JasonColapietro/suede-creator-skills / skills/suede-visibility-grader
suede-visibility-grader
VerifiedGrade one public page A-F across findability, first-screen clarity, CTA pull, proof and trust, AI citation readiness, and design signal, with up to five ranked fixes. Use when asked to "grade this page before promotion" or give a quick readiness check of a landing page, README, docs, or campaign. NOT FOR: deep SEO and schema audits (use suede-seo-audit), AI crawler/citation measurement (use suede-ai-seo), or implementing conversion changes (use suede-site-alchemy).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.5 KB |
| SKILL.md | skill md | 11.0 KB |
| agents/openai.yaml | config | 468 B |
| references/sample-report.md | markdown | 1.8 KB |
| references/surface-type-standards.md | markdown | 1.9 KB |
| references/worked-handoff.md | markdown | 1.5 KB |
references/worked-handoff.md
View on GitHub# Suede Visibility Grader Skills: Worked Handoff
## Inputs
Request: “Grade this page before promotion.” Supply one exact URL, primary reader,
surface type, and intended action. Synthetic evidence: desktop rendering and
source are available, the primary CTA opens the intended destination, but mobile
has not been inspected. A short first-viewport gut check uses quick mode; a full
page request uses deep mode.
## Expected output
Use the Output Format in the main skill: inspected URL/source, live status,
screenshots and viewport evidence, six lane grades with reasons, overall grade,
up to five ranked fixes for deep mode, verification, and advisory ship gate.
Compute lanes and caps from the rules rather than impressions. Mobile not
inspected blocks A. Quick mode is at most B and has no top-fixes list. Missing
live inspection caps overall at C. Do not infer actual rankings or AI citations
from a well-structured page.
## Failure case
The URL cannot be reached. Grade supplied source only, name live and rendering
checks unverified, and apply the source-only cap. If the CTA is broken, report
the observed failure and apply the stricter overall conditions in the grade
rules; do not let a positive design count cancel the broken task path.
## Validation
Recompute the design pass count, AI readability deductions, overall conditions,
and all applicable caps. Verify that each fix points to an inspected location,
not a generic SEO suggestion. The ship gate follows the final grade and caveats.
Read-only grading must leave the page, metadata, and schema unchanged.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |