meta-ad-policy-checker

Pre-flight policy check for Meta ads. Takes ad copy plus advertiser context, resolves and fetches the relevant Meta transparency-center policy pages at runtime, and returns a Pass / Fix Required / Block verdict with cited findings and rewrites.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 strongly actionable, well-sequenced methodology skill with concrete procedures, a real error-recovery loop, and a mandatory output contract; its only weaknesses are slight intro duplication and the absence of any reference-file split for the mutable policy lookup tables.

Suggestions

Trim the duplicated framing: merge the 'Core principle' paragraph into the intro and drop one of the two 'Meta is the final gatekeeper' statements.

Move the Phase 1 policy lookup-key tables into a one-level-deep reference file (e.g. references/policy-lookup.md) so the mutable bulk is separated from the stable methodology.

Dimension	Reasoning	Score
Conciseness	Phases 0–6 are lean tables and templates that assume Claude's competence, but the intro states the skill's approach twice ("This skill is a pre-flight check..." then "Core principle: ...") and "Don't replace Meta's review" duplicates "Won't replace Meta's actual ad review" — minor trimmable instances rather than pervasive padding.	4 / 5
Actionability	Fully concrete instruction-only guidance: exact intake fields, trigger-to-lookup-key tables, the ad-standards index URL, a quantified caching rule ("10 ad variants should produce 3–6 policy-page fetches"), a 404 fallback procedure, severity calibration rules, and an exact output template ("Use this exact structure").	5 / 5
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit checkpoints and a genuine feedback loop (fetch → 404 → site-restricted search → log "policy URL drift" note), plus grounding validation ("If you can't quote, the finding isn't grounded — drop it"); the skill is read-only analysis, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist, and the single ~200-line file is well-sectioned with the inline slug list explicitly justified ("updates are a single-file change"), but the mutable policy lookup tables are bulk content that could live in a one-level-deep reference file — a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

75%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 specific, well-scoped description with concrete third-person actions and a distinct niche, held back only by the absence of any explicit 'Use when...' trigger guidance and missing common synonyms like Facebook ads or ad disapproval.

Suggestions

Add an explicit trigger clause, e.g. "Use when preparing or submitting Meta (Facebook/Instagram) ads, after generating ad copy variants, or when an ad was disapproved for policy reasons."

Include natural synonyms users would say — "Facebook ads", "ad disapproval", "ad compliance" — to improve trigger term coverage.

Name the verdict trigger context (before submission via Meta Ads Manager or API) so the 'when' is explicit rather than implied by "pre-flight".

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions in third person — "Takes ad copy plus advertiser context", "resolves and fetches the relevant Meta transparency-center policy pages at runtime", "returns a Pass / Fix Required / Block verdict with cited findings and rewrites" — covering input, source, process, and output comprehensively, exceeding the 'minor gaps' level 4 anchor.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance — "pre-flight" only weakly implies timing — which caps completeness at 3 per the judging guideline.	3 / 5
Trigger Term Quality	Natural phrases like "policy check", "Meta ads", "ad copy", and "pre-flight" are present, but common user variations such as "Facebook ads", "ad disapproval", or "ad compliance" are missing, matching the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	"Meta ads" combined with "transparency-center policy pages" and the Pass/Fix Required/Block verdict form a clear niche with minimal overlap risk against sibling skills like variant generators or landing-page auditors.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/ads/composites/meta-ad-policy-checker/SKILL.md
Commit: cc3e518

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.