Workflow·Marketing, SEO & Social

Backlink Audit

Name: Backlink Audit
Author: OpenClaudia

Audit a domain's backlink profile using the SemRush API.

You say

Buy it · $79 Read it before you buy $79 Written by OpenClaudia · unverified publisher

Context cost: 3.5k tokensestimated from the bundle, loaded when it triggers
Bundle: 1 file · 14.0 kBtext throughout, nothing executable
Licence: MITpaid listing
Last change: —no release on file
Servers it uses: Noneruns standalone

What it does

Audit a domain's backlink profile using the SemRush API. Use when the user says "audit backlinks", "check my backlinks", "backlink analysis", "link profile", "toxic links", "disavow", "link building opportunities", "referring domains", "anchor text", or asks about a site's link authority.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

seobacklinkssemrushlink-building

Filed under

Marketing, SEO & Social

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md14.0 kB · 378 lines

--- name: backlink-audit description: Audit a domain's backlink profile using the SemRush API. Use when the user says "audit backlinks", "check my backlinks", "backlink analysis", "link profile", "toxic links", "disavow", "link building opportunities", "referring domains", "anchor text", or asks about a site's link authority. ---

6# Backlink Audit Skill

8You are an expert link building strategist and backlink auditor. Use the SemRush API to analyze a domain's backlink profile, identify toxic links, and find link building opportunities.

10## Prerequisites

12This skill requires either SEMRUSH_API_KEY or AHREFS_API_KEY (or both). Check for them in environment variables or in ~/.claude/.env.global. Prefer whichever is available; if both are present, use SemRush as primary and Ahrefs to cross-reference. If neither is found, inform the user:

14```

15This skill requires a SemRush or Ahrefs API key. Set one via:

16 export SEMRUSH_API_KEY=your_key_here

17 export AHREFS_API_KEY=your_key_here

18Or add them to ~/.claude/.env.global

19```

21## SemRush Backlink API Endpoints

23Use curl via the Bash tool. Base URL: https://api.semrush.com/analytics/v1/

25### Core Endpoints

27**1. Backlinks Overview**

28```

29https://api.semrush.com/analytics/v1/?key={KEY}&type=backlinks_overview&target={domain}&target_type=root_domain&export_columns=total,domains_num,urls_num,ips_num,ipclassc_num,follows_num,nofollows_num,texts_num,images_num,forms_num,frames_num

30```

32**2. Backlinks List (individual links)**

33```

34https://api.semrush.com/analytics/v1/?key={KEY}&type=backlinks&target={domain}&target_type=root_domain&export_columns=source_url,source_title,target_url,anchor,external_num,internal_num,redirect,nofollow,image,first_seen,last_seen&display_limit=100&display_offset=0

35```

37**3. Referring Domains**

38```

39https://api.semrush.com/analytics/v1/?key={KEY}&type=backlinks_refdomains&target={domain}&target_type=root_domain&export_columns=domain,domain_ascore,backlinks_num,ip,country,first_seen,last_seen&display_limit=100&display_sort=domain_ascore_desc

40```

42**4. Anchor Text Distribution**

43```

44https://api.semrush.com/analytics/v1/?key={KEY}&type=backlinks_anchors&target={domain}&target_type=root_domain&export_columns=anchor,domains_num,backlinks_num&display_limit=50&display_sort=backlinks_num_desc

45```

47**5. Indexed Pages (pages receiving links)**

48```

49https://api.semrush.com/analytics/v1/?key={KEY}&type=backlinks_pages&target={domain}&target_type=root_domain&export_columns=target_url,backlinks_num,domains_num&display_limit=50&display_sort=backlinks_num_desc

50```

52**6. Competitor Backlinks (for comparison)**

53```

54# Reuse endpoints above with competitor domain as target

55```

57**7. Referring Domain Authority Score**

58Domain Authority Score (domain_ascore) is returned with referring domains and ranges 0-100.

60## Alternative: Ahrefs API

62If AHREFS_API_KEY is available (and SemRush is not), use the Ahrefs API v3 endpoints below. All endpoints require the Bearer token header.

64### Ahrefs Core Endpoints

66**1. Backlinks Overview (Stats)**

67```bash

68# Ahrefs backlinks overview

69curl -s "https://api.ahrefs.com/v3/site-explorer/backlinks-stats?target={domain}&output=json" \

70 -H "Authorization: Bearer ${AHREFS_API_KEY}"

71```

72Returns: live_backlinks, all_time_backlinks, live_refdomains, all_time_refdomains, live_refpages, dofollow_backlinks, nofollow_backlinks.

74**2. Referring Domains**

75```bash

76# Ahrefs referring domains

77curl -s "https://api.ahrefs.com/v3/site-explorer/refdomains?target={domain}&output=json&limit=100" \

78 -H "Authorization: Bearer ${AHREFS_API_KEY}"

79```

80Returns: Array of referring domains with domain, domain_rating, backlinks, first_seen, last_seen, dofollow, nofollow. Sort by domain_rating to see highest-authority referrers first.

82**3. Backlinks List**

83```bash

84curl -s "https://api.ahrefs.com/v3/site-explorer/backlinks?target={domain}&output=json&limit=100&mode=subdomains" \

85 -H "Authorization: Bearer ${AHREFS_API_KEY}"

86```

87Returns: Individual backlinks with url_from, url_to, anchor, domain_rating, first_seen, last_seen, nofollow, redirect, edu, gov.

89**4. Anchors**

90```bash

91curl -s "https://api.ahrefs.com/v3/site-explorer/anchors?target={domain}&output=json&limit=50&mode=subdomains" \

92 -H "Authorization: Bearer ${AHREFS_API_KEY}"

93```

94Returns: Anchor text distribution with anchor, backlinks, refdomains.

96**5. Pages by Backlinks (Best by Links)**

97```bash

98curl -s "https://api.ahrefs.com/v3/site-explorer/best-by-links?target={domain}&output=json&limit=50" \

99 -H "Authorization: Bearer ${AHREFS_API_KEY}"

100```

101Returns: Top linked pages with url, backlinks, refdomains, dofollow.

102

103**6. Domain Rating**

104```bash

105curl -s "https://api.ahrefs.com/v3/site-explorer/domain-rating?target={domain}&output=json" \

106 -H "Authorization: Bearer ${AHREFS_API_KEY}"

107```

108Returns: domain_rating (0-100) and ahrefs_rank.

109

110### Ahrefs vs. SemRush Field Mapping

111

112When using Ahrefs instead of SemRush, map the fields as follows:

113| SemRush Field | Ahrefs Equivalent | Notes |

114|---------------|-------------------|-------|

115| domain_ascore | domain_rating | Both are 0-100 authority scores |

116| total (backlinks) | live_backlinks | Ahrefs separates live vs. all-time |

117| domains_num | live_refdomains | Referring domains count |

118| follows_num | dofollow_backlinks | Dofollow link count |

119| nofollows_num | nofollow_backlinks | Nofollow link count |

120| first_seen / last_seen | first_seen / last_seen | Same concept, both available |

121

122The audit process (Steps 1-7 below) works identically regardless of which API you use. Simply substitute the corresponding endpoints and field names.

123

124## Audit Process

125

126### Step 1: Pull Backlink Overview

127

128Fetch the backlink overview and summarize:

129

130```markdown

131## Backlink Profile Summary: {domain}

132

133| Metric | Value |

134|--------|-------|

135| Total Backlinks | {total} |

136| Referring Domains | {domains_num} |

137| Referring IPs | {ips_num} |

138| Referring Subnets (Class C) | {ipclassc_num} |

139| Follow Links | {follows_num} ({%}) |

140| Nofollow Links | {nofollows_num} ({%}) |

141| Text Links | {texts_num} ({%}) |

142| Image Links | {images_num} ({%}) |

143| Backlink-to-Domain Ratio | {total/domains_num} |

144```

145

146### Step 2: Analyze Referring Domains

147

148Pull the top referring domains sorted by authority score. Evaluate:

149

150**Domain Quality Tiers:**

151

153|------|----------------|---------|--------|

159

160**Domain Quality Distribution:**

161Calculate the percentage of referring domains in each tier. A healthy profile should have:

162- Tier 1-2: at least 10-15% of referring domains

163- Tier 3: 30-40%

164- Tier 4: 20-30%

165- Tier 5: < 20% (flag if higher)

166

167**Diversity Analysis:**

168- Unique IPs vs. referring domains (ratio close to 1:1 is healthy)

169- Unique Class C subnets (should be close to IP count)

170- Country distribution (should match target market)

171- TLD distribution (.com, .org, .edu, .gov diversity is positive)

172

173### Step 3: Analyze Anchor Text Distribution

174

175Pull anchor text data and classify each anchor:

176

178|------------|---------------|-------------|---------|

187

188**Red flags in anchor text:**

189- Exact match > 10% = Over-optimized (Penguin risk)

190- Single anchor > 15% of total = Unnatural concentration

191- Money keyword anchors from low-quality sites = Likely spam

192- Irrelevant anchors (casino, pharma, adult) = Toxic links

193- Foreign language anchors unrelated to business = Likely spam

194

195### Step 4: Identify Toxic Links

196

197Score each backlink for toxicity based on these signals:

198

199**Toxicity Signals (each adds to a toxicity score 0-100):**

200

201| Signal | Weight | Detection Method |

202|--------|--------|-----------------|

203| Source domain AS < 10 | +15 | From referring domains data |

204| Source is known link farm/PBN pattern | +30 | Domain name patterns: keyword-keyword-keyword.com, random strings |

205| Anchor text is exact match keyword | +10 | From anchor text analysis |

206| Source page has 100+ external links | +20 | From external_num column |

207| Source is irrelevant niche | +15 | Compare source domain topic to target |

208| Source has no organic traffic | +15 | Check via domain_organic if budget allows |

209| Link from sitewide (footer/sidebar) | +10 | Same domain, many links to same target |

210| Link from non-indexed page | +20 | Page not in Google (manual check) |

211| Redirect chain to target | +10 | From redirect column |

212| Foreign language + irrelevant | +15 | From anchor text + domain TLD |

213

214**Toxicity Rating:**

215- 0-20: Clean - no action needed

216- 21-40: Monitor - watch for changes

217- 41-60: Suspicious - investigate further

218- 61-80: Likely toxic - consider disavow

219- 81-100: Toxic - add to disavow list

220

221### Step 5: Link Velocity Analysis

222

223Analyze the first_seen and last_seen dates to determine:

224

225- **Monthly new links** over the past 12 months

226- **Monthly lost links** (links where last_seen is in the past)

227- **Net link growth rate**

228- **Velocity spikes** (unnatural bursts of links)

229

230**Healthy velocity patterns:**

231- Steady, gradual growth = Natural

232- Correlated with content publishing = Natural

233- Sudden spike then flat = Likely campaign or mention (investigate)

234- Massive spike from low-quality domains = Negative SEO attack (flag immediately)

235- Declining trend = Losing links, need outreach

236

237### Step 6: Competitor Comparison

238

239Pull backlink overview for 2-3 competitors and compare:

240

241```markdown

242## Competitor Backlink Comparison

243

244| Metric | {Your Domain} | {Competitor 1} | {Competitor 2} | {Competitor 3} |

245|--------|--------------|----------------|----------------|----------------|

246| Total Backlinks | | | | |

247| Referring Domains | | | | |

248| Avg. Domain AS | | | | |

249| Follow % | | | | |

250| Link Growth (6mo) | | | | |

251```

252

253**Link Gap Analysis:**

254Find domains that link to competitors but not to the target:

2551. Pull top 100 referring domains for each competitor

2562. Filter out domains already linking to the target

2573. Sort by authority score

2584. These are outreach targets

259

260### Step 7: Generate Disavow File

261

262If toxic links are found, generate a Google Disavow file:

263

264```

265# Disavow file for {domain}

266# Generated: {date}

267# Total entries: {count}

268

269# Individual URLs (confirmed toxic)

270{url1}

271{url2}

272

273# Full domains (majority of links from domain are toxic)

274domain:{domain1}

275domain:{domain2}

276```

277

278**Disavow rules:**

279- Only disavow domains where 80%+ of their links are toxic

280- For mixed domains, disavow individual URLs

281- Never disavow high-authority domains (AS > 60) without manual verification

282- Always recommend the user review the list before submitting

283

284## Output Report Format

285

286```markdown

287# Backlink Audit Report: {domain}

288**Date:** {date}

289**Total Backlinks:** {total}

290**Referring Domains:** {count}

291**Health Score:** {score}/100

292

293## Executive Summary

294{2-3 sentences summarizing the health of the backlink profile}

295

296## Profile Overview

297{Overview table from Step 1}

298

299## Referring Domain Quality

300

301### Distribution by Authority

303|------|-------|-------|-----------|--------|

304| Tier 1 | 80-100 | {} | {}% | {Good/Needs more} |

305| ... | ... | ... | ... | ... |

306

307### Top 20 Referring Domains

309|--------|----------|-----------|-----------|--------|

310| {} | {} | {} | {} | {} |

311

312## Anchor Text Analysis

313

314### Distribution

315| Type | Percentage | Status |

316|------|-----------|--------|

317| Branded | {}% | {Healthy/Over/Under} |

318| ... | ... | ... |

319

320### Top 20 Anchors

322|--------|---------|-----------|------|

323| {} | {} | {} | {} |

324

325## Toxic Link Analysis

326

327### Summary

328- **Total toxic links found:** {count}

329- **Toxic referring domains:** {count}

330- **Recommended for disavow:** {count}

331

332### Toxic Links Detail

334|-----------|--------|---------------|---------|

335| {} | {} | {}/100 | {} |

336

337## Link Velocity

338{Monthly new/lost links chart description}

339{Assessment of velocity health}

340

341## Competitor Comparison

342{Comparison table}

343

344## Link Building Opportunities

345

346### Domains Linking to Competitors (Not You)

348|--------|----------|---------------------|-------------------|

349| {} | {} | {} | {} |

350

351### Recommended Link Building Tactics

3521. **{Tactic}** - {Description, estimated effort, expected results}

3532. ...

354

355## Action Items

356

357### Immediate (This Week)

3581. {Specific action}

359

360### Short Term (This Month)

3611. {Specific action}

362

363### Ongoing

3641. {Specific action}

365

366## Disavow File

367{If applicable, include the generated disavow file content}

368```

369

370## Notes

371

372- SemRush API has rate limits. Space out calls if making many requests.

373- Backlink data may be up to 30 days old. Note this in the report.

374- Never recommend disavowing links from legitimately authoritative domains.

375- For new sites (< 6 months), a small backlink profile is normal, not a problem.

376- Always recommend manual review of the disavow list before submission to Google Search Console.

377- If the user has Google Search Console access, recommend cross-referencing with GSC's link report for the most complete picture.

378

In the file

SKILL.md1,903 words

Files1

LicenceMIT

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈80

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

3,420

on trigger

The instruction body, read only when the skill fires.

1.8%

of a 200k window

Ten skills this size would take about 18% of the window before you open a file.

050k100k150k200k context window

3.5k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption

Installsnone yet

Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for

Writes filesno

Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

14 other skills in Marketing, SEO & Social

What is in the bundle

1 file, 14.0 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

SKILL.md14.0 kB

What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

$79 once

Backlink Audit · MIT · OpenClaudia

one-time

Price$79 once

LicenceMIT — the author’s, unchanged by this purchase

Paid throughStripe, once, on the card you add at the checkout

Keeps workingfor good — the files are yours once they are on disk

Updatesevery update its author ships, delivered through this account

You can read the whole bundle before paying — the SKILL.md above is the product, not a preview of it. What the money buys is the delivery: the folder packaged and handed to your machine by key, every update its author ships, and our support if it does not do what this listing says. The terms of use are MIT, set by the author and unchanged by buying it here.

Payment runs through Stripe, on a page like this one rather than a redirect. Once there is an account it joins the same mcprush invoice as everything else you run, so there is never a second card to enter.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/

Claude Desktop

ChatGPT

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok.grok/skills/

Zed.agents/skills/

Windsurf.windsurf/skills/

Agent SDK.claude/skills/

HTTP / API

This release

Versionnot versioned

Publishedno release date on file

Price$79

Referenceopenclaudia/backlink-audit

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

No earlier releases have been published to the marketplace.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

OpenClaudia

Publishes on mcprush.

0 servers listed2 skills listednot claimed

Profile

Publisher

Servers0