CtrlK
BlogDocsLog inGet started
Tessl Logo

cowart-open-canvas

Open, reopen, or explicitly refresh the native Cowart canvas when the user asks to see it, or when a bare @Cowart invocation has no other requested workflow.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is a tight, well-structured single-purpose skill with executable tooling detail and a clear failure-recovery branch. It is strong on conciseness and workflow clarity, with only minor trim and checkpoint-expansion opportunities.

Suggestions

Show a copy-paste-ready tool call using the host-exposed prefixed name (mcp__cowart_mcp__render_cowart_canvas_widget) with the projectDir argument so the actionability step is fully executable.

Make the 'Confirm the widget opens' checkpoint explicit by stating what success looks like (e.g. the returned ui://widget/cowart/canvas.html template renders) so the workflow hits a 5.

Trim the opening restatement of the description ('The actual canvas-opening capability is the cowart_mcp MCP server and its render_cowart_canvas_widget tool') since the frontmatter already conveys this.

DimensionReasoningScore

Conciseness

The body is efficient and mostly free of concept-padding Claude already knows, with the fewest unnecessary tokens, though sentences like 'The actual canvas-opening capability is the cowart_mcp MCP server...' restate the description and could be trimmed slightly.

4 / 5

Actionability

It gives an executable tool name, the host-exposed variant, and a concrete JSON arguments example, but stops short of a copy-paste-ready tool call block with the full prefixed name, leaving a minor execution gap.

4 / 5

Workflow Clarity

The three numbered steps are clearly sequenced with an explicit failure/retry path (tool not visible -> discovery -> retry -> only then suggest a new task), and validation guidance ('Confirm the widget opens'); minor checkpoint detail on what 'confirm' entails keeps it just below a 5.

4 / 5

Progressive Disclosure

The single-purpose skill is organized into clear sections (Workflow, Constraints) with no bundle files and appropriately scoped inline content; it is lean and well-structured, though it has no one-level-deep references to point to (none are needed here).

4 / 5

Total

16

/

20

Passed

Description

88%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 strong: concrete actions, explicit 'Use when'-style triggers, and clear boundaries against sibling skills. Its only gap is slightly broader natural-keyword coverage (synonyms like 'show'/'launch').

DimensionReasoningScore

Specificity

The description names concrete actions ('Open, reopen, or explicitly refresh the native Cowart canvas') plus a specific fallback condition (bare @Cowart invocation with no other requested workflow), giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly answers 'what' (open/reopen/refresh the canvas) and 'when' ('when the user asks to see it, or when a bare @Cowart invocation has no other requested workflow') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

It includes natural user phrases like 'open, reopen, or explicitly refresh' and 'see it', but omits synonyms a user might say (e.g. 'show', 'launch', 'view canvas') and the literal product term 'Cowart canvas' appears only as the capability name rather than as a trigger keyword.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined (opening the canvas vs image generation, annotation, HTML, Slides, or follow-up requests), with explicit exclusion of adjacent Cowart workflows that minimize conflict risk.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
zhongerxin/Cowart
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.