g-shevchenkog-shevchenko/utility-skills/skills/free-seo-stack/SKILL.md

free-seo-stack

Skill0 starsChanged 2 months agoMITView on GitHub

Free alternatives to Semrush Ahrefs Ubersuggest paid SEO stack Lighthouse CrUX GSC Bing Yandex IndexNow rank audit backlinks security your scripts

Reads credentials

In this repository9 other files it gives its agents.
- figma-diagram-visualizationSkill
- figma-mcp-freeSkill
- n8n-temp-cleanupSkill
- pantheon-style-repo-quickrefSkill
- pdf-signingSkill
- remote-mac-accessSkill
- talk-deck-builderSkill
- youtube-transcribeSkill
- zoom-hostSkill

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Reality: no free drop-in replaces Ahrefs-scale backlink graph or Semrush-scale global keyword difficulty.
line 27
Distinctive:
Red tier: Avoid recommending third-party bulk Google SERP scrapers as “Semrush replacement” — ToS + account ban risk.
line 60
Very specific:
If the workspace is your-repo (or a clone with scripts/visual-verify/):
line 80
Very specific:
If your repo available → run or instruct the scripts above.
line 111
Very specific:
If no repo → manual checklist: Lighthouse, GSC UI, CrUX in PSI, Bing + Yandex Webmaster (if relevant), curl -I, robots.txt, sitemap, …
line 112
Distinctive:
Always note residual gaps: full backlink index, global keyword difficulty at scale, historical competitor exports — require paid data or …
line 113
Distinctive:
Security: follow Security and compliance above before suggesting any non-official API.
line 114

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Free SEO stack (Semrush / Ahrefs alternatives)

When to use

User mentions Semrush, Ahrefs, paid SEO suite, no budget, free site audit, keyword tool without subscription, backlink checker free, or wants a repeatable technical + rank baseline without vendor lock-in.
Complements geo-audit (GEO/AEO visibility): this skill is tooling + methodology, not full GEO scoring.

When not to use

Client explicitly pays for Semrush/Ahrefs and wants workflow inside those products.
Single trivial definition (“what is Domain Rating”) with no audit request.

Technology radar (what actually strengthens the stack)

Reality: no free drop-in replaces Ahrefs-scale backlink graph or Semrush-scale global keyword difficulty. The stack below is official APIs + owned measurement first; paid APIs only as explicit opt-in.

Tier	Sources	Role vs paid suites	your fit
S — Official, verified properties	GSC (Search Analytics + URL Inspection), CrUX, Lighthouse, PageSpeed/PSI API	Performance + your queries/pages + index status	Scripts in `scripts/visual-verify/`
S — Other engines (verify + API)	Bing Webmaster API (OAuth)	Queries, crawl issues, inbound links sample for Bing	Future script — same pattern as GSC: OAuth app, store tokens only in `your credentials config`
S — RU market	Yandex Webmaster API (OAuth)	Search queries / indexing for `.ru` properties	Same as Bing: official OAuth, no scrapers
A — Publishing / crawl hints	IndexNow	Push URLs to participating engines (Bing, etc.)	Not a rankings or backlink tool — runbook: host public key file on origin + `POST` submissions; key is not a vault secret (it is world-readable on the site)
B — Opt-in paid data	DataForSEO, SerpAPI, etc.	Volume, SERP snapshots at scale	Out of “free stack” — require budget + ToS review; keys only in `your credentials config`; never commit
Red — High risk	Gray SERP scrapers, “unofficial Google APIs”, shared cookie login services	May violate search engine ToS / account safety	Do not automate or recommend without legal + security sign-off; prefer official APIs

Integration map (your-repo)

Capability	Tool	Status
Lab CWV	`lighthouse-mobile.mjs`	Shipped
Field CWV	`crux-field-metrics.mjs`	Shipped (GCP key)
GSC performance	`gsc-api-search-analytics.mjs`	Shipped (SA JWT)
GSC index status	`gsc-url-inspection-inspect.mjs`	Shipped (SA JWT; quota-limited)
Crawl-lite / headers	`free-seo-alt-signals.mjs`	Shipped
PSI UI (fragile)	`psi-pagespeed-stealth.mjs`	Shipped (optional)
Bundle	`phase0-external-evidence.mjs`	Shipped; set `GSC_URL_INSPECTION=1` to include URL Inspection
Bing / Yandex	REST + OAuth	Documented here — implement when a property is verified and tokens are available

Security and compliance (mandatory for agents)

Secrets: API keys, service account JSON paths, OAuth refresh tokens → only local your credentials config (gitignored). Never paste into client chats, tickets, or public Gists.
Google Cloud keys: Restrict CrUX / PSI keys to the specific APIs; avoid unrestricted browser keys in automation.
GSC service account: Principle of least privilege; property must grant the SA in Search Console UI — no “share my Google password” flows.
URL Inspection: Strict daily quota — use --max and small URL sets; never loop full sitemaps in CI without a product decision.
IndexNow: The key file is published on the origin by design — treat it like robots.txt visibility, not like an API secret in 1Password.
Red tier: Avoid recommending third-party bulk Google SERP scrapers as “Semrush replacement” — ToS + account ban risk; disclose if user insists.

What paid suites usually provide (mental model)

Bucket	Typical paid feature	Free / owned substitute
Technical / CWV	Site Audit, Core Web Vitals views	Lighthouse (lab), CrUX API (field p75), PageSpeed
Search performance	Organic keywords, landing pages	GSC `searchanalytics`
Index state	(partially)	GSC URL Inspection (quota)
Rank tracking	Daily positions for a keyword list	SerpBear (your Hermes), Bing / Yandex Webmaster
Crawl / index	On-page issues, duplicates	GSC coverage, scripts (`robots.txt`, sitemaps, `curl -I`), `fetch` + HTML checks
Backlinks / authority	Link index, competitor links	No full free replacement — GSC Links (limited), Bing link reports, manual checks
Content / keyword research	Volume, difficulty, SERP features	GSC queries, manual SERP / PAA, Trends (context only)

your automation (your-repo)

If the workspace is your-repo (or a clone with scripts/visual-verify/):

Phase bundle (artifacts under .artifacts/hwai-phase0/):
```
node scripts/visual-verify/phase0-external-evidence.mjs
```
Optional env: SKIP_LIGHTHOUSE=1, SKIP_PSI_STEALTH=1, GSC_URL_INSPECTION=1 (adds URL Inspection for Phase0 URLs — uses quota).
Pieces
- Lab LCP / CLS / INP (mobile): node scripts/visual-verify/lighthouse-mobile.mjs
- Field CrUX (needs API key): node scripts/visual-verify/crux-field-metrics.mjs
- GSC top queries + pages (SA JWT): node scripts/visual-verify/gsc-api-search-analytics.mjs
  Resolves https://example/ vs sc-domain:example via sites.list (lib/gsc-site-resolve.mjs).
- GSC URL Inspection (index status, low quota):
  node scripts/visual-verify/gsc-url-inspection-inspect.mjs --url https://example.com/page
  or --from-phase0 / GSC_INSPECTION_URLS=... — use --max to cap calls.
- Free “crawl-lite”: node scripts/visual-verify/free-seo-alt-signals.mjs
- Optional pagespeed.web.dev with stealth Playwright: node scripts/visual-verify/psi-pagespeed-stealth.mjs
Credentials (local, never commit)
your credentials config: GSC service account, optional CHROME_UX_REPORT_API_KEY / GOOGLE_API_KEY.
See claude/KNOWLEDGE_BASE.md (Phase 0.4–0.6 row).
Rank / keyword gap
Hermes SerpBear — KB External Services → Hermes SerpBear; not a Semrush clone, but covers your keyword set on a schedule.

Agent workflow

Confirm goal: technical baseline, GSC performance, index checks, rank tracking, or “like Semrush report” (set expectations on backlinks/competitor depth).
If your repo available → run or instruct the scripts above; store JSON + README paths in .artifacts/.
If no repo → manual checklist: Lighthouse, GSC UI, CrUX in PSI, Bing + Yandex Webmaster (if relevant), curl -I, robots.txt, sitemap, IndexNow runbook if they own the origin.
Always note residual gaps: full backlink index, global keyword difficulty at scale, historical competitor exports — require paid data or primary research.
Security: follow Security and compliance above before suggesting any non-official API.

Team copy (hwai-internal)

Canonical long-form mapping: the SEO alternatives doc in your-internal-docs (from seed).
Install skill: skills/imported/free-seo-stack/SKILL.md → symlink to ~/.claude/skills/free-seo-stack per skills/README.md.

SSOT links (your-repo)

scripts/visual-verify/README.md
the SEO audit plan (Phase 0.4–0.6)
claude/KNOWLEDGE_BASE.md — search “Phase 0.4–0.6”

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free