CtrlK
BlogDocsLog inGet started
Tessl Logo

ad-creative

When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.

68

Quality

83%

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

The canonical home for this skill is ad-creative in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-organized, actionable instruction skill with concrete templates, a spec table, clear multi-mode workflows, and an explicit validation checklist. Its main weakness is that it depends on bundle files (references/ and scripts/) that are not present, breaking progressive disclosure and one referenced executable tool.

Suggestions

Either ship references/platform-specs.md, references/creative-frameworks.md, and scripts/ad_copy_validator.py, or remove the dead links and inline the essential detail so the skill is self-contained.

Add an explicit validate→fix→retry feedback loop (e.g., 'If ad_copy_validator flags a violation, rewrite the flagged line and re-run until clean') to lift workflow_clarity.

Trim rhetorical framing lines under each funnel-stage heading ('They don't know you yet...', 'They're close. Remove the last objection.') to improve token efficiency.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's intelligence — no padding about what an ad or a platform is; the platform-spec table, headline formulas, and iteration steps are domain knowledge Claude lacks. Minor editorial framing lines ('They don't know you yet. Meet them where they are.') could be trimmed. Not 5 because a few transitional sentences are more rhetorical than instructional; not 3 because there is no concept over-explanation.

4 / 5

Actionability

Provides concrete templates with real examples (headline formula patterns + sample headlines), a platform char-limit table, and a copy-paste output format. Not 5 because it instructs the reader to 'use scripts/ad_copy_validator.py' and 'see references/...' for executable detail, yet none of those bundle files exist, leaving referenced executable guidance unresolvable. Not 3 because the bulk of guidance is concrete and directly usable.

4 / 5

Workflow Clarity

Three numbered workflows plus a 5-step iteration methodology with an explicit Step 5 'Validate and Submit' feeding a Quality Checklist — clear sequencing with validation. Not 5 because the error-recovery feedback loop ('if validation fails, fix and re-validate') is implicit rather than an explicit validate→fix→retry cycle as in the anchor 5 example; not 3 because checkpoints (validation step, checklist, proactive triggers) are clearly present.

4 / 5

Progressive Disclosure

Structure is well-intended: overview content inline with two clearly-signaled one-level-deep references ('See references/platform-specs.md for full specs...'; 'See references/creative-frameworks.md...'). However, scoring against the actual bundle, references/, scripts/, and assets/ do not exist, so the signaled navigation leads to dead ends and the offloaded detail is unreachable. Not 4 because broken references are a substantive delivery gap, not a 'minor organization gap'; not 2 because the inline content is well-sectioned and references are clearly signaled rather than buried.

3 / 5

Total

15

/

20

Passed

Description

95%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 strong, well-structured description that names concrete actions, surfaces many natural trigger phrases, and explicitly disambiguates from sibling skills. Voice is appropriately third person and it is concise for the coverage it provides.

DimensionReasoningScore

Specificity

Opens with 'generate, iterate, or scale ad creative for paid advertising' — three concrete verbs naming the domain; comparable to anchor 4 ('several specific actions'), though slightly above the 3-anchor which only expects 1-2 actions. Not a 5 because the verbs are fairly high-level and lack granular sub-actions like the PDF example's four distinct operations.

4 / 5

Completeness

Explicitly answers both 'what' ('generate, iterate, or scale ad creative for paid advertising'; 'pure creative production') and 'when' ('Use when they say...') with concrete trigger phrases. Matches anchor 5; not 4 because the 'when' is specific and trigger-laden rather than weakly implied.

5 / 5

Trigger Term Quality

Lists a comprehensive set of natural phrases users would actually say ('write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' 'creative testing') covering synonyms and platform-specific terms. Not below 5 because coverage is exhaustive for this domain; file extensions are N/A for ad copy.

5 / 5

Distinctiveness Conflict Risk

Explicitly carves a niche ('distinct from paid-ads (campaign strategy)'; 'Use ad-creative when you need the copy, not the campaign plan') with platform-specific triggers minimizing overlap. Matches anchor 5; not 4 because it actively disambiguates from the nearest competing skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

14

/

16

Passed

Repository
alirezarezvani/claude-skills
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.