CtrlK
BlogDocsLog inGet started
Tessl Logo

consent-mode

Use when auditing slow page loads, heavy assets, or rendering delays related to Implement Google Consent Mode v2. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

58

Quality

67%

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 ./skills/consent-mode/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 clean, brief overview that delegates implementation detail well to a single real reference file. The body's weaknesses are that its Check/Fix guidance stays at the naming-things level (no inline code or commands) and the workflow lacks an explicit post-fix verification step, both of which live only in the referenced file.

Suggestions

Inline the minimal gtag.js consent-default snippet (or a one-line pointer like 'set ad_storage/ad_user_data/ad_personalization/analytics_storage to denied with wait_for_update') so the Fix section is actionable without opening the reference.

Add an explicit post-fix validation checkpoint, e.g. 'After the fix, re-inspect network pings in DevTools/Tag Assistant to confirm `gcd` reflects the updated consent state', to close the Check → Fix loop.

Trim the opening paragraph and Quick Reference bullets, which restate the same compliance/measurement rationale, to remove redundant context Claude already knows.

DimensionReasoningScore

Conciseness

The body is lean (~45 lines) with tight one-line sections ("Verify that Google Consent Mode v2 is correctly implemented and sending the appropriate consent states"), and the opening paragraph is only mildly explanatory. Not a 5: the first paragraph ("Consent Mode v2 is essential for adhering to privacy regulations (like GDPR)...") and the Quick Reference bullets partially restate each other and re-explain context Claude already knows; not a 3: the padding is minor, not 'some unnecessary explanation'.

4 / 5

Actionability

Some concrete anchors exist — "support the new `ad_user_data` and `ad_personalization` consent types", "Ensure the `gcd` parameter is present in pings" — but the Fix section gives only a high-level direction ("Update your GTM or gtag.js implementation") with no code or commands in the body; everything executable is delegated to references/rule.md. Not a 4: there is no copy-paste-ready guidance in SKILL.md itself; not a 2: specific consent type names and the gcd check give more than minimal high-level hints.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections imply a rough audit-then-fix sequence, but the steps are one-liners with no explicit validation checkpoint confirming the fix took effect (e.g. re-inspecting pings for `gcd`/`gcs` after the change). Not a 4: the verify-after-fix loop is implicit, not 'most checkpoints present'; not a 2: the sections do define a recognizable sequence rather than leaving gaps everywhere.

3 / 5

Progressive Disclosure

The body is a concise overview with a single clearly signaled, one-level-deep reference ("For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`"), and that file exists with the full code examples and validation guidance. Content is appropriately split: overview in SKILL.md, implementation detail in the reference, matching the under-50-lines simple-skill guidance.

5 / 5

Total

15

/

20

Passed

Description

70%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 well-formed description with an explicit 'Use when' trigger clause, natural user-facing keywords, and a clear verify-first stance. Its main weakness is that the stated actions are generic audit verbs (verify, audit, recommend) while the concrete capability — implementing/fixing Consent Mode v2 — is only implied by the embedded rule title.

Suggestions

State the concrete outcome as an action, e.g. "Implement and fix Google Consent Mode v2 consent types (ad_user_data, ad_personalization) in GTM or gtag.js" instead of relying on the embedded rule title "related to Implement Google Consent Mode v2".

Add common synonyms users would say, such as "page speed", "consent banner", or "CMP", to strengthen trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ("auditing slow page loads, heavy assets, or rendering delays related to Implement Google Consent Mode v2") and 1-2 concrete actions ("Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes"), but the actions are generic audit verbs and it never states the concrete outcome (implementing/fixing Consent Mode v2). Not a 4: it does not list several specific actions with only minor gaps; not a 2: the domain and a real verification action are explicitly stated.

3 / 5

Completeness

Both parts are present: an explicit trigger clause ("Use when auditing slow page loads, heavy assets, or rendering delays related to Implement Google Consent Mode v2") and a 'what' ("Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes"). Not a 5: the 'what' describes the verification approach but never explicitly states the deliverable (implementing/adjusting Consent Mode v2); not a 3: the 'when' clause is explicit, not weakly implied.

4 / 5

Trigger Term Quality

Natural trigger phrases users would actually say are present: "slow page loads", "heavy assets", "rendering delays", plus tool names "DevTools", "Lighthouse", "field data". Not a 5: common synonyms and variations like "page speed", "consent banner", "CMP", or "Google Tags" are missing; not a 3: coverage goes well beyond one or two generic keywords.

4 / 5

Distinctiveness Conflict Risk

The Consent Mode v2 niche is distinctive and the trigger is scoped to performance auditing of that feature, minimizing wrong-skill triggers. Not a 5: it could still overlap with generic web-performance-audit skills when the user mentions slow page loads without naming Consent Mode; not a 3: the overlap risk is minor and confined to closely related performance skills.

4 / 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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.