CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

weather-svg-creator

Creates an SVG weather card showing the current temperature for Dubai. Writes the SVG to orchestration-workflow/weather.svg and updates orchestration-workflow/output.md.

52

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/weather-svg-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 well organized, concise, and follows a clear three-step sequence, but it delegates all executable detail to reference.md and examples.md, which are missing from the bundle, making the skill unexecutable as shipped. Fixing the broken references (or inlining the templates) and clarifying the ambiguous "Read then write" instruction are the highest-impact changes.

Suggestions

Ship the referenced bundle files — create reference.md (SVG and markdown templates, design specs) and examples.md (example input/output pairs) so the delegation in the body resolves; alternatively inline the templates if the bundle is intended to be single-file.

Clarify instruction steps 2 and 3: replace "Read then write" with the concrete operation (e.g. "Create `orchestration-workflow/weather.svg` with the rendered SVG") and specify what, if anything, should be read first.

Remove the redundant restatement of the description in the opening line and consolidate the duplicate reference.md pointers (Instructions step 1 and "Additional resources") into one clearly labeled resources section.

DimensionReasoningScore

Conciseness

The body is lean with no concept explanations — "Use the exact temperature value and unit provided — do not re-fetch or modify" earns its tokens. Not a 5 because the opening line "Creates a visual SVG weather card for Dubai, UAE and writes the output files" duplicates the frontmatter description, and reference.md is pointed to twice (Instructions step 1 and again under "Additional resources").

4 / 5

Actionability

The core executable content — "Use the SVG template from [reference.md](reference.md), replacing placeholders with actual values" and the markdown template — is delegated entirely to reference.md, which does not exist in the bundle (no references/ directory, no reference.md anywhere). With the template file absent there are no specific steps to execute the skill's main artifact; only file paths and ordering are concrete. Not a 3 because unlike the pseudocode anchor, the missing template leaves no partial executable guidance for the SVG itself; not a 1 because target paths, the data contract, and output order are specified.

2 / 5

Workflow Clarity

The three steps are clearly sequenced and the skill is simple and non-destructive, so the simple-skill exception applies. Not a 5 because "Read then write to `orchestration-workflow/weather.svg`" is ambiguous — it is unclear what should be read and why reading precedes creating a new file — leaving the single action not fully unambiguous.

4 / 5

Progressive Disclosure

References are well signaled and one level deep ([reference.md](reference.md), [examples.md](examples.md)), but neither file exists in the bundle — no references/, scripts/, or assets/ directories are present. Scored against the actual bundle structure per the guidelines, the navigation chain is broken, so the structure fails at its purpose. Not a 1 because there is no nesting or wall of text; not a 3 because working references are a prerequisite for "good structure", and here they resolve to nothing.

2 / 5

Total

12

/

20

Passed

Description

62%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 concrete about what it does and where it writes, but it completely lacks any "when to use" trigger guidance and has thin keyword coverage. Adding a "Use when..." clause and natural trigger phrases would raise completeness and trigger-term quality substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when creating or updating the Dubai weather card for the orchestration workflow."

Include natural trigger terms users would say — "weather", "current temperature", "SVG card" — as synonyms alongside the existing keywords.

Clarify the relationship between the two outputs (e.g. "...and writes a markdown summary of the card") so the second action reads as more than a file path update.

DimensionReasoningScore

Specificity

Names several concrete actions — "Creates an SVG weather card showing the current temperature for Dubai", "Writes the SVG to orchestration-workflow/weather.svg", "updates orchestration-workflow/output.md" — with concrete output paths. Not a 5 because coverage is narrow and the summary/output relationship is only implied; not a 3 because multiple specific actions with explicit paths exceed the 1-2 action anchor.

4 / 5

Completeness

The "what" is clear (create an SVG weather card for Dubai, write two specific output files) but there is no "when" — no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline. Not a 4 because nothing implies when to invoke this skill.

3 / 5

Trigger Term Quality

Relevant keywords exist ("SVG", "weather card", "temperature", "Dubai") but there are no natural variations or synonyms and no usage phrasing that a user would naturally say. Not a 4 because the keyword set is thin and lacks common variations; not a 2 because the terms present are domain-relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

The niche is unambiguous — an SVG weather card specifically for Dubai with two named output files — so overlap with other skills is minimal. Not a 4 because no closely related skill would plausibly compete for this exact trigger.

5 / 5

Total

15

/

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

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

shanraisshan/claude-code-best-practice

Path

.claude/skills/weather-svg-creator/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.