live-artifact

Create refreshable, auditable Open Design artifacts backed by connector or local data. Trigger when the user asks for live dashboards, refreshable reports, synced views, or reusable data-backed artifacts.

Quality

76%

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 ./design-templates/live-artifact/SKILL.md

Quality

Content

82%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, highly actionable skill body with concrete daemon wrapper commands, a precise template-binding contract, and a sequenced workflow with a retry feedback loop. Small gains are available by reducing command/key-list repetition and pulling more binding detail fully into the reference file.

Suggestions

De-duplicate the connector-listing command and forbidden-key list so each appears once, with the body pointing to the relevant reference for the rest.

Move the inlined binding-rule detail fully into references/artifact-schema.md, keeping the body to the essential contract and a pointer.

Add an explicit agent-run validation checkpoint (e.g. 'preview the hydrated index.html before registering') to strengthen the workflow's validation feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is dense and operationally focused, assuming Claude's competence with the daemon and binding contract, though the connector-listing command and forbidden-key list recur across the body and references and could be tightened slightly.	4 / 5
Actionability	Copy-paste-ready wrapper commands ('tools live-artifacts create --input artifact.json'), explicit binding syntax ('{{data.path.to.value}}', 'data-od-repeat="item in data.items"'), and concrete safety rules give fully executable guidance for the common cases.	5 / 5
Workflow Clarity	A clear 7-step sequence with an explicit fix-and-retry feedback loop ('On validation failure, fix the source files and retry... Do not bypass validation'), though validation is delegated to the daemon rather than an agent-run checkpoint, leaving a minor gap.	4 / 5
Progressive Disclosure	A clear resource map signals three one-level-deep references with descriptions, and the body stays overview-oriented; minor duplication of binding rules between the body and artifact-schema.md keeps it just short of a 5.	4 / 5
	Total	17 / 20 Passed

Description

70%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 concise, third-person description that clearly states what the skill does and when to trigger it, with good natural keyword coverage and a well-defined niche. It could be sharpened by enumerating more concrete artifact actions to lift specificity and completeness toward the top anchors.

Suggestions

Add 1-2 more concrete verbs (e.g. 'register, refresh, and audit') to the 'what' clause to improve specificity.

Include a couple more everyday trigger phrasings or the canonical file/artifact names users might say to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Open Design artifacts backed by connector or local data') and a couple of concrete qualities (refreshable, auditable), but the action is the generic 'Create' without enumerating several distinct operations, so it stops short of comprehensive coverage.	3 / 5
Completeness	Both 'what' ('Create refreshable, auditable Open Design artifacts...') and 'when' ('Trigger when the user asks for live dashboards, refreshable reports, synced views...') are present and explicit; the 'what' remains slightly high-level, keeping it just below a 5.	4 / 5
Trigger Term Quality	Strong natural keyword coverage ('live dashboards, refreshable reports, synced views, reusable data-backed artifacts') with live/refreshable synonyms and bilingual triggers, though a few common phrasings and explicit file/extension terms are absent.	4 / 5
Distinctiveness Conflict Risk	The Open Design live-artifact niche with connector/local-data backing and live/refreshable triggers is mostly distinct, with only minor overlap risk against generic dashboard or report skills.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/live-artifact/SKILL.md
Commit: 1a7a23d

Reviewed: about 5 hours 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.