agentsclimarketplace
Sign in

Diagnose

Skill Sandy-zippy/claude-code-seo-stack/skills/diagnose

Merge the audit and visibility reports into the 15 fastest fixes ranked by effort vs impact, plus the exact questions people ask AI that the site never answers. Use when asked "what do we fix first", "run diagnose", or after audit + visibility have produced reports.From its SKILL.md

Install
npx -y skills add Sandy-zippy/claude-code-seo-stack --skill diagnose

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.3 KB, 535 tokens by cl100k_base, as published. Nobody here has run it

Diagnose

Reports are not plans. This skill turns the audit and visibility reports into a ranked, do-this-first plan a non-SEO can execute.

Inputs

  • seo-reports/audit-<date>.md and seo-reports/visibility-<date>.md (run those skills first if missing).
  • DataForSEO MCP for question mining.

Steps

  1. Merge findings: pull every P0/P1 from the audit and every "why you're skipped" reason from the visibility report into one list. Dedupe (a missing schema finding and a "no corroboration" skip-reason may share one fix).
  2. Mine the unanswered questions (DataForSEO): for the site's top 3 topics, pull People Also Ask questions and related/long-tail queries with question modifiers (how, best, vs, worth it, near me). Cross-check each against the site: does ANY page answer it? Collect the misses — these are the questions people ask AI where you are silent.
  3. Rank by effort vs impact: score each candidate fix Impact (1-5: traffic/citation potential, from real impressions and visibility gaps) and Effort (1-5: one-line change → new content). Sort by Impact/Effort descending. Take the top 15.
  4. Write the plan: each fix gets: what, why (evidence from the reports), how (concrete: "add Organization JSON-LD with sameAs links to LinkedIn + Google Business profile"), and effort (minutes/hours/days).

Output

DIAGNOSIS: <domain> — <date>

YOUR 15 FASTEST FIXES (ranked)
1. <fix> — impact <n>/5, effort <n>/5 — why: <evidence> — how: <one line>
...

QUESTIONS PEOPLE ASK AI THAT YOU NEVER ANSWER
1. "<question>" — <monthly volume or PAA source> — suggested page/section: <where it should live>
...

HAND-OFF
Fixes 1-N are content/schema changes → run the fix skill.
Fixes N+1... need human/dev decisions: <list>

Save to seo-reports/diagnosis-<date>.md. The fix skill consumes it.

Rules

  • Never pad to 15. If only 11 fixes are real, ship 11 and say so.
  • Impact scores must trace to a number in the upstream reports (impressions, position, citation gap), not gut feel.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most debug triage skills give in 535 tokens

Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07

  • Investigate root cause before proposing any fixin 102 of 839, across 67 files
  • Read error messages completelyin 89 of 839, across 49 files
  • Create a failing test case before fixingin 84 of 839, across 46 files
  • Reproduce the issue consistentlyin 82 of 839, across 41 files
  • Change one variable at a timein 82 of 839, across 42 files
  • Check recent changesin 74 of 839, across 36 files
  • Write the regression test before fixingin 74 of 839, across 40 files
  • Fix the root cause not the symptomin 60 of 839, across 45 files
  • Implement a single fix at a timein 59 of 839, across 20 files
  • Trace data flow backward to the sourcein 50 of 839, across 20 files
  • Remove all debug instrumentationin 49 of 839, across 13 files
  • Form a single hypothesisin 48 of 839, across 18 files

Said here and by no other author read

  • merge p0 and p1 findings into one list
  • deduplicate merged findings
  • pull top three topic questions from dataforseo
  • cross-check each question against the site
  • collect unanswered questions
  • rank fixes by impact over effort

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,629. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.