aiskillstore/marketplace / skills/aaron-he-zhu/content-quality-auditor
content-quality-auditor
VerifiedUse when auditing content quality, E-E-A-T, or publish readiness; runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan. Not for structural tags/headers alone — use on-page-seo-auditor; not for domain/citation trust — use domain-authority-auditor. 内容质量/EEAT评分
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.5 KB |
| references/auditor-runtime.md | markdown | 10.6 KB |
| references/item-reference.md | markdown | 5.3 KB |
| references/recursive-refinement.md | markdown | 3.5 KB |
| skill-report.json | config | 48.6 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T11:35:11.030Z",
"slug": "aaron-he-zhu-content-quality-auditor",
"source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/seo-geo/optimize/content-quality-auditor",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "e5a4c2346e4707b545143f6198d71f2131f2138c7cf058f7ae1fc29f4a2e3310",
"tree_hash": "6c808d24bd79c13100ffc43f2a2e01efe4a0c25f49885b4401c46fb2b5b2b7ef",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "content-quality-auditor",
"description": "Audits one content artifact with an 80-item CORE-EEAT framework, evidence coverage, qualified veto checks, and a prioritized publish-readiness fix plan.",
"summary": "Assess content evidence and publish readiness with a reproducible CORE-EEAT audit.",
"icon": "📦",
"version": "13.0.3",
"author": "aaron-he-zhu",
"license": "Apache-2.0",
"tags": [
"content-audit",
"eeat",
"seo",
"publish-readiness",
"quality-assurance"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"filesystem",
"external_commands",
"network"
],
"category": "writing"
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All 51 static detections are contextual false positives from Markdown formatting, fixed documentation links, repository metadata, and scoped local tooling. No prompt injection, arbitrary path access, user-controlled command construction, network exfiltration, or other malicious intent was found.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "filesystem",
"evidence": [
{
"file": "references/item-reference.md",
"line_start": 3,
"line_end": 3
},
{
"file": "references/recursive-refinement.md",
"line_start": 14,
"line_end": 14
},
{
"file": "references/recursive-refinement.md",
"line_start": 45,
"line_end": 45
},
{
"file": "SKILL.md",
"line_start": 47,
"line_end": 47
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 49,
"line_end": 49
},
{
"file": "SKILL.md",
"line_start": 50,
"line_end": 50
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 160,
"line_end": 160
},
{
"file": "SKILL.md",
"line_start": 161,
"line_end": 161
},
{
"file": "SKILL.md",
"line_start": 162,
"line_end": 162
},
{
"file": "SKILL.md",
"line_start": 165,
"line_end": 165
},
{
"file": "SKILL.md",
"line_start": 169,
"line_end": 169
},
{
"file": "SKILL.md",
"line_start": 170,
"line_end": 170
},
{
"file": "SKILL.md",
"line_start": 171,
"line_end": 171
},
{
"file": "SKILL.md",
"line_start": 172,
"line_end": 172
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 33
},
{
"file": "SKILL.md",
"line_start": 33,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 37
},
{
"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": 50
},
{
"file": "SKILL.md",
"line_start": 50,
"line_end": 50
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 59
},
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 81
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 84
},
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 85,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 98,
"line_end": 104
},
{
"file": "SKILL.md",
"line_start": 104,
"line_end": 114
},
{
"file": "SKILL.md",
"line_start": 114,
"line_end": 114
},
{
"file": "SKILL.md",
"line_start": 115,
"line_end": 115
},
{
"file": "SKILL.md",
"line_start": 116,
"line_end": 116
},
{
"file": "SKILL.md",
"line_start": 117,
"line_end": 117
},
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 123,
"line_end": 123
},
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 126
},
{
"file": "SKILL.md",
"line_start": 126,
"line_end": 137
},
{
"file": "SKILL.md",
"line_start": 137,
"line_end": 137
},
{
"file": "SKILL.md",
"line_start": 141,
"line_end": 143
},
{
"file": "SKILL.md",
"line_start": 143,
"line_end": 145
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
},
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 52
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 10
},
{
"file": "SKILL.md",
"line_start": 15,
"line_end": 15
}
]
}
],
"static_findings": [
{
"id": "blocker:references/auditor-runtime.md:138:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/auditor-runtime.md",
"line_start": 138,
"line_end": 138,
"snippet": "\"condition\": \"a material connection, paid placement, or affiliate relationship exists\","
},
{
"id": "filesystem:references/item-reference.md:3:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/item-reference.md",
"line_start": 3,
"line_end": 3,
"snippet": "Quick reference for all 80 CORE-EEAT audit items. Full scoring criteria in [core-eeat-benchmark.md]("
},
{
"id": "filesystem:references/recursive-refinement.md:14:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/recursive-refinement.md",
"line_start": 14,
"line_end": 14,
"snippet": "[auditor-runbook.md §4](../../../../references/auditor-runbook.md) for cap and"
},
{
"id": "filesystem:references/recursive-refinement.md:45:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/recursive-refinement.md",
"line_start": 45,
"line_end": 45,
"snippet": "[core-eeat-benchmark.md](../../../../references/core-eeat-benchmark.md)."
},
{
"id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 30,
"line_end": 33,
"snippet": "```text"
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 33,
"line_end": 37,
"snippet": "```"
},
{
"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": 37,
"snippet": "Use this skill for the content artifact and its source-credibility evidence. Use `on-page-seo-audito"
},
{
"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": "1. `../../../references/auditor-runbook.md`"
},
{
"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": "2. `../../../references/scoring-semantics.md`"
},
{
"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": 50,
"snippet": "3. `../../../references/core-eeat-benchmark.md`"
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 50,
"line_end": 50,
"snippet": "4. `../../../references/framework-catalog.json` (`CORE-EEAT` entry)"
},
{
"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": 52,
"snippet": "For a standalone installation, read the bundled immutable `references/auditor-runtime.md` instead. N"
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 59,
"line_end": 59,
"snippet": "- **Profile/content type**: `product-review`, `how-to-guide`, `comparison`, `landing-page`, `blog-po"
},
{
"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": 81,
"snippet": "4. Use `unknown` for applicable but unobserved evidence. Use `na` only for catalog-declared conditio"
},
{
"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": 84,
"snippet": "- `CORE-EEAT-C01`: material title/promise mismatch."
},
{
"id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 84,
"line_end": 85,
"snippet": "- `CORE-EEAT-R10`: material internal factual contradiction; an isolated broken link is not this veto"
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 85,
"line_end": 86,
"snippet": "- `CORE-EEAT-T04`: a material connection exists and required disclosure is absent/materially obscure"
},
{
"id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 86,
"line_end": 86,
"snippet": "6. Create a JSON run conforming to `audit-run.schema.json` and execute `python3 \"$AARON_SKILLS_ROOT/"
},
{
"id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 98,
"line_end": 104,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:104:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 104,
"line_end": 114,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:114:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 114,
"line_end": 114,
"snippet": "- Complete, no veto, healthy score/no failures: `DONE` + `SHIP`."
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 115,
"line_end": 115,
"snippet": "- Complete, remediation needed or one veto: `DONE_WITH_CONCERNS` + `FIX`; one veto caps final at 59."
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 116,
"line_end": 116,
"snippet": "- Complete, 2+ vetoes: `DONE` + `BLOCK`; omit final score."
},
{
"id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 117,
"line_end": 117,
"snippet": "- Applicable evidence missing: `NEEDS_INPUT` + `UNDECIDED`; omit raw/final scores."
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 119,
"line_end": 119,
"snippet": "Route claim/disclosure fixes to `offer-claims-registry`, content fixes to `content-writer` or `geo-c"
},
{
"id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 123,
"line_end": 123,
"snippet": "- Product-review profile, complete evidence, raw 78, one verified T04 failure: `DONE_WITH_CONCERNS/F"
},
{
"id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 125,
"line_end": 126,
"snippet": "- Complete evidence, verified C01 and R10 failures: `DONE/BLOCK`, raw retained, no final score."
},
{
"id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 126,
"line_end": 137,
"snippet": "- Any applicable Unknown item: `NEEDS_INPUT/UNDECIDED`, no raw or final score, regardless of the obs"
},
{
"id": "external_commands:SKILL.md:137:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 137,
"line_end": 137,
"snippet": "Default to plain-language findings. When traceability is requested, qualify IDs as `CORE-EEAT-C01`, "
},
{
"id": "external_commands:SKILL.md:141:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 141,
"line_end": 143,
"snippet": "Do not write memory merely because an audit was requested. If the user explicitly authorizes persist"
},
{
"id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 143,
"line_end": 145,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:52:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 52,
"snippet": "For a standalone installation, read the bundled immutable `references/auditor-runtime.md` instead. N"
},
{
"id": "external_commands:SKILL.md:52:template-literal-with-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Template literal with command substitution",
"file": "SKILL.md",
"line_start": 52,
"line_end": 52,
"snippet": "For a standalone installation, read the bundled immutable `references/auditor-runtime.md` instead. N"
},
{
"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:15:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 15,
"line_end": 15,
"snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"seo-geo\", \"phase\": \"optimiz"
},
{
"id": "filesystem:SKILL.md:47:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 47,
"line_end": 47,
"snippet": "1. `../../../references/auditor-runbook.md`"
},
{
"id": "filesystem:SKILL.md:48:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 48,
"line_end": 48,
"snippet": "2. `../../../references/scoring-semantics.md`"
},
{
"id": "filesystem:SKILL.md:49:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 49,
"line_end": 49,
"snippet": "3. `../../../references/core-eeat-benchmark.md`"
},
{
"id": "filesystem:SKILL.md:50:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 50,
"line_end": 50,
"snippet": "4. `../../../references/framework-catalog.json` (`CORE-EEAT` entry)"
},
{
"id": "filesystem:SKILL.md:52:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 52,
"line_end": 52,
"snippet": "For a standalone installation, read the bundled immutable `references/auditor-runtime.md` instead. N"
},
{
"id": "filesystem:SKILL.md:160:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 160,
"line_end": 160,
"snippet": "- [CORE-EEAT benchmark](../../../references/core-eeat-benchmark.md)"
},
{
"id": "filesystem:SKILL.md:161:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 161,
"line_end": 161,
"snippet": "- [Auditor runbook](../../../references/auditor-runbook.md)"
},
{
"id": "filesystem:SKILL.md:162:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 162,
"line_end": 162,
"snippet": "- [Scoring semantics](../../../references/scoring-semantics.md)"
},
{
"id": "filesystem:SKILL.md:165:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 165,
"line_end": 165,
"snippet": "- [Humanizer controls](../../../references/humanizer-slop.md)"
},
{
"id": "filesystem:SKILL.md:169:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 169,
"line_end": 169,
"snippet": "- **FIX content:** [content-writer](../../build/content-writer/SKILL.md)"
},
{
"id": "filesystem:SKILL.md:170:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 170,
"line_end": 170,
"snippet": "- **FIX technical evidence:** [technical-seo-checker](../../optimize/technical-seo-checker/SKILL.md)"
},
{
"id": "filesystem:SKILL.md:171:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 171,
"line_end": 171,
"snippet": "- **Resolve claims:** [offer-claims-registry](../../../protocol/offer-claims-registry/SKILL.md)"
},
{
"id": "filesystem:SKILL.md:172:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 172,
"line_end": 172,
"snippet": "- **Add domain context:** [domain-authority-auditor](../../monitor/domain-authority-auditor/SKILL.md"
},
{
"id": "filesystem:SKILL.md:52:standard-device-file-access",
"category": "filesystem",
"severity": "low",
"pattern": "Standard device file access",
"file": "SKILL.md",
"line_start": 52,
"line_end": 52,
"snippet": "For a standalone installation, read the bundled immutable `references/auditor-runtime.md` instead. N"
},
{
"id": "blocker:SKILL.md:39:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 39,
"line_end": 39,
"snippet": "**Reads:** one artifact plus its cited/source controls. **Writes:** only a permissioned v3 artifact."
},
{
"id": "blocker:SKILL.md:152:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 152,
"line_end": 152,
"snippet": "- All expected IDs observed, Unknown, or valid N/A; no missingness renormalization."
}
],
"finding_verdicts": [
{
"id": "blocker:references/auditor-runtime.md:138:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This JSON condition defines when affiliate disclosure applies. It does not inspect system state, accounts, processes, or privileges."
},
{
"id": "filesystem:references/item-reference.md:3:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The sequence appears in a fixed Markdown link to the documented CORE-EEAT benchmark. It does not accept user input or perform a filesystem operation."
},
{
"id": "filesystem:references/recursive-refinement.md:14:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown link to the auditor runbook for veto handling. It is documentation navigation, not arbitrary path access."
},
{
"id": "filesystem:references/recursive-refinement.md:45:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown link to the benchmark used for dimension weights. No user-controlled path is read or written."
},
{
"id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks start a fenced text example containing sample audit requests. They do not invoke Ruby or a shell."
},
{
"id": "external_commands:SKILL.md:33:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks close a fenced text example. No executable expression or command is present."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format related skill names in prose. They are Markdown markup, not shell execution."
},
{
"id": "external_commands:SKILL.md:47:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format a fixed repository documentation path. No command syntax or dynamic input is present."
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format a fixed scoring-semantics path. They do not execute the path."
},
{
"id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format a fixed benchmark path. The line contains no shell or Ruby invocation."
},
{
"id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks identify a fixed catalog path and entry name. This is documentation, not command execution."
},
{
"id": "external_commands:SKILL.md:52:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Most backticks on this line are Markdown formatting. The command substitution runs a fixed git repository-root query without user input or data transmission."
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format a closed list of supported content-type values. No executable statement is present."
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the literal audit states unknown and na. They are data vocabulary, not executable code."
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the CORE-EEAT-C01 item identifier. The line describes a veto condition and executes nothing."
},
{
"id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the CORE-EEAT-R10 item identifier. This is an audit rule, not an external command."
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format the CORE-EEAT-T04 item identifier. The line only explains a disclosure condition."
},
{
"id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The line documents a local deterministic scorer invocation with a quoted fixed root and an explicit input file. It contains no Ruby backticks, untrusted interpolation, or network action."
},
{
"id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks start a fenced Markdown output example. They do not execute a command."
},
{
"id": "external_commands:SKILL.md:104:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks close a fenced Markdown output example. No executable expression is present."
},
{
"id": "external_commands:SKILL.md:114:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format typed status and verdict labels. They are output vocabulary, not shell syntax."
},
{
"id": "external_commands:SKILL.md:115:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format typed status and verdict labels. The line contains no external command."
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format typed status and verdict labels for multiple vetoes. Nothing is executed."
},
{
"id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Inline backticks format typed missing-evidence status labels. They are not command substitutions."
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format names of related skills used for handoff. The prose does not invoke those skills or a shell."
},
{
"id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format worked-example status values and a field name. They are illustrative audit output."
},
{
"id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format worked-example verdict values. No command or dynamic code is present."
},
{
"id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format worked-example status values. This is documentation of scoring behavior."
},
{
"id": "external_commands:SKILL.md:137:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format qualified CORE-EEAT item identifiers. They cannot execute code."
},
{
"id": "external_commands:SKILL.md:141:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks format a constrained relative artifact path. The line requires explicit permission and validation before any write."
},
{
"id": "external_commands:SKILL.md:143:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks open a fenced Bash example. The fence itself is Markdown and performs no execution."
},
{
"id": "external_commands:SKILL.md:52:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The substitution runs a fixed git rev-parse query only to locate the repository root, suppressing errors and using no user input. It does not expose or transmit repository data."
},
{
"id": "external_commands:SKILL.md:52:template-literal-with-command-substitution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a quoted shell variable assignment in documentation, not a JavaScript template literal. Its fixed git fallback has no user-controlled command fragment."
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The URL is repository homepage metadata. The skill does not instruct a request to this address or send data to it."
},
{
"id": "network:SKILL.md:15:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The URL is repeated inside package metadata as the project homepage. It is not a network endpoint used by the audit workflow."
},
{
"id": "filesystem:SKILL.md:47:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed path identifies the repository auditor runbook required by the skill. It is not derived from user input and does not enable arbitrary traversal."
},
{
"id": "filesystem:SKILL.md:48:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed path identifies the repository scoring semantics document. No dynamic path construction or write occurs."
},
{
"id": "filesystem:SKILL.md:49:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed path identifies the repository CORE-EEAT benchmark. It is a scoped documentation dependency, not arbitrary filesystem access."
},
{
"id": "filesystem:SKILL.md:50:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed path identifies the repository framework catalog and a named entry. It contains no user-controlled traversal component."
},
{
"id": "filesystem:SKILL.md:52:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The parent-relative segment is inside a fixed Markdown link to runtime instructions. The standalone fallback uses a bundled file and forbids searching parent directories."
},
{
"id": "filesystem:SKILL.md:160:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown reference link to the CORE-EEAT benchmark. It does not read an arbitrary user-selected path."
},
{
"id": "filesystem:SKILL.md:161:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown reference link to the auditor runbook. The path is documentation navigation only."
},
{
"id": "filesystem:SKILL.md:162:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown reference link to scoring semantics. It has no dynamic or writable component."
},
{
"id": "filesystem:SKILL.md:165:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This is a fixed Markdown reference link to supporting humanizer controls. It does not perform path traversal at runtime."
},
{
"id": "filesystem:SKILL.md:169:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed relative link points to a related content-writing skill for remediation handoff. It is not an instruction to access arbitrary files."
},
{
"id": "filesystem:SKILL.md:170:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed relative link points to a related technical SEO skill. No path input is accepted and no filesystem mutation occurs."
},
{
"id": "filesystem:SKILL.md:171:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed relative link points to the claims registry skill. It is a documentation link, not user-controlled traversal."
},
{
"id": "filesystem:SKILL.md:172:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This fixed relative link points to the domain authority auditor. It does not expose arbitrary filesystem access."
},
{
"id": "filesystem:SKILL.md:52:standard-device-file-access",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The only device path is /dev/null, used to suppress errors from a fixed git root query. It neither reads sensitive device data nor writes a persistent file."
},
{
"id": "blocker:SKILL.md:39:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This line documents the skill's read and permissioned-write scope plus completion criteria. It performs no host, account, process, or network discovery."
},
{
"id": "blocker:SKILL.md:152:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This validation checkpoint checks CORE-EEAT item identifiers and missingness handling. It does not inspect the host system."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 4,
"total_lines": 730,
"audit_model": "codex",
"audited_at": "2026-07-12T11:35:11.030Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Audit Content Quality and E-E-A-T Readiness",
"value_statement": "Content audits can miss weak evidence, disclosure gaps, and publish blockers. This skill applies an 80-item CORE-EEAT review with typed states and prioritized fixes.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"content quality audit",
"E-E-A-T audit",
"publish readiness",
"SEO content review",
"evidence coverage",
"content compliance"
],
"actual_capabilities": [
"Audits one declared content artifact against 80 stable CORE-EEAT items.",
"Applies profile-specific weights for nine supported content types.",
"Records pass, partial, fail, unknown, and not-applicable states with evidence.",
"Checks qualified vetoes for promise mismatch, factual contradiction, and missing material-connection disclosure.",
"Produces SHIP, FIX, BLOCK, or UNDECIDED guidance when the required runtime and evidence are available."
],
"limitations": [
"A comparable score requires complete evidence for every applicable item.",
"The audit does not predict search rankings, citations, traffic, or business outcomes.",
"Visual and mobile claims require rendered captures or user-provided exports.",
"Standalone installations without the root runtime cannot calculate scores, persist artifacts, or issue a gate verdict."
],
"use_cases": [
{
"title": "Review a Draft Before Publication",
"description": "Find evidence gaps, trust issues, and priority fixes before an article enters final approval.",
"target_user": "Content editors"
},
{
"title": "Compare Content Quality Consistently",
"description": "Apply one versioned framework across reviews, comparisons, guides, landing pages, and other supported profiles.",
"target_user": "SEO specialists"
},
{
"title": "Check Claims and Disclosures",
"description": "Identify material contradictions, promise mismatches, and missing relationship disclosures in higher-risk content.",
"target_user": "Compliance and marketing teams"
}
],
"prompt_templates": [
{
"title": "Basic Draft Audit",
"prompt": "Audit this blog post for the U.S. market before publication: [paste content]. Show the verdict, major findings, and priority fixes.",
"scenario": "Use for a first publish-readiness review."
},
{
"title": "Evidence Gap Review",
"prompt": "Audit this how-to guide with CORE-EEAT. List every unknown item, required evidence, and the fastest actions needed for a complete score.",
"scenario": "Use when source coverage may be incomplete."
},
{
"title": "Comparison Content Audit",
"prompt": "Audit this comparison for [market]. Verify claim support, author expertise, methodology, disclosures, contradictions, and profile-specific evidence: [content and sources].",
"scenario": "Use for commercial comparison content."
},
{
"title": "Advanced Re-Audit",
"prompt": "Re-audit this revised product review against the prior findings. Preserve item traceability, explain score changes, verify vetoes, and identify remaining evidence gaps.",
"scenario": "Use after evidence-backed revisions."
}
],
"output_examples": [
{
"input": "A complete blog post with citations, author details, and publication context.",
"output": "Verdict: FIX. Strong research coverage, but the article needs clearer methodology, a corrections policy reference, and two claim-level citations."
},
{
"input": "A product review with affiliate links but no visible relationship disclosure.",
"output": "Verdict: FIX. A material connection exists without adequate disclosure, so the final score is capped until the disclosure is corrected."
},
{
"input": "A draft with missing source records and no rendered evidence.",
"output": "Verdict: UNDECIDED. The audit lists unknown items, the missing inputs, current coverage, and the available score interval without inventing a total."
}
],
"best_practices": [
"Provide one stable artifact, its content type, market, publication state, and observation date.",
"Include primary sources, author details, disclosures, policies, and rendered captures when relevant.",
"Use the same runtime and catalog version when comparing audits over time."
],
"anti_patterns": [
"Do not request a numeric score when applicable evidence is missing.",
"Do not treat the audit as a guarantee of rankings, citations, or conversions.",
"Do not select a content profile only because it produces a higher score."
],
"faq": [
{
"question": "What content types are supported?",
"answer": "The skill supports reviews, guides, comparisons, landing pages, blog posts, FAQs, alternatives, best-of pages, and testimonials."
},
{
"question": "Does every audit produce a score?",
"answer": "No. Missing applicable evidence produces an UNDECIDED result with coverage, gaps, and an interval instead of a comparable total."
},
{
"question": "Can it audit a live URL?",
"answer": "Yes. Provide the URL, content type, market, publication state, and any evidence unavailable from the rendered page."
},
{
"question": "Does it replace legal or medical review?",
"answer": "No. It checks evidence and presentation but does not provide professional advice or fabricate expert approval."
},
{
"question": "What can block publication?",
"answer": "Qualified vetoes cover material promise mismatch, material internal factual contradiction, and absent disclosure for a material relationship."
},
{
"question": "Can it save audit results?",
"answer": "Only with explicit permission, the full repository runtime, the required validator, and a valid constrained artifact path."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "auditor-runtime.md",
"type": "file",
"path": "references/auditor-runtime.md",
"lines": 381
},
{
"name": "item-reference.md",
"type": "file",
"path": "references/item-reference.md",
"lines": 100
},
{
"name": "recursive-refinement.md",
"type": "file",
"path": "references/recursive-refinement.md",
"lines": 76
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 173
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |