CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conversion-tracking

Verify available conversion and pixel diagnostics before launch; hand off tag changes to the account owner.

Quality

78%

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 ./packages/claude-directory/skills/conversion-tracking/SKILL.md

The canonical home for this skill is conversion-tracking in Synter-Media-AI/plugin

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.

The body is an exemplary lean, tool-driven instruction skill: it specifies exact tools per step, builds in explicit validation gates and a re-verification loop, and stays within a single well-organized page with zero padding. The only gap is the absence of example invocations or expected-evidence comparisons that would make the guidance fully copy-paste ready. It scores at or near the top on every dimension.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence throughout — it never explains what a conversion or pixel is, and lines like "A configured conversion is not proof that the right event fires" add only non-obvious judgment guidance. Every token earns its place across four tight paragraphs.

5 / 5

Actionability

Names the exact tool for each purpose (`ga4_get_properties`, `ga4_get_conversions`, `ga4_get_report`, `get_pixel_health`, `run_launch_preflight`) with concrete handoff and reporting requirements, so the guidance is largely executable. Minor gaps remain: no example invocations or parameters, and phrases like "over a stated period" and "Compare the intended business action with the evidence returned" leave execution details unspecified, which keeps it below the copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

A clear sequence runs from account confirmation through property/conversion/event reads, evidence comparison, gap handoff, and post-change re-verification ("After changes, repeat the reads and confirm a test conversion in the platform's own diagnostics"). Validation is explicit ("Mark fields and checks unavailable from the tools as unverified") and there is a hard launch gate ("Do not launch or scale until required tracking checks pass"), matching the anchor-5 feedback-loop pattern.

5 / 5

Progressive Disclosure

This is a single-purpose skill under 50 lines with no bundle files (no references/, scripts/, or assets/ exist) and no need for external references, so the simple-skill exception applies: the short body is organized into focused topical paragraphs with no inlined bulk content or nested references. Well-organized and fully self-contained.

5 / 5

Total

19

/

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.

The description is concise, in third person, and names a distinct niche with two concrete actions, but it lacks any "when to use" trigger guidance and misses natural keyword variations. Its coverage of the skill's actual capabilities is partial relative to the body. Adding a "Use when..." clause and richer trigger terms would lift the weakest dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when preparing to launch or scale campaigns and conversion tracking, pixels, or event firing must be verified first" — this addresses both completeness and trigger_term_quality.

Include natural keyword variations users would actually say: "conversion tracking", "pixel health", "GA4 conversions", "tag manager" rather than only "conversion and pixel diagnostics".

Mirror the body's full capability set (inspect configured conversions, check recorded events over a period, run launch preflight) instead of only "verify diagnostics and hand off tag changes".

DimensionReasoningScore

Specificity

Names the domain and two concrete actions — "Verify available conversion and pixel diagnostics" and "hand off tag changes" — but omits capabilities the body actually covers (inspecting configured conversions, checking recorded events, launch preflight), so coverage is not comprehensive as anchor 4 requires.

3 / 5

Completeness

The "what" is clear (verify diagnostics pre-launch, hand off tag changes), but there is no "when" — no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is concrete and specific.

3 / 5

Trigger Term Quality

Contains relevant domain keywords ("conversion", "pixel diagnostics", "launch", "tag changes") but misses common natural variations users would say, such as "conversion tracking", "GA4", "tag manager", or "Meta/Facebook pixel", and includes no "Use when" phrasing. Not 2 because the keywords are domain-specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

"conversion and pixel diagnostics before launch" carves out a clear ad-ops verification niche that is unlikely to trigger for unrelated skills, with only minor overlap risk against general analytics or launch-checklist skills. Not 5 because the absence of explicit trigger phrases leaves the niche less locked-in than the anchor-5 example.

4 / 5

Total

13

/

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

Synter-Media-AI/plugin

Path

packages/claude-directory/skills/conversion-tracking/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.