an explicit 'Use when...' clause with concrete user-uttered triggers (e.g. 'Use when the user asks to write, update, or improve docs, READMEs, guides, or MDX pages') to push completeness and trigger-term quality toward 5.

Surface the Mintlify/MDX specialization directly in the description (e.g. mentioning MDX pages or Mintlify components) to sharpen distinctiveness against general writing skills.

Include common synonyms users actually say ('docs', 'technical writing', 'user guides') alongside 'documentation' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the documentation domain and lists multiple concrete actions across the skill's modes ('Write, edit, and maintain', 'collaborative drafting, autonomous writing, or improving existing docs'), giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	It states clearly what the skill does and provides a near-equivalent 'Use for...' trigger clause naming concrete scenarios, satisfying both what and when, though the 'when' is mode-oriented rather than user-utterance-oriented so it is not the fully explicit trigger phrasing of a 5.	4 / 5
Trigger Term Quality	Natural keywords like 'documentation', 'collaborative drafting', 'autonomous writing', and 'improving existing docs' are present, but common synonyms a user might say (e.g. 'docs', 'technical writing', 'README', 'guides') are missing, so coverage is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'write, edit, and maintain documentation' framing with collaborative/autonomous mode distinction is mostly distinct with only minor overlap risk against general writing helpers, but the Mintlify/MDX specialization that would give it a clearly distinct niche is not surfaced in the description itself.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: InsForge/InsForge
Path: .claude/skills/doc-author/SKILL.md
Commit: a93d362

Reviewed: 1 day 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.