[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AF87VMT5VAAC67ME1YPYW6":3,"skill-same:01M7AF87VMT5VAAC67ME1YPYW6":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":6,"updatedAt":39,"install":40,"resources":52},"01M7AF87VMT5VAAC67ME1YPYW6","seo-backlinks",null,"Analyze a site's backlink profile, anchors, toxic signals, competitors, gaps, and disavow candidates. Use only when links or referring domains are the requested focus.","iamwaqargulzar\u002FMarketing-Agent-OS","iamwaqargulzar","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F96654715?v=4","01M7ACMBN0TACNXY53QYG8KDF6","Waqar Gulzar","01M7ACMBNP5ZX60H8CD3JK0633",8,"MIT","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-b\u002Fskills\u002Fseo-backlinks\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-b\u002Fskills\u002Fseo-backlinks\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: seo-backlinks\ndescription: \"Analyze a site's backlink profile, anchors, toxic signals, competitors, gaps, and disavow candidates. Use only when links or referring domains are the requested focus.\"\nuser-invocable: true\nargument-hint: \"\u003Curl>\"\nlicense: MIT\ncompatibility: \"Free: Common Crawl + verify always available. Optional: Moz API, Bing Webmaster, Keywords Everywhere (free signup). Premium: DataForSEO extension.\"\nmetadata:\n  author: AgriciDaniel\n  version: \"2.4.2\"\n  category: seo\n---\n\n# Backlink Profile Analysis\n\n## Source Detection\n\nBefore analysis, detect available data sources:\n\n1. **DataForSEO MCP** (premium): Check if `backlinks_summary` tool is available\n2. **Moz API** (free signup): `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check moz --json`\n3. **Bing Webmaster** (free signup): `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check bing --json`\n4. **Keywords Everywhere** (free signup; domain rank plus referring-domain count): `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check keywordseverywhere --json`\n5. **Common Crawl** (always available): Domain-level graph with PageRank\n6. **Verification Crawler** (always available): Checks if known backlinks still exist\n\nRun `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check --json` to detect all sources at once.\n\nIf no sources are configured beyond the always-available tier:\n- Still produce a report using Common Crawl domain metrics\n- Suggest: \"Run `\u002Fseo backlinks setup` to add free Moz and Bing API keys for richer data\"\n\n## Quick Reference\n\n| Command | Purpose |\n|---------|---------|\n| `\u002Fseo backlinks \u003Curl>` | Full backlink profile analysis (uses all available sources) |\n| `\u002Fseo backlinks gap \u003Curl1> \u003Curl2>` | Competitor backlink gap analysis |\n| `\u002Fseo backlinks toxic \u003Curl>` | Toxic link detection and disavow recommendations |\n| `\u002Fseo backlinks new \u003Curl>` | New and lost backlinks (DataForSEO only) |\n| `\u002Fseo backlinks verify \u003Curl> --links \u003Cfile>` | Verify known backlinks still exist |\n| `\u002Fseo backlinks setup` | Show setup instructions for free backlink APIs |\n\n## Analysis Framework\n\nProduce all 7 sections below. Each section lists data sources in preference order.\n\n### 1. Profile Overview\n\n**DataForSEO:** `backlinks_summary` → total backlinks, referring domains, domain rank, follow ratio, trend.\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py metrics \u003Curl> --json` → Domain Authority, Page Authority, Spam Score, linking root domains, external links.\n\n**Keywords Everywhere:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run keywordseverywhere_api.py rank \u003Cdomain> --json` → 0-10 Open PageRank (`open_page_rank`), a global `rank`, and a referring-domain count (`referring_domains`), per the current API; no anchors or individual links. Use as a fallback when Moz isn't configured; do not use in place of Moz when both are available.\n\n**Common Crawl:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run commoncrawl_graph.py \u003Cdomain> --json` → PageRank, harmonic centrality, and low-confidence rank\u002Fpresence data.\n\n**Scoring:**\n\n| Metric | Good | Warning | Critical |\n|--------|------|---------|----------|\n| Referring domains | >100 | 20-100 | \u003C20 |\n| Follow ratio | >60% | 40-60% | \u003C40% |\n| Domain diversity | No single domain >5% | 1 domain >10% | 1 domain >25% |\n| Trend | Growing or stable | Slow decline | Rapid decline (>20%\u002Fquarter) |\n\n### 2. Anchor Text Distribution\n\n**DataForSEO:** `backlinks_anchors`\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py anchors \u003Curl> --json`\n\n**Bing Webmaster:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run bing_webmaster.py links \u003Curl> --json` (extract anchor text from link details)\n\n**Healthy distribution benchmarks:**\n\n| Anchor Type | Target Range | Over-Optimization Signal |\n|-------------|-------------|-------------------------|\n| Branded (company\u002Fdomain name) | 30-50% | \u003C15% |\n| URL\u002Fnaked link | 15-25% | N\u002FA |\n| Generic (\"click here\", \"learn more\") | 10-20% | N\u002FA |\n| Exact match keyword | 3-10% | >15% |\n| Partial match keyword | 5-15% | >25% |\n| Long-tail \u002F natural | 5-15% | N\u002FA |\n\nFlag if exact-match anchors exceed 15% as a review heuristic; it may indicate unnatural or link-spam patterns.\n\n### 3. Referring Domain Quality\n\n**DataForSEO:** `backlinks_referring_domains`\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py domains \u003Curl> --json` → domains with DA scores\n\n**Common Crawl:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run commoncrawl_graph.py \u003Cdomain> --json` → domain-level rank\u002Fpresence data, no verified referring-domain counts\n\nAnalyze:\n- **TLD distribution**: .edu, .gov, .org = high authority. Excessive .xyz, .info = low quality\n- **Country distribution**: Match target market. 80%+ from irrelevant countries = PBN signal\n- **Domain rank distribution**: Healthy profiles have links from all authority tiers\n- **Follow\u002Fnofollow per domain**: Sites that only nofollow = limited SEO value\n\n### 4. Toxic Link Detection\n\n**DataForSEO:** `backlinks_bulk_spam_score` + toxic patterns from reference\n\n**Moz API:** Raw vendor spam_score from `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py metrics \u003Curl> --json` (source-label the value; apply thresholds only if verified against current Moz docs)\n\n**Verification Crawler:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run verify_backlinks.py --target \u003Curl> --links \u003Cfile> --json` (verify suspicious links still exist)\n\n**High-risk indicators (flag immediately):**\n- Links from known PBN (Private Blog Network) domains\n- Unnatural anchor text patterns (100% exact match from a domain)\n- Links from penalized or deindexed domains\n- Mass directory submissions (50+ directory links)\n- Link farms (sites with 10K+ outbound links per page)\n- Paid link patterns (footer\u002Fsidebar links across all pages of a domain)\n\n**Medium-risk indicators (review manually):**\n- Links from unrelated niches\n- Reciprocal link patterns\n- Links from thin content pages (\u003C100 words)\n- Excessive links from a single domain (>50 backlinks from 1 domain)\n\nLoad `..\u002Fseo\u002Freferences\u002Fbacklink-quality.md` for the full 30 toxic patterns and disavow criteria.\n\n### 5. Top Pages by Backlinks\n\n**DataForSEO:** `backlinks_backlinks` with target type \"page\"\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py pages \u003Cdomain> --json`\n\nFind:\n- Which pages attract the most backlinks\n- Pages with high-authority links (link magnets)\n- Pages with zero backlinks (internal linking opportunities)\n- 404 pages with backlinks (redirect opportunities to reclaim link equity)\n\n### 6. Competitor Gap Analysis\n\n**DataForSEO:** `backlinks_referring_domains` for both domains, then compare\n\n**Bing Webmaster:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run bing_webmaster.py compare \u003Curl1> \u003Curl2> --json`\nonly when both properties are registered and accessible to the same Bing API\naccount. For arbitrary competitors, use DataForSEO, Moz, or Common Crawl.\n\n**Moz API:** Compare DA\u002FPA between domains via `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py metrics \u003Curl> --json` for each\n\nOutput:\n- Domains linking to competitor but NOT to target = link building opportunities\n- Domains linking to both = validate existing relationships\n- Domains linking only to target = competitive advantage\n- Top 20 link building opportunities with domain authority\n\n### 7. New and Lost Backlinks\n\n**DataForSEO only:** `backlinks_backlinks` with date filters for 30\u002F60\u002F90 day changes\n\n**Verification Crawler:** For known links, verify current status with `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run verify_backlinks.py --target \u003Curl> --links \u003Cfile> --json`\n\n**Note:** Free sources cannot track new\u002Flost links over time. If this section is requested without DataForSEO, inform the user: \"Link velocity tracking requires the DataForSEO extension. Free sources provide point-in-time snapshots only.\"\n\n**Red flags:**\n- Sudden spike in new links (possible negative SEO attack)\n- Sudden loss of many links (site penalty or content removal)\n- Declining velocity over 3+ months (content not attracting links)\n\n## Backlink Health Score\n\nCalculate a 0-100 score. When mixing sources, apply confidence weighting:\n\n| Factor | Weight | Sources (preference order) | Confidence |\n|--------|--------|---------------------------|------------|\n| Referring domain count | 20% | DataForSEO > Moz | 1.0 \u002F 0.85 |\n| Domain quality distribution | 20% | DataForSEO > Moz DA distribution | 1.0 \u002F 0.85 |\n| Anchor text naturalness | 15% | DataForSEO > Moz > Bing anchors | 1.0 \u002F 0.85 \u002F 0.70 |\n| Toxic link ratio | 20% | DataForSEO > Moz spam score | 1.0 \u002F 0.85 |\n| Link velocity trend | 10% | DataForSEO only | 1.0 |\n| Follow\u002Fnofollow ratio | 5% | DataForSEO > Bing details | 1.0 \u002F 0.70 |\n| Geographic relevance | 10% | DataForSEO > Bing country | 1.0 \u002F 0.70 |\n\n**Data sufficiency gate:** Count how many of the 7 factors have at least one data source available.\n- **4+ factors with data:** Produce a numeric 0-100 score (redistribute missing weights proportionally)\n- **Fewer than 4 factors:** Do NOT produce a numeric score. Instead display:\n  ```\n  Backlink Health Score: INSUFFICIENT DATA (X\u002F7 factors scored)\n  ```\n  Show individual factor scores that ARE available with their source and confidence.\n  Recommend: \"Configure Moz API (free) for a scoreable profile. Run `\u002Fseo backlinks setup`\"\n\n### MUST NOT: score what you did not measure\n\n**When Common Crawl is the only available source, you MUST NOT produce a numeric\nscore of any kind** -- not a health score, not a per-factor score, not an\n\"approximate\" or \"estimated\" figure. Common Crawl supplies rank and presence\nsignals only. Report low-confidence rank\u002Fpresence data and the literal string\n`Not Assessed` in place of every number.\n\n**A finding written with `source: not-assessed` MUST NOT carry a numeric score.**\n\nA numeric score with fewer than 4 data sources is **misleading**: it implies poor\nhealth when the reality is that we simply lack data.\n\n### Validation gate (required, not optional)\n\nThis rule has been stated in this skill before and was violated anyway, so it is\nnow checkable. **Before writing any backlink output, run the validator:**\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run validate_backlink_report.py --report \u003Creport>.json --json\n```\n\nPass the sources you actually collected (`cc_data`, `moz_data`, `bing_data`,\n`dataforseo_data`, `scoring_factors`, and your `findings` list). The\n`source_score_consistency` check fails the report with `status: FAIL` when:\n\n- a numeric score is present but no scoreable source (Moz, Bing, or DataForSEO)\n  supplied data -- i.e. the Common-Crawl-only case, and\n- any finding marked `source: not-assessed` carries a numeric `score`, `value`,\n  or `health_score`.\n\n**If the validator returns `status: FAIL`, do not present the report.** Fix the\nfindings -- replace the offending numbers with `Not Assessed` -- and re-run until\nit passes.\n\n## Output Format\n\n### Backlink Health Score: XX\u002F100 (or INSUFFICIENT DATA)\n\n| Section | Status | Score | Data Source |\n|---------|--------|-------|-------------|\n| Profile Overview | pass\u002Fwarn\u002Ffail | XX\u002F100 | Moz (0.85) |\n| Anchor Distribution | pass\u002Fwarn\u002Ffail | XX\u002F100 | Moz (0.85) |\n| Referring Domain Quality | pass\u002Fwarn\u002Ffail | XX\u002F100 | CC (0.50) |\n| Toxic Links | pass\u002Fwarn\u002Ffail | XX\u002F100 | Moz Spam (0.85) |\n| Top Pages | info | N\u002FA | Moz (0.85) |\n| Link Velocity | pass\u002Fwarn\u002Ffail | XX\u002F100 | DataForSEO only |\n\n### Critical Issues (fix immediately)\n### High Priority (fix within 1 month)\n### Medium Priority (ongoing improvement)\n### Link Building Opportunities (top 10)\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|-----------|\n| No sources configured | No API keys, no DataForSEO | Run `\u002Fseo backlinks setup` |\n| Moz rate limit | Free tier: 1 req\u002F10s | Wait 10 seconds, retry. Built into script. |\n| Bing site not verified | Site not verified in Bing | Verify at https:\u002F\u002Fwww.bing.com\u002Fwebmasters |\n| CC download timeout | Large graph file, slow connection | Use `--timeout 180` flag |\n| DataForSEO unavailable | Extension not installed | Run `.\u002Fextensions\u002Fdataforseo\u002Finstall.sh` |\n| No backlink data returned | Domain too new or very small | Note: small sites may have \u003C10 backlinks |\n\n**Fallback cascade:**\n1. DataForSEO available? → Use as primary (confidence: 1.0)\n2. Moz configured? → Use for DA\u002FPA\u002Fspam\u002Fanchors (confidence: 0.85)\n3. Bing configured? → Use for registered-property links and comparison only\n   when both properties are accessible (confidence: 0.70)\n4. Moz not configured but Keywords Everywhere is? → Use for a Profile Overview\n   rank-only fallback (confidence: 0.60; single metric, no link counts\u002Fanchors)\n5. Always: Common Crawl for domain-level metrics (confidence: 0.50)\n6. Always: Verification crawler for known link checks (confidence: 0.95)\n7. Nothing works? → \"Run `\u002Fseo backlinks setup` to configure free APIs\"\n\n## Pre-Delivery Review (MANDATORY)\n\nBefore presenting any backlink analysis to the user, run this checklist internally.\nDo NOT skip this step. Fix any issues found before showing the report.\n\n### Fact-Check Every Claim\n- [ ] **Schema claims**: Did parse_html return `@type` for each block? If any `@type` is missing,\n      re-check, it may use `@graph` wrapper (valid JSON-LD, not malformed).\n- [ ] **\"link_removed\" findings**: Is the page JS-rendered? If `unverifiable_js`, say so, never\n      report a JS-rendered page as \"link removed\" (that's a false negative).\n- [ ] **H1 findings**: Are any H1s in the `h1_suspicious` list? If so, note they are likely\n      counters\u002Fstats, not semantic headings.\n- [ ] **Reciprocal links**: If site A links to site B AND B links back to A, flag it as a\n      reciprocal link pattern. Check outbound links against verified inbound sources.\n- [ ] **Health score**: Are 4+ of 7 factors scored? If not, report INSUFFICIENT DATA, never\n      show a misleading numeric score.\n\n### Verify Data Source Labels\n- [ ] Every metric in the report has a source label (e.g., \"Parsed (0.95)\", \"CC (0.50)\")\n- [ ] Every \"not found\" result distinguishes between \"not crawled\" vs \"below threshold\" vs \"error\"\n- [ ] Social media pages flagged as `unverifiable_js` (not `link_removed`)\n\n### Cross-Check Consistency\n- [ ] Platform detection matches actual signals (check for wp-content, shopify CDN, etc.)\n- [ ] Referring domain count in summary matches the actual verified links list\n- [ ] No claim is presented without a data source backing it\n\nIf ANY check fails, fix the finding before presenting. Never present inferred data as fact.\n\n## Post-Analysis\n\nAfter completing any backlink analysis command, always offer:\n\"Generate a professional PDF report? Use `\u002Fseo google report`\"\n\n## Reference Documentation\n\nLoad on demand (do NOT load at startup):\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fseo\u002Freferences\u002Fbacklink-quality.md` -- Detailed toxic link patterns and scoring methodology (shared reference, load when analyzing toxic links or spam scores)\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fseo\u002Freferences\u002Ffree-backlink-sources.md` -- Source comparison, confidence weighting, setup guides (shared reference, load when configuring free backlink APIs)\n","# Backlink Profile Analysis\n\n## Source Detection\n\nBefore analysis, detect available data sources:\n\n1. **DataForSEO MCP** (premium): Check if `backlinks_summary` tool is available\n2. **Moz API** (free signup): `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check moz --json`\n3. **Bing Webmaster** (free signup): `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check bing --json`\n4. **Keywords Everywhere** (free signup; domain rank plus referring-domain count): `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check keywordseverywhere --json`\n5. **Common Crawl** (always available): Domain-level graph with PageRank\n6. **Verification Crawler** (always available): Checks if known backlinks still exist\n\nRun `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run backlinks_auth.py --check --json` to detect all sources at once.\n\nIf no sources are configured beyond the always-available tier:\n- Still produce a report using Common Crawl domain metrics\n- Suggest: \"Run `\u002Fseo backlinks setup` to add free Moz and Bing API keys for richer data\"\n\n## Quick Reference\n\n| Command | Purpose |\n|---------|---------|\n| `\u002Fseo backlinks \u003Curl>` | Full backlink profile analysis (uses all available sources) |\n| `\u002Fseo backlinks gap \u003Curl1> \u003Curl2>` | Competitor backlink gap analysis |\n| `\u002Fseo backlinks toxic \u003Curl>` | Toxic link detection and disavow recommendations |\n| `\u002Fseo backlinks new \u003Curl>` | New and lost backlinks (DataForSEO only) |\n| `\u002Fseo backlinks verify \u003Curl> --links \u003Cfile>` | Verify known backlinks still exist |\n| `\u002Fseo backlinks setup` | Show setup instructions for free backlink APIs |\n\n## Analysis Framework\n\nProduce all 7 sections below. Each section lists data sources in preference order.\n\n### 1. Profile Overview\n\n**DataForSEO:** `backlinks_summary` → total backlinks, referring domains, domain rank, follow ratio, trend.\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py metrics \u003Curl> --json` → Domain Authority, Page Authority, Spam Score, linking root domains, external links.\n\n**Keywords Everywhere:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run keywordseverywhere_api.py rank \u003Cdomain> --json` → 0-10 Open PageRank (`open_page_rank`), a global `rank`, and a referring-domain count (`referring_domains`), per the current API; no anchors or individual links. Use as a fallback when Moz isn't configured; do not use in place of Moz when both are available.\n\n**Common Crawl:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run commoncrawl_graph.py \u003Cdomain> --json` → PageRank, harmonic centrality, and low-confidence rank\u002Fpresence data.\n\n**Scoring:**\n\n| Metric | Good | Warning | Critical |\n|--------|------|---------|----------|\n| Referring domains | >100 | 20-100 | \u003C20 |\n| Follow ratio | >60% | 40-60% | \u003C40% |\n| Domain diversity | No single domain >5% | 1 domain >10% | 1 domain >25% |\n| Trend | Growing or stable | Slow decline | Rapid decline (>20%\u002Fquarter) |\n\n### 2. Anchor Text Distribution\n\n**DataForSEO:** `backlinks_anchors`\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py anchors \u003Curl> --json`\n\n**Bing Webmaster:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run bing_webmaster.py links \u003Curl> --json` (extract anchor text from link details)\n\n**Healthy distribution benchmarks:**\n\n| Anchor Type | Target Range | Over-Optimization Signal |\n|-------------|-------------|-------------------------|\n| Branded (company\u002Fdomain name) | 30-50% | \u003C15% |\n| URL\u002Fnaked link | 15-25% | N\u002FA |\n| Generic (\"click here\", \"learn more\") | 10-20% | N\u002FA |\n| Exact match keyword | 3-10% | >15% |\n| Partial match keyword | 5-15% | >25% |\n| Long-tail \u002F natural | 5-15% | N\u002FA |\n\nFlag if exact-match anchors exceed 15% as a review heuristic; it may indicate unnatural or link-spam patterns.\n\n### 3. Referring Domain Quality\n\n**DataForSEO:** `backlinks_referring_domains`\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py domains \u003Curl> --json` → domains with DA scores\n\n**Common Crawl:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run commoncrawl_graph.py \u003Cdomain> --json` → domain-level rank\u002Fpresence data, no verified referring-domain counts\n\nAnalyze:\n- **TLD distribution**: .edu, .gov, .org = high authority. Excessive .xyz, .info = low quality\n- **Country distribution**: Match target market. 80%+ from irrelevant countries = PBN signal\n- **Domain rank distribution**: Healthy profiles have links from all authority tiers\n- **Follow\u002Fnofollow per domain**: Sites that only nofollow = limited SEO value\n\n### 4. Toxic Link Detection\n\n**DataForSEO:** `backlinks_bulk_spam_score` + toxic patterns from reference\n\n**Moz API:** Raw vendor spam_score from `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py metrics \u003Curl> --json` (source-label the value; apply thresholds only if verified against current Moz docs)\n\n**Verification Crawler:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run verify_backlinks.py --target \u003Curl> --links \u003Cfile> --json` (verify suspicious links still exist)\n\n**High-risk indicators (flag immediately):**\n- Links from known PBN (Private Blog Network) domains\n- Unnatural anchor text patterns (100% exact match from a domain)\n- Links from penalized or deindexed domains\n- Mass directory submissions (50+ directory links)\n- Link farms (sites with 10K+ outbound links per page)\n- Paid link patterns (footer\u002Fsidebar links across all pages of a domain)\n\n**Medium-risk indicators (review manually):**\n- Links from unrelated niches\n- Reciprocal link patterns\n- Links from thin content pages (\u003C100 words)\n- Excessive links from a single domain (>50 backlinks from 1 domain)\n\nLoad `..\u002Fseo\u002Freferences\u002Fbacklink-quality.md` for the full 30 toxic patterns and disavow criteria.\n\n### 5. Top Pages by Backlinks\n\n**DataForSEO:** `backlinks_backlinks` with target type \"page\"\n\n**Moz API:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py pages \u003Cdomain> --json`\n\nFind:\n- Which pages attract the most backlinks\n- Pages with high-authority links (link magnets)\n- Pages with zero backlinks (internal linking opportunities)\n- 404 pages with backlinks (redirect opportunities to reclaim link equity)\n\n### 6. Competitor Gap Analysis\n\n**DataForSEO:** `backlinks_referring_domains` for both domains, then compare\n\n**Bing Webmaster:** `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run bing_webmaster.py compare \u003Curl1> \u003Curl2> --json`\nonly when both properties are registered and accessible to the same Bing API\naccount. For arbitrary competitors, use DataForSEO, Moz, or Common Crawl.\n\n**Moz API:** Compare DA\u002FPA between domains via `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run moz_api.py metrics \u003Curl> --json` for each\n\nOutput:\n- Domains linking to competitor but NOT to target = link building opportunities\n- Domains linking to both = validate existing relationships\n- Domains linking only to target = competitive advantage\n- Top 20 link building opportunities with domain authority\n\n### 7. New and Lost Backlinks\n\n**DataForSEO only:** `backlinks_backlinks` with date filters for 30\u002F60\u002F90 day changes\n\n**Verification Crawler:** For known links, verify current status with `\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run verify_backlinks.py --target \u003Curl> --links \u003Cfile> --json`\n\n**Note:** Free sources cannot track new\u002Flost links over time. If this section is requested without DataForSEO, inform the user: \"Link velocity tracking requires the DataForSEO extension. Free sources provide point-in-time snapshots only.\"\n\n**Red flags:**\n- Sudden spike in new links (possible negative SEO attack)\n- Sudden loss of many links (site penalty or content removal)\n- Declining velocity over 3+ months (content not attracting links)\n\n## Backlink Health Score\n\nCalculate a 0-100 score. When mixing sources, apply confidence weighting:\n\n| Factor | Weight | Sources (preference order) | Confidence |\n|--------|--------|---------------------------|------------|\n| Referring domain count | 20% | DataForSEO > Moz | 1.0 \u002F 0.85 |\n| Domain quality distribution | 20% | DataForSEO > Moz DA distribution | 1.0 \u002F 0.85 |\n| Anchor text naturalness | 15% | DataForSEO > Moz > Bing anchors | 1.0 \u002F 0.85 \u002F 0.70 |\n| Toxic link ratio | 20% | DataForSEO > Moz spam score | 1.0 \u002F 0.85 |\n| Link velocity trend | 10% | DataForSEO only | 1.0 |\n| Follow\u002Fnofollow ratio | 5% | DataForSEO > Bing details | 1.0 \u002F 0.70 |\n| Geographic relevance | 10% | DataForSEO > Bing country | 1.0 \u002F 0.70 |\n\n**Data sufficiency gate:** Count how many of the 7 factors have at least one data source available.\n- **4+ factors with data:** Produce a numeric 0-100 score (redistribute missing weights proportionally)\n- **Fewer than 4 factors:** Do NOT produce a numeric score. Instead display:\n  ```\n  Backlink Health Score: INSUFFICIENT DATA (X\u002F7 factors scored)\n  ```\n  Show individual factor scores that ARE available with their source and confidence.\n  Recommend: \"Configure Moz API (free) for a scoreable profile. Run `\u002Fseo backlinks setup`\"\n\n### MUST NOT: score what you did not measure\n\n**When Common Crawl is the only available source, you MUST NOT produce a numeric\nscore of any kind** -- not a health score, not a per-factor score, not an\n\"approximate\" or \"estimated\" figure. Common Crawl supplies rank and presence\nsignals only. Report low-confidence rank\u002Fpresence data and the literal string\n`Not Assessed` in place of every number.\n\n**A finding written with `source: not-assessed` MUST NOT carry a numeric score.**\n\nA numeric score with fewer than 4 data sources is **misleading**: it implies poor\nhealth when the reality is that we simply lack data.\n\n### Validation gate (required, not optional)\n\nThis rule has been stated in this skill before and was violated anyway, so it is\nnow checkable. **Before writing any backlink output, run the validator:**\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fclaude-seo\" run validate_backlink_report.py --report \u003Creport>.json --json\n```\n\nPass the sources you actually collected (`cc_data`, `moz_data`, `bing_data`,\n`dataforseo_data`, `scoring_factors`, and your `findings` list). The\n`source_score_consistency` check fails the report with `status: FAIL` when:\n\n- a numeric score is present but no scoreable source (Moz, Bing, or DataForSEO)\n  supplied data -- i.e. the Common-Crawl-only case, and\n- any finding marked `source: not-assessed` carries a numeric `score`, `value`,\n  or `health_score`.\n\n**If the validator returns `status: FAIL`, do not present the report.** Fix the\nfindings -- replace the offending numbers with `Not Assessed` -- and re-run until\nit passes.\n\n## Output Format\n\n### Backlink Health Score: XX\u002F100 (or INSUFFICIENT DATA)\n\n| Section | Status | Score | Data Source |\n|---------|--------|-------|-------------|\n| Profile Overview | pass\u002Fwarn\u002Ffail | XX\u002F100 | Moz (0.85) |\n| Anchor Distribution | pass\u002Fwarn\u002Ffail | XX\u002F100 | Moz (0.85) |\n| Referring Domain Quality | pass\u002Fwarn\u002Ffail | XX\u002F100 | CC (0.50) |\n| Toxic Links | pass\u002Fwarn\u002Ffail | XX\u002F100 | Moz Spam (0.85) |\n| Top Pages | info | N\u002FA | Moz (0.85) |\n| Link Velocity | pass\u002Fwarn\u002Ffail | XX\u002F100 | DataForSEO only |\n\n### Critical Issues (fix immediately)\n### High Priority (fix within 1 month)\n### Medium Priority (ongoing improvement)\n### Link Building Opportunities (top 10)\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|-----------|\n| No sources configured | No API keys, no DataForSEO | Run `\u002Fseo backlinks setup` |\n| Moz rate limit | Free tier: 1 req\u002F10s | Wait 10 seconds, retry. Built into script. |\n| Bing site not verified | Site not verified in Bing | Verify at https:\u002F\u002Fwww.bing.com\u002Fwebmasters |\n| CC download timeout | Large graph file, slow connection | Use `--timeout 180` flag |\n| DataForSEO unavailable | Extension not installed | Run `.\u002Fextensions\u002Fdataforseo\u002Finstall.sh` |\n| No backlink data returned | Domain too new or very small | Note: small sites may have \u003C10 backlinks |\n\n**Fallback cascade:**\n1. DataForSEO available? → Use as primary (confidence: 1.0)\n2. Moz configured? → Use for DA\u002FPA\u002Fspam\u002Fanchors (confidence: 0.85)\n3. Bing configured? → Use for registered-property links and comparison only\n   when both properties are accessible (confidence: 0.70)\n4. Moz not configured but Keywords Everywhere is? → Use for a Profile Overview\n   rank-only fallback (confidence: 0.60; single metric, no link counts\u002Fanchors)\n5. Always: Common Crawl for domain-level metrics (confidence: 0.50)\n6. Always: Verification crawler for known link checks (confidence: 0.95)\n7. Nothing works? → \"Run `\u002Fseo backlinks setup` to configure free APIs\"\n\n## Pre-Delivery Review (MANDATORY)\n\nBefore presenting any backlink analysis to the user, run this checklist internally.\nDo NOT skip this step. Fix any issues found before showing the report.\n\n### Fact-Check Every Claim\n- [ ] **Schema claims**: Did parse_html return `@type` for each block? If any `@type` is missing,\n      re-check, it may use `@graph` wrapper (valid JSON-LD, not malformed).\n- [ ] **\"link_removed\" findings**: Is the page JS-rendered? If `unverifiable_js`, say so, never\n      report a JS-rendered page as \"link removed\" (that's a false negative).\n- [ ] **H1 findings**: Are any H1s in the `h1_suspicious` list? If so, note they are likely\n      counters\u002Fstats, not semantic headings.\n- [ ] **Reciprocal links**: If site A links to site B AND B links back to A, flag it as a\n      reciprocal link pattern. Check outbound links against verified inbound sources.\n- [ ] **Health score**: Are 4+ of 7 factors scored? If not, report INSUFFICIENT DATA, never\n      show a misleading numeric score.\n\n### Verify Data Source Labels\n- [ ] Every metric in the report has a source label (e.g., \"Parsed (0.95)\", \"CC (0.50)\")\n- [ ] Every \"not found\" result distinguishes between \"not crawled\" vs \"below threshold\" vs \"error\"\n- [ ] Social media pages flagged as `unverifiable_js` (not `link_removed`)\n\n### Cross-Check Consistency\n- [ ] Platform detection matches actual signals (check for wp-content, shopify CDN, etc.)\n- [ ] Referring domain count in summary matches the actual verified links list\n- [ ] No claim is presented without a data source backing it\n\nIf ANY check fails, fix the finding before presenting. Never present inferred data as fact.\n\n## Post-Analysis\n\nAfter completing any backlink analysis command, always offer:\n\"Generate a professional PDF report? Use `\u002Fseo google report`\"\n\n## Reference Documentation\n\nLoad on demand (do NOT load at startup):\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fseo\u002Freferences\u002Fbacklink-quality.md` -- Detailed toxic link patterns and scoring methodology (shared reference, load when analyzing toxic links or spam scores)\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fseo\u002Freferences\u002Ffree-backlink-sources.md` -- Source comparison, confidence weighting, setup guides (shared reference, load when configuring free backlink APIs)\n",{"name":5,"license":15,"metadata":25,"description":7,"argument-hint":29,"compatibility":30,"user-invocable":31},{"author":26,"version":27,"category":28},"AgriciDaniel","2.4.2","seo","\u003Curl>","Free: Common Crawl + verify always available. Optional: Moz API, Bing Webmaster, Keywords Everywhere (free signup). Premium: DataForSEO extension.",true,"main","ad108f7eb3f6764136d02fb875772ebb34f54078","upstreams\u002Fsource-b\u002Fskills\u002Fseo-backlinks",2,"https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar","iamwaqargulzar.com","2026-11-03 21:14:34",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":31},[42,45,48],{"tool":43,"command":44},"npx","npx skills add iamwaqargulzar\u002FMarketing-Agent-OS --skill seo-backlinks",{"tool":46,"command":47},"bunx","bunx skills add iamwaqargulzar\u002FMarketing-Agent-OS --skill seo-backlinks",{"tool":49,"command":50},"pnpm","pnpm dlx skills add iamwaqargulzar\u002FMarketing-Agent-OS --skill seo-backlinks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-b\u002Fskills\u002Fseo-backlinks\u002FSKILL.md",[53],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",143,[59,67,74,81,88,95],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":20},"01M7AG5VYEX7J2R2AAD54A7YT7","video","When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Sora,' 'Runway,' 'Kling,' 'Seedance,' 'Hailuo,' 'MiniMax,' 'Pika,' 'Hunyuan,' 'Wan,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'record a product demo,' 'feature demo video,' 'in-app demo,' 'video pipeline,' 'copy this edit,' 'match this video style,' 'reverse-engineer this video,' 'edit like this reference,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social. For paid video ad creative, see ad-creative.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-d\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":20},"01M7AG5FMXWA33FQDNS9PS1TE6","social","When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter\u002FX, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'social media strategy,' 'grow my following,' 'TikTok video,' 'Reels,' 'Shorts,' 'video script,' 'video hook,' 'short-form video,' 'create a reel,' 'social listening,' 'brand mentions,' 'competitor monitoring,' 'top posts to comment on,' 'find people asking for,' 'carousel,' 'slide-by-slide,' or 'document post.' Use this for social content, repurposing, scheduling, video scripts, and listening. Posts avoid AI tells like 'it's not X, it's Y' reveals and broetry. For broader content strategy, see content-strategy. For paid ads, see ad-creative. For earned media, see public-relations.","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-d\u002Fskills\u002Fsocial\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":20},"01M7AG559W96W3DGE31KXYY78S","sms","When the user wants to plan, build, or optimize SMS, MMS, or WhatsApp marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional\u002Fauth SMS. Also use when the user mentions \"SMS marketing,\" \"text message campaigns,\" \"SMS sequence,\" \"SMS automation,\" \"abandoned cart text,\" \"post-purchase SMS,\" \"Klaviyo SMS,\" \"Postscript,\" \"Attentive,\" \"Twilio,\" \"A2P 10DLC,\" \"TCPA,\" \"SMS compliance,\" \"short code,\" \"toll-free SMS,\" \"MMS campaign,\" \"should I do SMS,\" \"SMS vs email,\" \"WhatsApp marketing,\" \"WhatsApp Business API,\" \"WhatsApp templates,\" or \"click-to-WhatsApp.\" For email sequences, see emails. For SMS copy framing, see copywriting. For opt-in popups that capture phone numbers, see popups.","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-d\u002Fskills\u002Fsms\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":20},"01M7AG4WJ9EDSECNTQN0FEAYCQ","site-architecture","When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user mentions \"sitemap,\" \"site map,\" \"visual sitemap,\" \"site structure,\" \"page hierarchy,\" \"information architecture,\" \"IA,\" \"navigation design,\" \"URL structure,\" \"breadcrumbs,\" \"internal linking strategy,\" \"website planning,\" \"what pages do I need,\" \"how should I organize my site,\" \"site navigation,\" \"which website builder should I use,\" \"migrate my website,\" or \"add a blog to my existing site.\" Use this whenever someone is planning what pages a website should have, how they connect, and where to build them. NOT for XML sitemaps (that's technical SEO — see seo-audit). For SEO audits, see seo-audit. For structured data, see schema.","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-d\u002Fskills\u002Fsite-architecture\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":20},"01M7AG4MH58GRMSHC0TADAWQ69","signup","When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions \"signup conversions,\" \"registration friction,\" \"signup form optimization,\" \"free trial signup,\" \"reduce signup dropoff,\" \"account creation flow,\" \"people aren't signing up,\" \"signup abandonment,\" \"trial conversion rate,\" \"nobody completes registration,\" \"too many steps to sign up,\" or \"simplify our signup.\" Use this whenever the user has a signup or registration flow that isn't performing. For post-signup onboarding, see onboarding. For lead capture forms (not account creation), see cro.","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-d\u002Fskills\u002Fsignup\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":20},"01M7AG4CGGH35KYDFHYSS1BQZ5","seo-audit","When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions \"SEO audit,\" \"technical SEO,\" \"why am I not ranking,\" \"SEO issues,\" \"on-page SEO,\" \"meta tags review,\" \"SEO health check,\" \"my traffic dropped,\" \"lost rankings,\" \"not showing up in Google,\" \"site isn't ranking,\" \"Google update hit me,\" \"page speed,\" \"core web vitals,\" \"crawl errors,\" \"indexing issues,\" \"stuck on page 2,\" \"striking distance keywords,\" \"title tag rewrite,\" \"low CTR,\" \"local SEO,\" \"Google Business Profile,\" or \"map pack.\" Use this even if the user just says something vague like \"my SEO is bad\" or \"help with SEO\" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.","https:\u002F\u002Fgithub.com\u002Fiamwaqargulzar\u002FMarketing-Agent-OS\u002Fblob\u002Fmain\u002Fupstreams\u002Fsource-d\u002Fskills\u002Fseo-audit\u002FSKILL.md",[],[]]