aiskillstore/marketplace / skills/aaron-he-zhu/performance-analyzer
performance-analyzer
VerifiedUse when the user asks to "analyze influencer campaign performance", "compare influencers", or "find what content worked"; produces metric scorecards vs target and benchmark, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion-attribution breakdowns, and ranked learnings. Not for dollar-level return math β use roi-calculator.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.2 KB |
| references/analysis-templates.md | markdown | 10.7 KB |
| skill-report.json | config | 45.4 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T13:24:17.252Z",
"slug": "aaron-he-zhu-performance-analyzer",
"source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/influencer/measure/performance-analyzer",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "ad0ab0bdb4845d742209fd3cf33b2b17f7281432b3c435d189c10c0a31a74062",
"tree_hash": "df181fa721e44f4cd8de60d32df8fc8c5ad68b787e527dca83d59b88d5326394",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "performance-analyzer",
"description": "Analyze influencer campaigns against targets and benchmarks. Compare platforms, creators, content, engagement quality, sentiment, conversions, and attribution.",
"summary": "Turn influencer campaign data into scorecards, rankings, attributed outcomes, and prioritized recommendations.",
"icon": "π¦",
"version": "16.0.3",
"author": "aaron-he-zhu",
"license": "Apache-2.0",
"category": "data",
"tags": [
"influencer-marketing",
"campaign-analysis",
"performance-metrics",
"content-analysis",
"conversion-attribution"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"filesystem",
"external_commands",
"network",
"env_access"
]
},
"security_audit": {
"risk_level": "high",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "Most alerts are false positives caused by Markdown links, code fences, placeholders, and metadata URLs. However, SKILL.md line 58 directs execution of an out-of-package Python connector and use of environment-held API credentials. Publication should require connector review, explicit network consent, and documented credential handling.",
"remediation": [
{
"issue": "The YouTube workflow executes a Python connector that is not included in the audited skill package.",
"suggestion": "Bundle and audit the connector, or remove the command. Require explicit user approval before execution and network access.",
"severity": "high"
},
{
"issue": "The YouTube workflow expects API credentials from the environment without describing secret handling.",
"suggestion": "Document the exact variable, minimum key permissions, destination API, and redaction rules. Never print or persist the key.",
"severity": "high"
}
],
"risk_factor_evidence": [
{
"factor": "filesystem",
"evidence": [
{
"file": "references/analysis-templates.md",
"line_start": 3,
"line_end": 3
},
{
"file": "references/analysis-templates.md",
"line_start": 5,
"line_end": 5
},
{
"file": "references/analysis-templates.md",
"line_start": 7,
"line_end": 7
},
{
"file": "references/analysis-templates.md",
"line_start": 8,
"line_end": 8
},
{
"file": "references/analysis-templates.md",
"line_start": 9,
"line_end": 9
},
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
},
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 43,
"line_end": 43
},
{
"file": "SKILL.md",
"line_start": 47,
"line_end": 47
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 77,
"line_end": 77
},
{
"file": "SKILL.md",
"line_start": 104,
"line_end": 104
},
{
"file": "SKILL.md",
"line_start": 105,
"line_end": 105
},
{
"file": "SKILL.md",
"line_start": 106,
"line_end": 106
},
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 108
},
{
"file": "SKILL.md",
"line_start": 109,
"line_end": 109
},
{
"file": "SKILL.md",
"line_start": 113,
"line_end": 113
},
{
"file": "SKILL.md",
"line_start": 117,
"line_end": 117
},
{
"file": "SKILL.md",
"line_start": 118,
"line_end": 118
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 26
},
{
"file": "SKILL.md",
"line_start": 26,
"line_end": 30
},
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 32
},
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 55
},
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 56
},
{
"file": "SKILL.md",
"line_start": 56,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 60
},
{
"file": "SKILL.md",
"line_start": 60,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 85,
"line_end": 99
},
{
"file": "SKILL.md",
"line_start": 99,
"line_end": 107
},
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 107
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 10
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
}
]
},
{
"factor": "env_access",
"evidence": [
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
}
]
}
],
"static_findings": [
{
"id": "filesystem:references/analysis-templates.md:3:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/analysis-templates.md",
"line_start": 3,
"line_end": 3,
"snippet": "Fill-in templates for each step of the influencer performance analysis. Each maps to a numbered step"
},
{
"id": "filesystem:references/analysis-templates.md:5:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/analysis-templates.md",
"line_start": 5,
"line_end": 5,
"snippet": "Repo-root links from this file use `../../../`."
},
{
"id": "filesystem:references/analysis-templates.md:7:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/analysis-templates.md",
"line_start": 7,
"line_end": 7,
"snippet": "- [skill-contract.md](../../../../references/skill-contract.md)"
},
{
"id": "filesystem:references/analysis-templates.md:8:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/analysis-templates.md",
"line_start": 8,
"line_end": 8,
"snippet": "- [state-model.md](../../../../references/state-model.md)"
},
{
"id": "filesystem:references/analysis-templates.md:9:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "references/analysis-templates.md",
"line_start": 9,
"line_end": 9,
"snippet": "- [CONNECTORS.md](../../../../CONNECTORS.md)"
},
{
"id": "blocker:references/analysis-templates.md:364:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "references/analysis-templates.md",
"line_start": 364,
"line_end": 364,
"snippet": "| @[handle2] | Renew at same level | Solid results |"
},
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly len"
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 26,
"snippet": "```"
},
{
"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": 30,
"snippet": "```"
},
{
"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": 32,
"snippet": "```"
},
{
"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": 36,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 36,
"line_end": 37,
"snippet": "- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); inf"
},
{
"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": 38,
"snippet": "- **Writes**: a performance analysis to `memory/influencer/performance-analyzer/YYYY-MM-DD-<campaign"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 53,
"snippet": "- **Promotes**: durable facts (top-performing creators, winning formats, platform ROI splits, roster"
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 53,
"line_end": 55,
"snippet": "Where a connector could speed the work, the skill marks it with a `~~` placeholder:"
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 55,
"line_end": 56,
"snippet": "- `~~social platform analytics` β native reach/engagement/video metrics per post."
},
{
"id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 56,
"line_end": 58,
"snippet": "- `~~web analytics` β site traffic, click-through, and on-site conversion data."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 58,
"line_end": 58,
"snippet": "**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \""
},
{
"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": 60,
"snippet": "- `~~ecommerce / sales platform` β revenue, orders, AOV, promo-code redemptions."
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 60,
"line_end": 85,
"snippet": "- `~~influencer database` β historical creator benchmarks for comparison."
},
{
"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": 99,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:99:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 99,
"line_end": 107,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 107,
"line_end": 107,
"snippet": "- [measurement-protocol.md](../../../references/measurement-protocol.md) β preregistered readback wi"
},
{
"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:13:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": "metadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"influencer\", \"phase\": \"meas"
},
{
"id": "filesystem:SKILL.md:20:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly len"
},
{
"id": "filesystem:SKILL.md:36:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 36,
"line_end": 36,
"snippet": "- **Reads**: campaign name and date range; native platform analytics (reach, views, engagement); inf"
},
{
"id": "filesystem:SKILL.md:43:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 43,
"line_end": 43,
"snippet": "- **Primary next skill**: [roi-calculator](../roi-calculator/SKILL.md) β turn measured performance i"
},
{
"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": "> Emit the standard shape from [skill-contract.md Β§Handoff Summary Format](../../../references/skill"
},
{
"id": "filesystem:SKILL.md:58:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 58,
"line_end": 58,
"snippet": "**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \""
},
{
"id": "filesystem:SKILL.md:62:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 62,
"line_end": 62,
"snippet": "No placeholder is required to run. See [CONNECTORS.md](../../../CONNECTORS.md) for the verified free"
},
{
"id": "filesystem:SKILL.md:77:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 77,
"line_end": 77,
"snippet": "Before naming any creator/format/platform a real winner, clear the significance bar in [measurement-"
},
{
"id": "filesystem:SKILL.md:104:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 104,
"line_end": 104,
"snippet": "- [skill-contract.md](../../../references/skill-contract.md) β shared contract and handoff format."
},
{
"id": "filesystem:SKILL.md:105:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 105,
"line_end": 105,
"snippet": "- [state-model.md](../../../references/state-model.md) β memory tiers and save-path conventions."
},
{
"id": "filesystem:SKILL.md:106:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 106,
"line_end": 106,
"snippet": "- [CONNECTORS.md](../../../CONNECTORS.md) β verified free/keyless data recipes per connector categor"
},
{
"id": "filesystem:SKILL.md:107:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 107,
"line_end": 107,
"snippet": "- [measurement-protocol.md](../../../references/measurement-protocol.md) β preregistered readback wi"
},
{
"id": "filesystem:SKILL.md:108:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 108,
"line_end": 108,
"snippet": "- The C3 benchmark at [references/c3/scoring-architecture.md](../../../references/c3/scoring-archite"
},
{
"id": "filesystem:SKILL.md:109:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 109,
"line_end": 109,
"snippet": "- Sibling skills: [roi-calculator](../roi-calculator/SKILL.md), [report-generator](../report-generat"
},
{
"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": "**Primary**: [roi-calculator](../roi-calculator/SKILL.md) β convert measured performance into dollar"
},
{
"id": "filesystem:SKILL.md:117:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 117,
"line_end": 117,
"snippet": "- [report-generator](../report-generator/SKILL.md) β package the analysis into a formal stakeholder "
},
{
"id": "filesystem:SKILL.md:118:path-traversal-sequence",
"category": "filesystem",
"severity": "high",
"pattern": "Path traversal sequence",
"file": "SKILL.md",
"line_start": 118,
"line_end": 118,
"snippet": "- [fit-scorer](../../discover/fit-scorer/SKILL.md) β feed proven performers back into creator scorin"
},
{
"id": "env_access:SKILL.md:58:generic-api-secret-keys",
"category": "env_access",
"severity": "high",
"pattern": "Generic API/secret keys",
"file": "SKILL.md",
"line_start": 58,
"line_end": 58,
"snippet": "**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \""
},
{
"id": "blocker:SKILL.md:20:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "> **Cross-discipline (paid ads):** this is also the cross-channel **paid-ads** scorecard/anomaly len"
}
],
"finding_verdicts": [
{
"id": "filesystem:references/analysis-templates.md:3:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence is part of a Markdown link to SKILL.md. It does not instruct filesystem traversal or access."
},
{
"id": "filesystem:references/analysis-templates.md:5:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line documents the relative-link convention for repository references. It performs no filesystem operation."
},
{
"id": "filesystem:references/analysis-templates.md:7:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a static Markdown link to shared documentation. No path is constructed from user input."
},
{
"id": "filesystem:references/analysis-templates.md:8:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a static Markdown link to shared documentation. It does not read or modify files."
},
{
"id": "filesystem:references/analysis-templates.md:9:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a static Markdown link to CONNECTORS.md. The relative path is navigation, not traversal behavior."
},
{
"id": "blocker:references/analysis-templates.md:364:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The text is a placeholder influencer handle in a recommendation table. It requests no system information."
},
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Backticks format a memory path in Markdown. The line contains no Ruby or shell command."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks open a fenced example prompt. They are Markdown syntax, not command substitution."
},
{
"id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks close a fenced example prompt. No executable command appears in the block."
},
{
"id": "external_commands:SKILL.md:30:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks open a fenced natural-language prompt. They do not invoke a shell."
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks close a fenced natural-language prompt. There is no command execution."
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Backticks format a memory file pattern in prose. The line describes optional input data and performs no command."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Backticks format the intended report path. There is no shell syntax or executable instruction."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Backticks format a Markdown file path. The line describes saved facts, not external command execution."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks identify a connector placeholder marker. They are documentation syntax and contain no command."
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The inline code is a descriptive connector placeholder. It does not execute analytics software."
},
{
"id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The inline code is a descriptive connector placeholder. It has no executable shell content."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.96,
"reason": "The line explicitly directs execution of a Python connector with arguments. The referenced script is outside the audited package and can make network requests.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The inline code is a connector category placeholder. It contains no program or shell invocation."
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The inline code is a connector category placeholder. It does not issue an external command."
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks open a Markdown output example. The example contains campaign metrics, not executable code."
},
{
"id": "external_commands:SKILL.md:99:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks close a Markdown output example. They do not invoke Ruby or a shell."
},
{
"id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Backticks format a helper filename and evidence label in documentation. The line provides no shell command or arguments."
},
{
"id": "network:SKILL.md:10:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL is the declared project homepage in frontmatter. It does not trigger a network request."
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The URL is repeated as source metadata. No data is sent to that address."
},
{
"id": "filesystem:SKILL.md:20:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Relative paths appear only in Markdown links to sibling skills. The line does not access files through user-controlled paths."
},
{
"id": "filesystem:SKILL.md:36:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The traversal sequence belongs to a static Markdown link. The memory path is a documented input convention."
},
{
"id": "filesystem:SKILL.md:43:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path links to a sibling skill document. It is not used for runtime file access."
},
{
"id": "filesystem:SKILL.md:47:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence occurs in a Markdown documentation link. It performs no filesystem action."
},
{
"id": "filesystem:SKILL.md:58:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The detected traversal sequence is in the README Markdown link. The executable path uses a fixed plugin-root variable without traversal."
},
{
"id": "filesystem:SKILL.md:62:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative sequence is a static Markdown link to connector documentation. It is not a file operation."
},
{
"id": "filesystem:SKILL.md:77:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "All relative sequences are static links to protocols and sibling skills. No path input is accepted or evaluated."
},
{
"id": "filesystem:SKILL.md:104:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence appears in a static reference link. It does not direct filesystem traversal."
},
{
"id": "filesystem:SKILL.md:105:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence appears in a static reference link. No runtime path access occurs."
},
{
"id": "filesystem:SKILL.md:106:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence appears in a static link to CONNECTORS.md. It is documentation navigation only."
},
{
"id": "filesystem:SKILL.md:107:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence appears in a static protocol link. No file path is derived from untrusted input."
},
{
"id": "filesystem:SKILL.md:108:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The sequence appears in a static benchmark documentation link. It has no filesystem side effect."
},
{
"id": "filesystem:SKILL.md:109:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative paths are Markdown links to sibling skills. They do not access files during analysis."
},
{
"id": "filesystem:SKILL.md:113:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a Markdown link to the next skill. It is not a traversal instruction."
},
{
"id": "filesystem:SKILL.md:117:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static sibling-skill link. No runtime filesystem access is requested."
},
{
"id": "filesystem:SKILL.md:118:path-traversal-sequence",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The relative path is a static sibling-skill link. It cannot be influenced by campaign input."
},
{
"id": "env_access:SKILL.md:58:generic-api-secret-keys",
"verdict": "confirmed",
"confidence": 0.94,
"reason": "The workflow explicitly expects YOUTUBE_API_KEY and references CLAUDE_PLUGIN_ROOT. Secret handling and connector behavior cannot be verified from the audited files.",
"severity": "high"
},
{
"id": "blocker:SKILL.md:20:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The line describes paid-ad analysis and output storage. It does not collect host, account, process, or network configuration."
}
],
"semantic_findings": [
{
"title": "Unaudited Connector Execution",
"description": "The skill instructs agents to run `${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py`, but that script is absent from the audited package. Its network and credential behavior cannot be reviewed.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
}
],
"confidence": 0.97,
"confidence_reasoning": "The command and external script path are explicit, while the file structure contains only SKILL.md and one reference document."
}
],
"critical_findings": [],
"high_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"",
"locations": [
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.96,
"confidence_reasoning": "The line explicitly directs execution of a Python connector with arguments. The referenced script is outside the audited package and can make network requests."
},
{
"title": "Generic API/secret keys",
"description": "**Measured YouTube post-performance (free key)**: when campaign content lives on YouTube, `python3 \"",
"locations": [
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
}
],
"review_kind": "capability",
"source_category": "env_access",
"source_severity": "high",
"confidence": 0.94,
"confidence_reasoning": "The workflow explicitly expects YOUTUBE_API_KEY and references CLAUDE_PLUGIN_ROOT. Secret handling and connector behavior cannot be verified from the audited files."
},
{
"title": "Unaudited Connector Execution",
"description": "The skill instructs agents to run `${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py`, but that script is absent from the audited package. Its network and credential behavior cannot be reviewed.",
"locations": [
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 58
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.97,
"confidence_reasoning": "The command and external script path are explicit, while the file structure contains only SKILL.md and one reference document."
}
],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 2,
"total_lines": 535,
"audit_model": "codex",
"audited_at": "2026-07-12T13:24:17.252Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Analyze Influencer Campaign Performance",
"value_statement": "Influencer results are difficult to compare across creators, platforms, and attribution methods. This skill converts campaign data into scorecards, rankings, insights, and recommendations.",
"seo_keywords": [
"Claude influencer analysis",
"Codex campaign analysis",
"Claude Code marketing skill",
"influencer performance analyzer",
"campaign metric scorecard",
"creator performance ranking",
"content performance analysis",
"engagement sentiment analysis",
"conversion attribution",
"social media benchmarks"
],
"actual_capabilities": [
"Scores campaign metrics against supplied targets and benchmarks.",
"Ranks platforms, creators, content formats, and themes.",
"Analyzes engagement quality, comment sentiment, and purchase intent signals.",
"Maps conversions across promo codes, UTM links, direct attribution, and estimates.",
"Identifies winning content patterns and underperformance causes.",
"Produces prioritized learnings, roster decisions, and future campaign recommendations."
],
"limitations": [
"Requires campaign exports, screenshots, analytics, or metrics supplied by the user.",
"Cannot verify missing benchmarks, attribution assumptions, or creator-reported data.",
"Does not calculate complete dollar-level ROI or final C3 scores.",
"YouTube retrieval requires an external connector and API key not included here."
],
"use_cases": [
{
"title": "Review a completed campaign",
"description": "Compare final results with targets and identify the strongest creators, platforms, and content.",
"target_user": "Influencer marketing manager"
},
{
"title": "Optimize an active campaign",
"description": "Find early underperformance and decide where to adjust creators, formats, or platform allocation.",
"target_user": "Growth marketing lead"
},
{
"title": "Build reusable benchmarks",
"description": "Capture performance patterns and creator baselines for future planning and selection.",
"target_user": "Marketing analyst"
}
],
"prompt_templates": [
{
"title": "Score one campaign",
"prompt": "Analyze [campaign] using these results, targets, and benchmarks: [data]. Summarize performance and list the three most important actions.",
"scenario": "Beginner review with consolidated campaign data"
},
{
"title": "Compare creators",
"prompt": "Compare [creator list] for [campaign]. Rank them by reach, engagement, conversions, and efficiency. Explain each renewal recommendation.",
"scenario": "Creator roster evaluation"
},
{
"title": "Find winning content",
"prompt": "Analyze these post-level results and comments: [data]. Compare formats, themes, hooks, sentiment, and purchase intent. Identify patterns worth testing again.",
"scenario": "Content and engagement analysis"
},
{
"title": "Run a full attribution review",
"prompt": "Evaluate [campaign] across platforms and creators using [data]. Separate measured, user-provided, and estimated outcomes. Apply [significance criteria] before declaring winners.",
"scenario": "Advanced cross-channel decision analysis"
}
],
"output_examples": [
{
"input": "Campaign results with reach, engagement, conversions, targets, and platform totals.",
"output": [
"Overall performance: Above target for reach and engagement, below target for conversions.",
"Top platform: TikTok produced the strongest engagement and conversion efficiency.",
"Priority action: Test stronger landing-page alignment before increasing spend."
]
},
{
"input": "Post-level metrics and comments from five creators.",
"output": [
"Top creator: @creator1 led qualified engagement and attributed sales.",
"Winning pattern: Short demonstrations with a direct opening generated more saves and purchase questions.",
"Roster decision: Renew two creators, keep one testing, and replace two underperformers."
]
},
{
"input": "Promo-code, UTM, direct, and estimated conversion records.",
"output": "The analysis separates attribution methods, flags overlapping claims, and ranks recommendations by evidence strength."
}
],
"best_practices": [
"Label every metric as measured, user-provided, calculated, or estimated.",
"Supply campaign targets, comparison periods, and creator-level source data.",
"Apply statistical and practical thresholds before declaring a winner."
],
"anti_patterns": [
"Do not compare creators using totals when audience size and spend differ materially.",
"Do not combine promo, UTM, and estimated conversions without checking overlap.",
"Do not treat sentiment samples or screenshots as complete population data."
],
"faq": [
{
"question": "What data should I provide?",
"answer": "Provide campaign dates, creator posts, platform metrics, targets, benchmarks, traffic, conversions, sales, and attribution records when available."
},
{
"question": "Can it compare creators across platforms?",
"answer": "Yes. Provide comparable metrics and spend data. The skill can normalize context and explain platform differences."
},
{
"question": "Does it calculate ROI?",
"answer": "It can organize revenue and efficiency inputs, but complete dollar-level ROI belongs in the separate ROI calculator workflow."
},
{
"question": "Can it retrieve live platform data?",
"answer": "The core workflow uses supplied data. YouTube retrieval needs an external Python connector and an API key."
},
{
"question": "How does it handle missing benchmarks?",
"answer": "It should state the gap, use supplied historical comparisons when appropriate, and avoid unsupported performance claims."
},
{
"question": "Can it analyze comment sentiment?",
"answer": "Yes. It can group supplied comments by sentiment and intent, but results depend on sample coverage and data quality."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "analysis-templates.md",
"type": "file",
"path": "references/analysis-templates.md",
"lines": 414
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 121
}
]
}
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 |