CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

live-artifact

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

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 commands, a novel template-binding contract spelled out precisely, and an explicit validation feedback loop. Its only real weaknesses are mild redundancy around connector/credential rules and the omission of the existing example template bundle from the resource map.

DimensionReasoningScore

Conciseness

The body is dense with genuinely novel contract detail (binding syntax, wrapper commands, safety rules) and mostly earns its tokens. Minor trimming is possible: connector listing/execution guidance is repeated in steps 1 and 6, credential/forbidden-key rules appear in both step 4 and step 6, and the brief 'Current status' section adds little — this matches anchor 4 (efficient with minor over-explanation) rather than the lean anchor 5.

4 / 5

Actionability

Copy-paste-ready bash commands with exact wrapper syntax ("$OD_NODE_BIN" "$OD_BIN" tools live-artifacts create --input artifact.json), exact binding examples ({{data.kpis.0.value}}, data-od-repeat="item in data.items"), and a concrete required-files list cover the common cases. Every step is executable, matching anchor 5.

5 / 5

Workflow Clarity

The 7-step workflow is clearly sequenced (scope → author files → compact data → safety → register → connectors → report) with an explicit validation feedback loop in step 7 ("On validation failure, fix the source files and retry through the wrapper. Do not bypass validation") and a pre-registration safety checkpoint in step 4. This matches the anchor 5 example of sequence plus validate/fix/retry.

5 / 5

Progressive Disclosure

A resource map lists all three real reference files (verified to exist) with one-line purposes, and references are signaled inline at the relevant steps, one level deep — good structure. However, the existing example bundle under assets/templates/clinic-console is never mentioned in the body, so an available asset is not navigable from the skill — a minor organization gap that keeps this below anchor 5.

4 / 5

Total

18

/

20

Passed

Description

78%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, well-structured description that explicitly states both capability and trigger conditions in third person, with mostly natural trigger terms. Its only weakness is that the 'what' rests on a single verb with modifiers rather than a list of concrete actions.

DimensionReasoningScore

Specificity

"Create refreshable, auditable OpenDesign artifacts backed by connector or local data" names the domain and one concrete action (create) plus attributes (refreshable, auditable, data sources), but does not enumerate several specific actions. It matches anchor 3 ("names domain and 1-2 concrete actions") better than anchor 4, which expects several listed actions like create, register, refresh, update.

3 / 5

Completeness

It explicitly answers both: what ("Create refreshable, auditable OpenDesign artifacts backed by connector or local data") and when ("Trigger when the user asks for live dashboards, refreshable reports, synced views, or reusable data-backed artifacts") with concrete trigger phrases. This mirrors the anchor 5 example structure; the 'when' clause is explicit, not implied.

5 / 5

Trigger Term Quality

"live dashboards, refreshable reports, synced views, or reusable data-backed artifacts" are natural phrases users would say, giving good coverage. A few common variations are missing from the description itself (e.g. "real-time", "auto-refresh", "live report", "status page"), so it falls just short of the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The "OpenDesign" qualifier plus "refreshable/auditable" and the specific trigger list carve a distinct niche with minimal conflict risk. Minor overlap remains with generic dashboard/report-generation skills, so it is not the clear-minimal-conflict anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.