CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-traffic-tracking

Compatibility pointer for AI assistant referrals and generative search visibility; maintained in Open Analytics.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/analytics/sources/ai-traffic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

A model moved-skill stub: a heading and three lean sentences containing a direct link, a copy-paste install command, and an explicit disclaimer that no independent rules live here. It wastes zero tokens and leaves zero ambiguity about where the maintained instructions reside.

DimensionReasoningScore

Conciseness

The body is three sentences with zero padding: 'The maintained instructions are in [Open Analytics: ai-traffic-tracking](...). Install with `npx skills add ...`. This entry preserves the old discovery path and contains no independent AI-source rules.' It explains nothing Claude already knows, and every token (link, install command, disclaimer) earns its place. Not 4, because there are no instances of over-explanation to trim at all.

5 / 5

Actionability

It provides a fully executable, copy-paste-ready command ('npx skills add kostja94/open-analytics --skill ai-traffic-tracking') plus a direct URL to the maintained SKILL.md, which covers the single common case for a moved skill: getting to the real instructions. Not 4, because nothing is missing or left as a hint — the redirect is completely concrete.

5 / 5

Workflow Clarity

This is a single-purpose skill under 50 lines whose only action — fetch/redirect to the successor location — is unambiguous, so the simple-skill exception applies. There are no destructive or batch operations, so the validation cap does not apply. Not 4, because there is no ambiguity or missing checkpoint: the destination link and install path are both explicit.

5 / 5

Progressive Disclosure

At ~3 lines of body with a clear heading and no bundle files needed, this fits the under-50-line guideline: the overview is the whole content, and the one reference (the successor repo URL) is clearly signaled and one level deep. Not 4, because nothing is inlined that belongs elsewhere or buried — the detailed rules correctly live in the successor skill.

5 / 5

Total

20

/

20

Passed

Description

53%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.

An honest, domain-specific description that clearly conveys the skill is a moved compatibility pointer, but it omits any 'Use when' trigger guidance and offers only two domain keyword phrases with no synonyms. It is distinguishable and truthful, yet under-serves discovery relative to the rubric's strong examples.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about AI traffic, AI assistant referrals (ChatGPT, Claude, Perplexity), or generative search visibility.'

Include natural synonyms users would actually say — 'AI traffic', 'AI referrals', 'AI-driven traffic', 'AI search visibility' — to broaden trigger coverage beyond the current two phrases.

State the redirect action explicitly as a verb-led capability (e.g. 'Redirects AI-traffic tracking requests to the maintained Open Analytics skill') so the 'what' reads as a concrete action rather than a label.

DimensionReasoningScore

Specificity

It names the domain concretely ('AI assistant referrals and generative search visibility') and one concrete function ('Compatibility pointer'), but lists no operational capability actions — the body confirms it 'contains no independent AI-source rules'. Not 4, because only one action (pointing/redirecting) is given rather than several specific actions; not 2, because the domain is well named and the pointer role is concrete rather than generic like 'Processes PDF files'.

3 / 5

Completeness

The 'what' is stated clearly ('Compatibility pointer for AI assistant referrals and generative search visibility; maintained in Open Analytics'), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4, because the 'when' is entirely absent rather than merely under-specified; not 2, because the 'what' is clear, not vague.

3 / 5

Trigger Term Quality

The phrases 'AI assistant referrals' and 'generative search visibility' are relevant domain terms a user might plausibly say, but common variations and synonyms are missing — e.g. 'AI traffic' itself, 'AI referrals', 'ChatGPT/LLM referrals', 'AI search visibility'. Not 4, because keyword coverage is thin (only two domain phrases); not 2, because the terms present are specific to the niche rather than generic filler like 'works with files'.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly distinct — 'AI assistant referrals' and 'generative search visibility' are specific enough that overlap risk with unrelated skills is minor. Not 5, because the description lacks explicit trigger phrases that would cleanly separate it from the successor skill or closely related analytics skills; not 3, because the domain terms are considerably more specific than broad anchors like 'Works with document files'.

4 / 5

Total

13

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

kostja94/marketing-skills

Path

skills/analytics/sources/ai-traffic/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.