aiskillstore/marketplace / skills/aaron-he-zhu/offsite-signal-analyzer
offsite-signal-analyzer
VerifiedUse when the user asks to "analyze backlinks", "analyze my off-site signals", or "track AI traffic / ChatGPT / Perplexity referrals"; profiles referring domains, anchor-text mix, toxic links, and disavow candidates (backlinks mode) or isolates AI-assistant referral sessions in GA4/GSC/logs and reports their trend, landing pages, and AI-vs-organic conversion (ai-referrals mode). Not for internal links — use site-structure-optimizer; not for keyword positions — use rank-tracker; not for multi-metric stakeholder reports — use performance-monitor. 外链分析/反向链接/AI流量/AI引荐/ChatGPT流量/AI转化
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.4 KB |
| references/backlinks-analysis-templates.md | markdown | 3.9 KB |
| references/link-quality-rubric.md | markdown | 7.5 KB |
| references/outreach-templates.md | markdown | 4.3 KB |
| skill-report.json | config | 49.9 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T13:10:57.582Z",
"slug": "aaron-he-zhu-offsite-signal-analyzer",
"source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/seo-geo/monitor/offsite-signal-analyzer",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "397763daaaf5c71f67871550ef2805517b58fac134bc307f2b32df1cac9d5356",
"tree_hash": "efe80472829eb1f2b8c81b802069bfd9f4b8116e287f000db184943fae947dae",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "offsite-signal-analyzer",
"description": "Analyzes backlink profiles or AI-assistant referral traffic from user-provided exports and supported data sources. It reports quality, trends, landing pages, conversions, and prioritized actions.",
"summary": "Analyze backlink quality and AI referral performance with source-labeled evidence.",
"icon": "📦",
"version": "16.0.2",
"author": "aaron-he-zhu",
"license": "Apache-2.0",
"category": "data",
"tags": [
"backlink-analysis",
"ai-referrals",
"seo",
"web-analytics",
"link-quality"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"network",
"external_commands",
"filesystem"
]
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Three command examples are confirmed medium-risk because they interpolate placeholders and invoke external Python scripts. The other 45 findings are documentation syntax, safe example domains, public links, or relative documentation references.",
"remediation": [
{
"issue": "Shell command examples interpolate user-controlled brands, queries, and domains.",
"suggestion": "Use structured process arguments, validate each value, and avoid constructing shell command strings or pipelines.",
"severity": "medium"
},
{
"issue": "The command examples invoke connector scripts outside this scanned skill package.",
"suggestion": "Bundle auditable scripts with the skill or document their verified source, permissions, network behavior, and expected outputs.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "network",
"evidence": [
{
"file": "references/link-quality-rubric.md",
"line_start": 103,
"line_end": 103
},
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 10
},
{
"file": "SKILL.md",
"line_start": 14,
"line_end": 14
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 75
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 28,
"line_end": 28
},
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 39
},
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 39
},
{
"file": "SKILL.md",
"line_start": 43,
"line_end": 43
},
{
"file": "SKILL.md",
"line_start": 46,
"line_end": 47
},
{
"file": "SKILL.md",
"line_start": 47,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 51,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 65
},
{
"file": "SKILL.md",
"line_start": 65,
"line_end": 67
},
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 67
},
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 69
},
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 71
},
{
"file": "SKILL.md",
"line_start": 73,
"line_end": 73
},
{
"file": "SKILL.md",
"line_start": 79,
"line_end": 81
},
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 88,
"line_end": 88
},
{
"file": "SKILL.md",
"line_start": 89,
"line_end": 129
},
{
"file": "SKILL.md",
"line_start": 129,
"line_end": 129
},
{
"file": "SKILL.md",
"line_start": 136,
"line_end": 140
},
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 140
},
{
"file": "SKILL.md",
"line_start": 151,
"line_end": 152
},
{
"file": "SKILL.md",
"line_start": 152,
"line_end": 154
}
]
},
{
"factor": "filesystem",
"evidence": [
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 57,
"line_end": 57
},
{
"file": "SKILL.md",
"line_start": 61,
"line_end": 61
},
{
"file": "SKILL.md",
"line_start": 65,
"line_end": 65
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 113,
"line_end": 113
},
{
"file": "SKILL.md",
"line_start": 134,
"line_end": 134
},
{
"file": "SKILL.md",
"line_start": 140,
"line_end": 140
},
{
"file": "SKILL.md",
"line_start": 147,
"line_end": 147
},
{
"file": "SKILL.md",
"line_start": 151,
"line_end": 151
},
{
"file": "SKILL.md",
"line_start": 152,
"line_end": 152
},
{
"file": "SKILL.md",
"line_start": 154,
"line_end": 154
}
]
}
],
"static_findings": [
{
"id": "network:references/link-quality-rubric.md:103:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "references/link-quality-rubric.md",
"line_start": 103,
"line_end": 103,
"snippet": "https://spam-site.example/toxic-page"
},
{
"id": "blocker:references/link-quality-rubric.md:74:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/link-quality-rubric.md",
"line_start": 74,
"line_end": 74,
"snippet": "| Paid links you cannot get removed | Yes | Only after attempting removal |"
},
{
"id": "blocker:references/link-quality-rubric.md:100:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/link-quality-rubric.md",
"line_start": 100,
"line_end": 100,
"snippet": "# Reason: [toxic link cleanup / negative SEO / paid links not removable]"
},
{
"id": "blocker:references/outreach-templates.md:7:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/outreach-templates.md",
"line_start": 7,
"line_end": 7,
"snippet": "| Rule | Do | Avoid |"
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 25,
"line_end": 25,
"snippet": "| `backlinks` (default) | backlink-analyzer | `~~link database` export / pasted CSV | Referring doma"
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 26,
"line_end": 26,
"snippet": "| `ai-referrals` | ai-traffic | GA4 / GSC / server-log export | AI-assistant referral sessions, tren"
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 28,
"line_end": 28,
"snippet": "**The seam**: backlinks answers \"is this domain worth trusting as a source?\" from the link graph; ai"
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 32,
"line_end": 37,
"snippet": "```text"
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 37,
"line_end": 39,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 39,
"line_end": 39,
"snippet": "If no mode is given, infer it: link/anchor/toxic/referring-domain wording → `backlinks`; AI-assistan"
},
{
"id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 43,
"line_end": 43,
"snippet": "**Expected output**: for `backlinks`, a backlink report (profile overview, quality/anchors/toxicity,"
},
{
"id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 46,
"line_end": 47,
"snippet": "- `backlinks` — target domain, backlink/referring-domain exports, competitor domains, anchor data, a"
},
{
"id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 47,
"line_end": 48,
"snippet": "- `ai-referrals` — domain, date range, the user's GA4 export / Search Console data and/or server acc"
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 48,
"line_end": 49,
"snippet": "- **Writes**: a user-facing monitoring deliverable and a reusable handoff summary under `memory/moni"
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 49,
"line_end": 49,
"snippet": "- **Promotes**: significant changes, confirmed anomalies, new AI sources appearing, and follow-up ac"
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 51,
"line_end": 52,
"snippet": "- `backlinks` — referring domains, anchor mix, and toxic-link share are reported with each metric so"
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 65,
"snippet": "- `ai-referrals` — the AI source list is explicit, every figure is source-tagged, AI sessions and co"
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 65,
"line_end": 67,
"snippet": "All integrations optional and keyless on your own data (see [CONNECTORS.md](../../../CONNECTORS.md))"
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 67,
"line_end": 67,
"snippet": "**backlinks mode** — pull backlink profiles from `~~link database` and competitor data from `~~SEO t"
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 69,
"line_end": 69,
"snippet": "**Keyless unlinked-mention read (backlinks mode)**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connecto"
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 71,
"line_end": 71,
"snippet": "**ai-referrals mode** — pull referral source/medium and conversions from `~~web analytics` (GA4 own "
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 73,
"line_end": 73,
"snippet": "**Keyless upstream AI-citation spot-check (ai-referrals mode)**: referral logs only show clicks *aft"
},
{
"id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 79,
"line_end": 81,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 81,
"line_end": 83,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 83,
"line_end": 83,
"snippet": "**Zero-dependency measurement loop (ai-referrals)**: store each period's AI-channel KPIs and let the"
},
{
"id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 88,
"line_end": 88,
"snippet": "- `backlinks` — no backlink data is provided and no `~~link database` is connected; link counts cann"
},
{
"id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 89,
"line_end": 129,
"snippet": "- `ai-referrals` — no GA4/GSC/log export is provided and no analytics tool is connected; AI sessions"
},
{
"id": "external_commands:SKILL.md:129:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 129,
"line_end": 129,
"snippet": "3. **Pull AI-referral sessions** — in GA4 use an Exploration on `Session source / medium` filtered b"
},
{
"id": "external_commands:SKILL.md:136:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 136,
"line_end": 140,
"snippet": "**CITE item mapping** (ai-referrals): these figures are an **engagement signal that informs (does no"
},
{
"id": "external_commands:SKILL.md:140:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 140,
"line_end": 140,
"snippet": "Ask \"Save these results for future sessions?\" If yes, write to `memory/monitoring/` using filename `"
},
{
"id": "external_commands:SKILL.md:151:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 151,
"line_end": 152,
"snippet": "- `backlinks`, toxic ratio > 15% or authority concern → [domain-authority-auditor](../domain-authori"
},
{
"id": "external_commands:SKILL.md:152:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 152,
"line_end": 154,
"snippet": "- `ai-referrals` → roll the AI channel into a full stakeholder report with [performance-monitor](../"
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 10,
"line_end": 10,
"snippet": "homepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\""
},
{
"id": "network:SKILL.md:14:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 14,
"line_end": 14,
"snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"seo-geo\", \"phase\": \"monitor"
},
{
"id": "network:SKILL.md:75:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 75,
"line_end": 75,
"snippet": "**Industry baseline for AI-crawler traffic (keyless)**: [Cloudflare Radar AI Insights](https://radar"
},
{
"id": "filesystem:SKILL.md:19:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 19,
"line_end": 19,
"snippet": "Reports the two off-site signal families a domain earns from the outside world: the **backlink profi"
},
{
"id": "filesystem:SKILL.md:53:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 53,
"line_end": 53,
"snippet": "- **Primary next skill**: [domain-authority-auditor](../domain-authority-auditor/SKILL.md) when toxi"
},
{
"id": "filesystem:SKILL.md:57:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 57,
"line_end": 57,
"snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
},
{
"id": "filesystem:SKILL.md:61:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 61,
"line_end": 61,
"snippet": "This skill does **not**: score CITE or run vetoes (that is the [domain-authority-auditor](../domain-"
},
{
"id": "filesystem:SKILL.md:65:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 65,
"line_end": 65,
"snippet": "All integrations optional and keyless on your own data (see [CONNECTORS.md](../../../CONNECTORS.md))"
},
{
"id": "filesystem:SKILL.md:83:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 83,
"line_end": 83,
"snippet": "**Zero-dependency measurement loop (ai-referrals)**: store each period's AI-channel KPIs and let the"
},
{
"id": "filesystem:SKILL.md:113:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 113,
"line_end": 113,
"snippet": "**CITE item mapping** (what feeds [domain-authority-auditor](../domain-authority-auditor/SKILL.md) i"
},
{
"id": "filesystem:SKILL.md:134:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 134,
"line_end": 134,
"snippet": "8. **Read movement against a control** — before crediting any change to an AI-traffic shift, apply ["
},
{
"id": "filesystem:SKILL.md:140:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 140,
"line_end": 140,
"snippet": "Ask \"Save these results for future sessions?\" If yes, write to `memory/monitoring/` using filename `"
},
{
"id": "filesystem:SKILL.md:147:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 147,
"line_end": 147,
"snippet": "- [Measurement & Attribution Protocol](../../../references/measurement-protocol.md) — readback windo"
},
{
"id": "filesystem:SKILL.md:151:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 151,
"line_end": 151,
"snippet": "- `backlinks`, toxic ratio > 15% or authority concern → [domain-authority-auditor](../domain-authori"
},
{
"id": "filesystem:SKILL.md:152:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 152,
"line_end": 152,
"snippet": "- `ai-referrals` → roll the AI channel into a full stakeholder report with [performance-monitor](../"
},
{
"id": "filesystem:SKILL.md:154:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 154,
"line_end": 154,
"snippet": "Termination: visited-set check (if the target already ran in this chain, STOP and report chain-compl"
}
],
"finding_verdicts": [
{
"id": "network:references/link-quality-rubric.md:103:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL uses the reserved .example domain inside a disavow-file format example. It cannot direct traffic to an operational external service."
},
{
"id": "blocker:references/link-quality-rubric.md:74:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This table row advises when paid links may warrant disavowal. It does not inspect the host system or request privileged information."
},
{
"id": "blocker:references/link-quality-rubric.md:100:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a comment template explaining why links were added to a disavow file. It contains no reconnaissance command or system access."
},
{
"id": "blocker:references/outreach-templates.md:7:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The words form a Markdown table header for outreach guidance. They do not instruct system discovery or collect environment details."
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format mode and connector labels in a Markdown table. No shell or Ruby expression is executed."
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the ai-referrals mode name in documentation. The line contains no executable command."
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticked text names another skill for a documented handoff. It is not command substitution or executable code."
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line opens a fenced text block containing example user prompts. A Markdown fence does not execute its contents."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line closes a fenced text block. It has no command execution behavior."
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks identify two analysis modes in prose. The line only describes mode selection."
},
{
"id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format mode and output-path names in the skill contract. No external process is invoked."
},
{
"id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line documents inputs for backlinks mode. Its backticks are Markdown formatting only."
},
{
"id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line documents user-provided analytics inputs. It contains no command or execution primitive."
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticked value is a relative output directory. The line describes a write contract, not external command execution."
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format memory filenames and a status value. No shell syntax or process invocation is present."
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line states completion criteria for backlinks mode. Backticks only format the mode label."
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line states completion criteria for AI referral analysis. It does not invoke an external program."
},
{
"id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The only backticked text is robots.txt within data-source guidance. The relative Markdown links are not commands."
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticked phrases are abstract connector labels. They are not shell commands or Ruby expressions."
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.9,
"reason": "The line explicitly directs execution of Python connector and ledger commands. Brand and domain placeholders may become user-controlled shell values without defined validation.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks denote optional analytics connector labels. The line requests exports when tools are unavailable and contains no command."
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.9,
"reason": "The line directs execution of Tavily and ledger Python commands using query and domain placeholders. Unsafe interpolation could permit command injection.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line opens a fenced block for a regular expression. It does not execute a shell command."
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This line closes the regular-expression code fence. It has no execution semantics."
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.93,
"reason": "The line instructs execution of ledger.py with domain and data placeholders. An unquoted domain in a shell command creates a plausible injection path.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:88:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line uses backticks to name a mode and an abstract connector. It defines a stop condition and executes nothing."
},
{
"id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the ai-referrals mode name. The surrounding text requires user data or cancellation and contains no executable instruction."
},
{
"id": "external_commands:SKILL.md:129:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format GA4 field and HTTP header names. The line describes filtering exported analytics or logs."
},
{
"id": "external_commands:SKILL.md:136:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticked name identifies a downstream skill. The line describes evidence boundaries and contains no command."
},
{
"id": "external_commands:SKILL.md:140:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Backticks format a relative directory, filename template, and skill name. The write occurs only after explicit user consent and is not external command execution."
},
{
"id": "external_commands:SKILL.md:151:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticked terms are a mode and downstream skill name. The line documents a recommendation rather than invoking a process."
},
{
"id": "external_commands:SKILL.md:152:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticked term names the ai-referrals mode. The Markdown link is a documented handoff, not executable code."
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This URL is repository homepage metadata. It does not instruct a request or transmit user data."
},
{
"id": "network:SKILL.md:14:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL repeats the public repository homepage in metadata. It is attribution, not an operational endpoint."
},
{
"id": "network:SKILL.md:75:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL points to a public Cloudflare Radar benchmark and the text limits its use to industry context. No user data is sent."
},
{
"id": "filesystem:SKILL.md:19:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The traversal sequence is a relative Markdown link to shared CITE documentation. It does not read or write files."
},
{
"id": "filesystem:SKILL.md:53:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The relative paths are Markdown links to neighboring skill documentation. They are not constructed from user input."
},
{
"id": "filesystem:SKILL.md:57:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The sequence navigates to a shared skill-contract document through a static Markdown link. No filesystem operation is directed."
},
{
"id": "filesystem:SKILL.md:61:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "These are static relative links documenting scope and handoffs. No user-controlled path reaches a filesystem API."
},
{
"id": "filesystem:SKILL.md:65:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The sequences are static Markdown links to connector and security policies. They do not perform path traversal."
},
{
"id": "filesystem:SKILL.md:83:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The detected sequence appears in a static link to the connector README. The command risk on this line is adjudicated separately."
},
{
"id": "filesystem:SKILL.md:113:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a static relative Markdown link to a neighboring skill. It does not access a user-selected path."
},
{
"id": "filesystem:SKILL.md:134:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The relative sequence links to the shared measurement protocol. It is documentation navigation, not a filesystem read."
},
{
"id": "filesystem:SKILL.md:140:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The traversal sequence belongs to a static skill-contract link. The documented memory write uses a fixed local directory and asks for consent."
},
{
"id": "filesystem:SKILL.md:147:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The sequence is a static Markdown reference to the measurement protocol. It cannot escape a runtime path because no file API is used."
},
{
"id": "filesystem:SKILL.md:151:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The path is a static link to neighboring skill documentation. It is not combined with user-controlled data."
},
{
"id": "filesystem:SKILL.md:152:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The path is a static Markdown link used for a recommended handoff. It does not direct file access."
},
{
"id": "filesystem:SKILL.md:154:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The relative path points to a fixed skill-contract document. The line describes workflow termination and contains no filesystem operation."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "**Keyless unlinked-mention read (backlinks mode)**: `python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/connecto",
"locations": [
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 69
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.9,
"confidence_reasoning": "The line explicitly directs execution of Python connector and ledger commands. Brand and domain placeholders may become user-controlled shell values without defined validation."
},
{
"title": "Ruby/shell backtick execution",
"description": "**Keyless upstream AI-citation spot-check (ai-referrals mode)**: referral logs only show clicks *aft",
"locations": [
{
"file": "SKILL.md",
"line_start": 73,
"line_end": 73
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.9,
"confidence_reasoning": "The line directs execution of Tavily and ledger Python commands using query and domain placeholders. Unsafe interpolation could permit command injection."
},
{
"title": "Ruby/shell backtick execution",
"description": "**Zero-dependency measurement loop (ai-referrals)**: store each period's AI-channel KPIs and let the",
"locations": [
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 83
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.93,
"confidence_reasoning": "The line instructs execution of ledger.py with domain and data placeholders. An unquoted domain in a shell command creates a plausible injection path."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 4,
"total_lines": 525,
"audit_model": "codex",
"audited_at": "2026-07-12T13:10:57.582Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Analyze Backlinks and AI Referral Traffic",
"value_statement": "Backlink exports and AI referral data are difficult to compare consistently. This skill produces source-labeled profiles, trends, landing-page insights, and prioritized actions.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"backlink analysis",
"AI referral traffic",
"ChatGPT referrals",
"link quality audit",
"GA4 AI traffic",
"toxic link review",
"SEO analytics"
],
"actual_capabilities": [
"Profiles referring domains, authority distribution, anchor text, follow status, and link velocity from supplied backlink data.",
"Scores link quality and identifies toxic-link or disavow candidates with documented safeguards.",
"Compares competitor backlink profiles and prioritizes link-building opportunities.",
"Defines an AI referral channel from GA4 exports or server logs using an adaptable source regex.",
"Compares AI referral trends, landing pages, engagement, and conversions against organic traffic."
],
"limitations": [
"It cannot measure backlink counts without a backlink export or connected link database.",
"It cannot measure AI sessions without GA4, Search Console, analytics, or server-log data.",
"Referral traffic indicates an AI link, but it does not prove citation prominence.",
"Disavow recommendations require manual review before submission to Google Search Console."
],
"use_cases": [
{
"title": "Audit a backlink profile",
"description": "Review referring domains, anchor distribution, toxic-link share, and prioritized cleanup actions from an exported backlink dataset.",
"target_user": "SEO specialists"
},
{
"title": "Measure AI referral performance",
"description": "Isolate AI-assistant sessions and compare landing pages, engagement, and conversions with organic traffic.",
"target_user": "Web analytics teams"
},
{
"title": "Find competitive link opportunities",
"description": "Compare competitor referring domains and rank outreach prospects by relevance, authority, effort, and expected impact.",
"target_user": "Content marketing managers"
}
],
"prompt_templates": [
{
"title": "Summarize my backlink profile",
"prompt": "Use backlinks mode for [domain]. Analyze this backlink export and summarize referring domains, anchor mix, follow ratio, authority distribution, and major concerns.",
"scenario": "Beginner review of one backlink export"
},
{
"title": "Review toxic links",
"prompt": "Review this backlink export for [domain]. Score suspicious links, calculate the toxic share, separate weak links from harmful links, and recommend manual review steps.",
"scenario": "Focused risk and disavow assessment"
},
{
"title": "Analyze AI referral traffic",
"prompt": "Use ai-referrals mode for [domain] during [date range]. Apply the source regex to this GA4 export and compare AI sessions with organic traffic.",
"scenario": "Channel trend and conversion analysis"
},
{
"title": "Build a combined off-site monitoring brief",
"prompt": "Analyze these backlink, competitor, GA4, and server-log exports for [domain]. Keep backlink and AI-referral metrics separate, label every source, and identify prioritized actions.",
"scenario": "Advanced evidence-based monitoring across both modes"
}
],
"output_examples": [
{
"input": "Analyze the backlink export for example.com.",
"output": [
"Mode: backlinks. Referring-domain growth is positive, while exact-match anchors exceed the review threshold.",
"Twelve domains require manual inspection; three show repeated spam indicators.",
"Priority actions: review flagged domains, diversify anchors, and pursue competitor-overlap prospects."
]
},
{
"input": "Compare ChatGPT and Perplexity referrals with organic traffic for the last 90 days.",
"output": [
"Mode: ai-referrals. AI assistants generated 420 measured sessions during the selected period.",
"AI conversion rate was 1.3 times the organic rate, but the sample remains small.",
"The pricing and comparison pages received the highest AI referral volume."
]
},
{
"input": "Find competitor backlink opportunities for my product site.",
"output": "The report ranks shared linking domains by authority and relevance, then recommends resource-page, broken-link, and unlinked-mention outreach opportunities."
}
],
"best_practices": [
"Provide dated exports and a comparison window so every change has a clear baseline.",
"Label each metric as measured, user-provided, estimated, or unavailable.",
"Manually inspect suspicious domains before preparing or uploading a disavow file."
],
"anti_patterns": [
"Do not estimate backlink volume or AI sessions when source data is unavailable.",
"Do not combine backlink metrics and AI referral metrics into one score.",
"Do not treat referral traffic as proof of citation prominence in an AI answer."
],
"faq": [
{
"question": "What data does backlink mode require?",
"answer": "Provide a backlink or referring-domain export, anchor data, and optional competitor domains. Without this data, the skill cannot calculate link metrics."
},
{
"question": "What data does AI referrals mode require?",
"answer": "Provide a GA4 source and medium export, Search Console data, server logs, or a connected analytics source."
},
{
"question": "Which AI assistants can it identify?",
"answer": "The starter pattern includes ChatGPT, Perplexity, Copilot, Gemini, Claude, DeepSeek, Doubao, Qwen, Poe, and related domains."
},
{
"question": "Can it upload a disavow file?",
"answer": "No. It can prepare candidates and guidance, but a person should review and upload the final file."
},
{
"question": "Does AI referral traffic prove a citation?",
"answer": "No. It shows that an AI answer linked to the site, but it does not prove citation position or prominence."
},
{
"question": "Can it analyze both modes together?",
"answer": "It keeps both datasets separate. When a request includes both, select one mode first and run the other afterward."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "backlinks-analysis-templates.md",
"type": "file",
"path": "references/backlinks-analysis-templates.md",
"lines": 117
},
{
"name": "link-quality-rubric.md",
"type": "file",
"path": "references/link-quality-rubric.md",
"lines": 146
},
{
"name": "outreach-templates.md",
"type": "file",
"path": "references/outreach-templates.md",
"lines": 107
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 155
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |