content

Use Content for repo-backed Markdown/MDX docs, blogs, resources, rich document editing, local components, shareable copies, and Content local-file workspaces. Prefer Content actions over raw filesystem writes when available.

Quality

73%

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 ./skills/content/SKILL.md

Quality

Content

68%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 lean, well-structured instruction skill with concrete commands, an explicit tool-availability fallback path, and clear boundaries. Its main weaknesses are the absence of validation/verification steps around destructive operations and a long inline configuration example that could be split out.

Suggestions

Add a verification step after destructive or batch operations (e.g., re-run get-document or refresh-list and confirm the expected state before reporting success) to lift the workflow-clarity cap.

Provide a short numbered end-to-end editing workflow (pull -> edit/update -> refresh-list -> verify) so the sequence reads as an explicit checkpoint list rather than scattered rules.

Move the full agent-native.json manifest example into a reference file and keep a minimal skeleton inline to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, never explaining known concepts; the clarification that 'Local File Mode does not make the host language model local' is non-obvious behavioral info, not padding. The ~38-line agent-native.json manifest example could be trimmed slightly, which keeps it just below anchor 5.	4 / 5
Actionability	Concrete executable commands are provided (`pnpm action list-documents`, `npx @agent-native/core@latest skills add content ...`) with JSON payloads and a full manifest example, plus explicit fallback guidance for when tools are absent. Placeholder ids like '"id":"local-file:..."' prevent the examples from being fully copy-paste ready, so anchor 5's bar is not met.	4 / 5
Workflow Clarity	Decision guidance is well sequenced (pull/get before editing, edit-document vs update-document, `refresh-list` after create/update/delete), but the action surface includes the destructive `delete-document` with no validation or verification steps anywhere in the workflow. Per the rubric's cap for destructive/batch operations without validation, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Sections are clearly organized (Choose The Path, Action Examples, Local File Mode, MDX And Components, Boundaries) with no nested references. The inline 38-line JSON manifest is central config rather than clearly displaced reference material, leaving only minor organization gaps that fit anchor 4.	4 / 5
	Total	15 / 20 Passed

Description

66%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 specific, distinct description that clearly states what the skill covers with natural trigger keywords. Its one real weakness is the missing explicit 'Use when...' trigger clause, which both caps completeness and leaves activation conditions implied.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to author, edit, or publish Markdown/MDX docs, blog posts, resource pages, or local MDX components.'

State the concrete actions in verb form (create, edit, update, share documents) rather than capability nouns to strengthen specificity.

Include file extensions and common synonyms (e.g., '.md/.mdx files', 'documentation site') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists several specific capability areas — 'repo-backed Markdown/MDX docs, blogs, resources, rich document editing, local components, shareable copies' — with only minor gaps. It falls short of anchor 5 because these are capability nouns rather than multiple concrete action verbs (no create/update/share document operations), and above anchor 3's 1-2 action bar.	4 / 5
Completeness	The 'what' is clear (repo-backed Markdown/MDX document work), but there is no 'Use when...' clause; 'Prefer Content actions over raw filesystem writes when available' is a conditional preference, not trigger guidance. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3 — clear what, when only weakly implied by the domain nouns.	3 / 5
Trigger Term Quality	Natural terms users would say are present: 'Markdown/MDX docs', 'blogs', 'resources', 'document editing', 'local components'. A few natural variations are missing (e.g., '.md/.mdx files', 'documentation site', 'content management'), which matches anchor 4's 'good keyword coverage; a few natural terms missing' rather than anchor 5's comprehensive synonym and extension coverage.	4 / 5
Distinctiveness Conflict Risk	'Content local-file workspaces', 'repo-backed', and 'local components' carve a distinct niche tied to the Content app with its own trigger vocabulary, giving minimal conflict risk with unrelated skills. There is minor overlap risk with generic markdown-editing or docs-site skills, which fits anchor 4 rather than anchor 5's 'clear niche with distinct triggers'.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: BuilderIO/agent-native
Path: skills/content/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.