landing-experience-checker

Use when the user asks to "pre-launch check the landing page", "run a Quality-Score preflight", or "verify ad-to-page message match before launch"; produces an ad↔page continuity report — message-match gaps, above-the-fold check, page-speed read, form-friction count, mobile-render flags — as a pass/fix punch list. Not for redesigning or rewriting the page — use landing-optimizer; not for scoring the account or the RQS — use ad-account-auditor. 落地页体验预检/广告落地页一致性检查

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear validated workflow and clean reference signaling, the only weak spot being redundant restatement of the five checks and sibling boundaries already covered by the description. No bundle files ship inside the skill, but external plugin-shared references are appropriately one level deep.

Suggestions

Trim the opening paragraph so it does not re-list the five checks already named in the description; keep only the ROAS-O lever framing and the checks-only boundary.

Consolidate the repeated not-for / sibling-routing statements (intro, end of Instructions, and Next Best Skill) into one canonical routing block to avoid stating the same exclusion three times.

Move the duplicated 'never invent a speed/Core Web Vitals/conversion figure' rule so it appears once (e.g. inside the Speed check step) rather than being restated across Data Sources, step 5, and the closing paragraph.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and it assumes Claude knows ROAS/Quality-Score basics, but the opening paragraph restates the description's five checks and the not-for boundaries are repeated across the intro, Instructions, and Next Best Skill, so it could be tightened.	2 / 3
Actionability	Gives copy-paste-ready execution ('python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecrawl.py" scrape <landing-url> --mobile'), concrete Quick Start phrasings, and per-check Pass/Partial/Fix criteria with specific gap markers — fully actionable for an instruction-style skill.	3 / 3
Workflow Clarity	An explicit 8-step numbered sequence is closed by a 4-item 'Quality bar' checklist with a feedback loop ('If any item fails, fix it or report it in the handoff — do not ship silently') and a 'Done when' gate, matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	The body is a well-organized overview that signals one-level-deep references (CONNECTORS.md, skill-contract.md, SECURITY.md, roas-benchmark.md, scripts/connectors/README.md) with descriptive labels in a dedicated Reference Materials section; no nested-reference chains.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, complete, and sharply delineated from sibling skills via explicit not-for routing. Voice stays in the directive third-person form used by the reference good examples, so no specificity penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete outputs — 'message-match gaps, above-the-fold check, page-speed read, form-friction count, mobile-render flags — as a pass/fix punch list' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (the five-check continuity punch list) and when ('Use when the user asks to...'), with an explicit 'Use when' trigger clause, so it clears the completeness cap.	3 / 3
Trigger Term Quality	Natural user phrasings are quoted directly — 'pre-launch check the landing page', 'run a Quality-Score preflight', 'verify ad-to-page message match before launch' — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Negative-scope clauses ('Not for redesigning or rewriting the page — use landing-optimizer; not for scoring the account or the RQS — use ad-account-auditor') carve a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 15 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/orchestrate/landing-experience-checker/SKILL.md
Commit: 4a77c48

Reviewed: 9 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.