CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

visualize

Use /visualize for creating compact charts, diagrams, or other visuals inline as part of the conversation itself. It chooses among Markdown tables, Mermaid, inline HTML, and other supported in-transcript forms. Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share.

Quality

85%

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

92%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.

An exemplary instruction-only skill body: terse environment-specific rules, exact executable details (paths, naming, tag, forbidden APIs), a fully sequenced workflow with a hard completion gate and review checklist, and a clean router-to-references structure where every cited file exists. The only flaw is mild redundancy — the smallest-result and tag-verification rules each appear two or three times across sections.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and teaches only environment-specific facts Claude cannot know ("The sandbox has no network access of any kind", "sandbox=\"allow-scripts\" without allow-same-origin", the store-dir convention). It is not anchor 5 because of repeated statements of the same rule: "smallest truthful result" (Mission), "Choose the smallest composition" (invariant 2), "Did you choose the smallest format" (Review), and the tag-verification rule appears in both Publish and the Completion gate. No filler or explanations of known concepts, so well above anchor 3.

4 / 5

Actionability

Guidance is fully concrete and copy-paste ready for an instruction-only skill: the exact tag `<cursor-content kind="visualization" src="visualizations/<slug>.html"></cursor-content>`, the exact environment variable `CURSOR_AGENT_STORE_FILES_DIR`, a precise slug pattern with a worked example (`revenue-by-quarter`), specific forbidden APIs ("fetch, XMLHttpRequest, WebSocket, navigator.sendBeacon"), and exact file paths. Routing conditions and the HTML lifecycle leave no step abstract.

5 / 5

Workflow Clarity

A clear five-step sequence (Route → Identify → Plan → Complete → Review) is expanded into an HTML lifecycle (Allocate → Author → Validate → Publish) with explicit checkpoints: the "Completion gate" ("do not finish until the final response contains exactly one content-reference tag... Verify that the tag's src uses the same file name"), a final review checklist, an explicit stop condition, and recovery paths for error cases ("If neither store location is available... tell the user", name collisions handled by appending -2). This matches the anchor-5 pattern of explicit validation, checklists, and error recovery; file writes are additionally protected by the never-overwrite rule.

5 / 5

Progressive Disclosure

The entry file is a pure router with one-level-deep, well-signaled references: all seven paths cited (foundations, charts, components, mockups, diagrams, art, catalog) exist in references/, each guarded by an unambiguous condition ("Every chart, plot, part-to-whole view... MUST read references/charts.md"), plus the explicit discipline "Read every applicable file. Read no unrelated file." Cross-links between reference files (e.g., foundations → charts for the D3 marker) are sibling pointers that SKILL.md already routes to, not buried 2+-level content deferral, so navigation stays flat and easy.

5 / 5

Total

19

/

20

Passed

Description

75%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 solid, third-person description that states concrete capabilities, the output forms, and an explicit use clause, with a sharp boundary against Canvas. It consistently lands just below the top anchor: trigger synonyms are incomplete, the capability list trails off into "other visuals", and the "when" guidance names the command rather than concrete user requests.

Suggestions

Add concrete user-need trigger phrases, e.g. "Use when the user asks for a chart, diagram, graph, plot, or table inside the conversation".

Include common synonyms such as "graph", "plot", "table", and "figure" so natural user phrasings match the description.

Name the distinctive HTML-route capabilities (mockups, simulations, structured views, artwork) instead of the open-ended "other visuals" to sharpen both the what and the niche.

DimensionReasoningScore

Specificity

"creating compact charts, diagrams, or other visuals inline" plus "It chooses among Markdown tables, Mermaid, inline HTML" names several concrete capabilities and the concrete output forms. It falls short of anchor 5 because coverage is not comprehensive — "other visuals" and "other supported in-transcript forms" leave the capability list open, and notable forms (mockups, simulations, artwork) are never named. It is clearly above anchor 3, which expects only 1-2 concrete actions.

4 / 5

Completeness

The "what" is clear ("creating compact charts, diagrams, or other visuals inline... chooses among Markdown tables, Mermaid, inline HTML") and a "Use /visualize for..." clause provides explicit trigger guidance, so the missing-when-clause cap of 3 does not apply. It is not anchor 5 because the "when" is framed around the command rather than concrete user-need phrases (e.g., "when the user asks for a chart, graph, or diagram in the chat").

4 / 5

Trigger Term Quality

Natural terms users would say are present: "charts", "diagrams", "visuals", "inline", "conversation". It stops short of anchor 5's comprehensive synonym coverage — common phrasings like "graph", "plot", "table", "figure", or "drawing" are absent. It is well above anchor 3 ("Works with PDF files"-level keyword coverage) because multiple natural terms appear.

4 / 5

Distinctiveness Conflict Risk

The explicit contrast — "inline as part of the conversation itself" versus "Use Canvas for durable artifacts outside the transcript that users may revisit, refine, or share" — carves a clear niche against the closest sibling skill. It misses anchor 5 because "or other visuals" is open-ended and could still overlap with general charting/dataviz skills whose triggers ("chart", "diagram") are shared.

4 / 5

Total

16

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

saski/arnesto

Path

.cursor/skills-cursor/visualize/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.