docs-conventions

Use when writing or reviewing Flet documentation, including Python docstrings (Google style, reST roles, admonitions), Markdown docs (cross-references, images, code examples), and sidebar navigation.

Quality

88%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, concise reference of Flet-specific documentation conventions with strong code examples and a clear verify step. Its only gap is progressive disclosure: all detail lives inline in SKILL.md with no reference files to offload the lengthy rule tables.

Suggestions

Move the detailed reST role and xref rule tables into a references/ file (e.g. references/cross-refs.md) and keep SKILL.md as a concise overview with a one-level-deep link, improving progressive disclosure.

Consider extracting the front matter / image / sidebar specifics into a references/ doc so the main skill stays a scannable index of conventions.

Dimension	Reasoning	Score
Conciseness	The body is dense but consists entirely of project-specific conventions Claude would not know (CrocoDocs role syntax, xref key format, front matter fields); it avoids explaining general concepts and every section earns its tokens.	3 / 3
Actionability	Provides concrete, copy-paste-ready examples for every topic — reST role snippets, xref syntax, markdown links, admonition blocks, <Image>/<CodeExample> JSX, and a sidebar YAML example with exact rules.	3 / 3
Workflow Clarity	Each convention is presented as an unambiguous action; the risky-ish regenerate step includes an explicit verify cue ('verify with a build or yarn crocodocs:generate') and a clear edit-then-regenerate sequence.	3 / 3
Progressive Disclosure	Sections are well-organized, but the ~200-line body is entirely inline with no bundle files in references/scripts/assets and no one-level-deep references to split out the detailed role/xref rule tables.	2 / 3
	Total	11 / 12 Passed

Description

85%

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, well-scoped description that covers both capabilities and explicit trigger conditions for Flet documentation work. Trigger-term quality is the only weak spot, leaning on internal jargon alongside natural terms.

Suggestions

Add everyday phrasings alongside technical terms, e.g. 'Use when writing or reviewing Flet docs, docstrings, or navigation — including Google-style docstrings, cross-references, images, code examples, and sidebar edits.'

Consider including user-natural variants such as 'docs', 'API docs', or 'docstrings' as plain keywords rather than only 'reST roles' and 'admonitions'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'writing or reviewing', 'Python docstrings (Google style, reST roles, admonitions)', 'cross-references, images, code examples', and 'sidebar navigation' — rather than vague abstractions.	3 / 3
Completeness	Explicitly answers both what it does ('writing or reviewing Flet documentation, including ...') and when to use it via the 'Use when' clause, matching the anchored example for full completeness.	3 / 3
Trigger Term Quality	Natural terms like 'documentation', 'docstrings', and 'docs' are present, but they are mixed with technical jargon ('reST roles', 'admonitions') that users may not naturally say, and common variations are only partially covered.	2 / 3
Distinctiveness Conflict Risk	Scoped to 'Flet documentation' specifically, a clear niche with distinct triggers unlikely to overlap with other skills.	3 / 3
	Total	11 / 12 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
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: flet-dev/flet
Path: .agents/skills/docs-conventions/SKILL.md
Commit: db0df8e

Reviewed: 4 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.