CtrlK
BlogDocsLog inGet started
Tessl Logo

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 save_plan, output_iframe, or slack_attach_html.

69

Quality

84%

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

86%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 body is an efficient, well-structured craft guide that assumes competence and packs concrete rules into headed sections, with a usable theming CSS scaffold and a plan-first workflow plus an editorial review loop. Its main gap is the absence of a complete worked HTML example tying the design-plan rules to a real artifact.

Suggestions

Add one short, complete worked HTML example (a minimal plan card or dashboard snippet) that applies the design-plan rules end to end, so the guidance is copy-paste ready rather than rule-only.

Make the plan-first sequence explicit as numbered steps (plan → derive → write → review) so the workflow reads as a checklist rather than a narrative across sections.

DimensionReasoningScore

Conciseness

The body is dense with craft rules and assumes Claude's competence — it never explains what HTML, CSS, media queries, or theming are — and nearly every sentence encodes an actionable rule that earns its place.

5 / 5

Actionability

Guidance is highly concrete (4–6 hex values, ~65-char measure, tabular-nums, flex/grid gap) and includes an executable theming CSS scaffold, but there is no full worked HTML example applying the design plan to a common case.

4 / 5

Workflow Clarity

A clear plan-first sequence (sketch plan → derive every decision from it → write → review/revise for editorial) with an explicit editorial review loop, though there are no formal validation checkpoints because the task is not destructive or batch-oriented.

4 / 5

Progressive Disclosure

A self-contained ~55-line file with clearly headed sections (Design plan, Runtime, Theming, Craft, Point of view), no nested or buried references, and no bundle files that need navigation.

5 / 5

Total

18

/

20

Passed

Description

82%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 specific, third-person, and explicit about both scope and when to use it, anchored to concrete tool names. It is strong overall, with the only soft spot being that it enumerates one action verb rather than several discrete actions.

Suggestions

Consider framing the scoped aspects (structure, design plan, runtime, theming, craft) as discrete verbs (e.g., "structure the page, plan the palette and type, handle the runtime, layer theming, apply craft") to lift specificity from one action to several.

Add a user-mention trigger (e.g., "or when the user asks for a dashboard, plan card, or Slack snippet") alongside the tool-name trigger to broaden natural phrasing coverage.

DimensionReasoningScore

Specificity

A single concrete action ("Author the HTML") is applied to three named artifact types and five scoped aspects (structure, design plan, runtime, theming, craft), giving comprehensive scope but only one verb rather than multiple distinct actions.

3 / 5

Completeness

States clearly what the skill does (author HTML for three artifact types across five concerns) and gives explicit trigger guidance ("Read this before writing HTML for save_plan, output_iframe, or slack_attach_html") with concrete tool-name triggers.

5 / 5

Trigger Term Quality

Includes natural artifact terms (HTML, dashboard iframe, Slack attachment) plus the exact tool names (save_plan, output_iframe, slack_attach_html); good coverage though it omits common synonyms or file-type cues.

4 / 5

Distinctiveness Conflict Risk

A tight niche tied to three specific publishing tools with distinct, unlikely-to-collide triggers; minimal overlap risk with other skills.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
langchain-ai/open-swe
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.