CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-artifacts

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publish_artifact, output_iframe, or slack_attach_html.

Quality

92%

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

93%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: dense, specific, and directive throughout, with a rare focus on non-obvious environmental constraints (opaque origins, dashboard-stamped data-theme) rather than generic design tutorial content. The only notable gap is the absence of an explicit verification step for the two-theme rendering requirement it mandates.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (never explains HTML, CSS, or fonts) and spends every line on non-obvious constraints and directives, e.g. "The viewer frames have an opaque origin, so `localStorage`, `sessionStorage`, and cookies throw on access" — nothing reads as padding.

5 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: a copy-paste-ready three-layer theming CSS block plus named, specific techniques ("`prefers-color-scheme`", "`text-wrap: balance`", "`font-variant-numeric: tabular-nums`", "`overflow-x: auto`", "`color-scheme`").

5 / 5

Workflow Clarity

A clear sequence is prescribed ("Sketch a compact plan before writing HTML, then follow it", then derive all decisions from it) with an explicit review-and-revise loop for editorial requests, but there is no general verification checkpoint (e.g., confirming both themes render) to reach the anchor-5 validation bar.

4 / 5

Progressive Disclosure

A single-file skill with six flat, well-labeled sections and no content that belongs in a separate file — nothing is reference-nested and nothing is buried, matching the well-organized no-external-references case.

5 / 5

Total

19

/

20

Passed

Description

87%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 strong description: it states a precise capability scope, names the three artifact surfaces it covers, and gives an explicit, tool-anchored use-when clause in third person. The only shortfall is modest synonym coverage beyond the tool names themselves.

DimensionReasoningScore

Specificity

Names the domain and enumerates specific coverage areas ("structure, design plan, available runtime, theming, and craft") across three concrete artifact types, but the action itself is singular ("Author the HTML"), leaving minor gaps versus a comprehensive multi-action list.

4 / 5

Completeness

Explicitly answers both what ("Author the HTML for a plan artifact, dashboard iframe, or Slack attachment") and when ("Read this before writing HTML for publish_artifact, output_iframe, or slack_attach_html") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Good natural-term coverage ("HTML", "dashboard", "iframe", "Slack attachment", "publish_artifact", "output_iframe", "slack_attach_html") — the tool names act as precise triggers — but common synonyms such as "web page" or "report" are missing, short of comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

Triggers are the exact tool names for a clear niche (publishing self-contained HTML artifacts), giving minimal overlap risk with generic HTML, frontend, or document skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

langchain-ai/open-swe

Path

openswe/bundled_skills/html-artifacts/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.