Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/report-generator

report-generator

Verified

Use when the user asks to "create a campaign report", "build an executive summary", or "deliver client results"; produces audience-tailored influencer marketing reports (executive, client, internal team) with data tables, narrative, key learnings, and recommendations. Not for raw metric computation β€” use performance-analyzer.

FileKindSize
SKILL.mdskill md7.9 KB
references/report-templates.mdmarkdown11.9 KB
skill-report.jsonconfig40.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-12T13:48:05.231Z",
    "slug": "aaron-he-zhu-report-generator",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/influencer/measure/report-generator",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "173ca7efcd2792ed486df85447d87a368396847ce2e2479beef8c914e1aad5ad",
    "tree_hash": "3305a3f155f388fa0f1eecb551303fb8937b3d8cc0b063f9a63ac09609f17695",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "report-generator",
    "description": "Creates audience-specific influencer marketing reports from existing campaign metrics, with structured results, insights, visual recommendations, and clear next steps.",
    "summary": "Turn campaign metrics into stakeholder-ready marketing reports.",
    "icon": "πŸ“¦",
    "version": "13.0.3",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "category": "writing",
    "tags": [
      "campaign-reporting",
      "influencer-marketing",
      "executive-summary",
      "performance-analysis",
      "client-reporting"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "filesystem",
      "external_commands",
      "network"
    ]
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All 38 static findings are false positives caused by Markdown links, code fences, inline code, metadata URLs, or ordinary reporting language. One medium semantic risk remains because the skill directs agents to persist campaign reports and selected metrics in shared memory without requesting confirmation.",
    "remediation": [
      {
        "issue": "Campaign metrics and conclusions are saved to persistent report and hot-cache files without an explicit consent or sensitivity check.",
        "suggestion": "Ask before saving, allow a no-persistence mode, and redact confidential client, creator, revenue, and customer data from shared memory.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "references/report-templates.md",
            "line_start": 3,
            "line_end": 3
          },
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 45,
            "line_end": 45
          },
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 49
          },
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 62
          },
          {
            "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": 110,
            "line_end": 110
          },
          {
            "file": "SKILL.md",
            "line_start": 111,
            "line_end": 111
          },
          {
            "file": "SKILL.md",
            "line_start": 112,
            "line_end": 112
          },
          {
            "file": "SKILL.md",
            "line_start": 116,
            "line_end": 116
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 121
          }
        ]
      },
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 28,
            "line_end": 32
          },
          {
            "file": "SKILL.md",
            "line_start": 32,
            "line_end": 34
          },
          {
            "file": "SKILL.md",
            "line_start": 34,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 40,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 59
          },
          {
            "file": "SKILL.md",
            "line_start": 59,
            "line_end": 60
          },
          {
            "file": "SKILL.md",
            "line_start": 60,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 70
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 76
          },
          {
            "file": "SKILL.md",
            "line_start": 84,
            "line_end": 100
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "filesystem:references/report-templates.md:3:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "references/report-templates.md",
        "line_start": 3,
        "line_end": 3,
        "snippet": "Full audience templates, visualization recommendations, writing best practices, and a worked example"
      },
      {
        "id": "blocker:references/report-templates.md:19:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/report-templates.md",
        "line_start": 19,
        "line_end": 19,
        "snippet": "| Client | Results, Value | Medium | \"What did I get?\" |"
      },
      {
        "id": "blocker:references/report-templates.md:457:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/report-templates.md",
        "line_start": 457,
        "line_end": 458,
        "snippet": "2. **Execution**: What we did"
      },
      {
        "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 **paid-ads** reporting surface β€” build exec/clie"
      },
      {
        "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": 28,
        "snippet": "```"
      },
      {
        "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": 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": 34,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 34,
        "line_end": 38,
        "snippet": "```"
      },
      {
        "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": 38,
        "snippet": "- **Reads**: campaign name, reporting period, target audience, and computed metrics (reach, engageme"
      },
      {
        "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": 40,
        "snippet": "- **Writes**: a finished report in the audience-appropriate template, saved to `memory/influencer/re"
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 40,
        "line_end": 57,
        "snippet": "- **Promotes**: durable verdicts (final ROI/ROAS, top performers, renew/drop calls, headline learnin"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 58,
        "snippet": "- `~~social platform analytics` β€” reach, impressions, engagement, video views per post"
      },
      {
        "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": 59,
        "snippet": "- `~~influencer database` β€” creator handles, tiers, fees, audience demographics"
      },
      {
        "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": "- `~~analytics` β€” link clicks, conversions, attributed revenue"
      },
      {
        "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": 70,
        "snippet": "- `~~CRM` β€” new-customer counts and downstream revenue"
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 70,
        "snippet": "2. **Pick the audience template and fill it in** β€” full executive, client, and internal-team templat"
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 76,
        "snippet": "5. **Save and promote** β€” write the finished report to `memory/influencer/report-generator/YYYY-MM-D"
      },
      {
        "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": 100,
        "snippet": "```markdown"
      },
      {
        "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 **paid-ads** reporting surface β€” build exec/clie"
      },
      {
        "id": "filesystem:SKILL.md:45:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 45,
        "line_end": 45,
        "snippet": "- **Primary next skill**: [content-quality-auditor](../../../seo-geo/optimize/content-quality-audito"
      },
      {
        "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": "> Emit the standard shape from [skill-contract.md Β§Handoff Summary Format](../../../references/skill"
      },
      {
        "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": "Without any of these, the skill asks you for the numbers and proceeds. See [CONNECTORS.md](../../../"
      },
      {
        "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": "- [skill-contract.md](../../../references/skill-contract.md) β€” shared contract and handoff format"
      },
      {
        "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": "- [state-model.md](../../../references/state-model.md) β€” memory tiers and save-path convention"
      },
      {
        "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": "- [CONNECTORS.md](../../../CONNECTORS.md) β€” free/keyless data recipes per connector category"
      },
      {
        "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": "- [performance-analyzer](../performance-analyzer/SKILL.md) β€” generates the metrics this report consu"
      },
      {
        "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": "- [roi-calculator](../roi-calculator/SKILL.md) β€” supplies ROI/ROAS figures"
      },
      {
        "id": "filesystem:SKILL.md:110:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 110,
        "line_end": 110,
        "snippet": "- [campaign-planner](../../plan/campaign-planner/SKILL.md) β€” original plan to compare results agains"
      },
      {
        "id": "filesystem:SKILL.md:111:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 111,
        "line_end": 111,
        "snippet": "- [content-amplifier](../../activate/content-amplifier/SKILL.md) β€” amplification results to report o"
      },
      {
        "id": "filesystem:SKILL.md:112:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 112,
        "line_end": 112,
        "snippet": "- [content-quality-auditor](../../../seo-geo/optimize/content-quality-auditor/SKILL.md) β€” quality ga"
      },
      {
        "id": "filesystem:SKILL.md:116:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 116,
        "line_end": 116,
        "snippet": "**Primary**: [content-quality-auditor](../../../seo-geo/optimize/content-quality-auditor/SKILL.md) β€”"
      },
      {
        "id": "filesystem:SKILL.md:120:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 120,
        "snippet": "- [performance-analyzer](../performance-analyzer/SKILL.md) β€” if the report exposes data gaps, re-ana"
      },
      {
        "id": "filesystem:SKILL.md:121:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 121,
        "snippet": "- [roi-calculator](../roi-calculator/SKILL.md) β€” recompute return figures if the financial inputs ch"
      },
      {
        "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 **paid-ads** reporting surface β€” build exec/clie"
      },
      {
        "id": "blocker:SKILL.md:76:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 76,
        "snippet": "5. **Save and promote** β€” write the finished report to `memory/influencer/report-generator/YYYY-MM-D"
      },
      {
        "id": "blocker:SKILL.md:123:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 123,
        "line_end": 123,
        "snippet": "**Termination note** (visited-set): if a recommended skill has already been invoked this session, st"
      }
    ],
    "finding_verdicts": [
      {
        "id": "filesystem:references/report-templates.md:3:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 3 contains a relative Markdown link to SKILL.md, not a filesystem read, write, or traversal operation."
      },
      {
        "id": "blocker:references/report-templates.md:19:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 19 is an audience-needs table entry asking what value a client received; it performs no system reconnaissance."
      },
      {
        "id": "blocker:references/report-templates.md:457:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 457-458 describe the execution and results stages of a report narrative, not host discovery or reconnaissance."
      },
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 20 uses inline Markdown code for memory paths and a relative link; it contains no Ruby backticks or shell invocation."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 26-28 are a plain fenced prompt example with no command, interpreter, or executable content."
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 28-32 close one Markdown fence and introduce another prompt example; no command execution is requested."
      },
      {
        "id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 32-34 contain a fenced natural-language reporting request, not shell or Ruby syntax."
      },
      {
        "id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 34-38 close a Markdown example and begin the skill contract; no external command is present."
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 38 names related skills with inline Markdown code and describes data inputs; it does not execute those names."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 39-40 format destination paths as inline code; no shell command or dynamic execution mechanism exists."
      },
      {
        "id": "external_commands:SKILL.md:40:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 40-57 describe memory promotion and optional data sources in prose, without invoking an external process."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 57-58 use inline code to label optional connector categories; the labels are not executable commands."
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 58-59 list optional influencer and analytics data categories with Markdown formatting only."
      },
      {
        "id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 59-60 name analytics and CRM connector categories; they contain no shell syntax or execution instruction."
      },
      {
        "id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 60-70 contain prose, Markdown links, and inline skill names, not an external command invocation."
      },
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 70 references related skill outputs using inline code and describes report assembly; no command is executed."
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 76 formats prescribed output paths as inline code; it does not contain shell backticks or an executable command."
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Lines 84-100 are a fenced Markdown report example, not code intended for execution."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 10 declares the public GitHub project homepage in frontmatter and does not instruct or perform a network request."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 13 repeats the public project homepage as metadata; no data transmission, download, or remote execution occurs."
      },
      {
        "id": "filesystem:SKILL.md:20:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 20 contains a relative Markdown link to a sibling skill; it is documentation navigation, not path traversal against user input."
      },
      {
        "id": "filesystem:SKILL.md:45:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 45 is a fixed relative Markdown link to a documented next skill and does not access arbitrary files."
      },
      {
        "id": "filesystem:SKILL.md:49:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 49 is a fixed relative documentation link to the shared handoff format, with no user-controlled path."
      },
      {
        "id": "filesystem:SKILL.md:62:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 62 links to a fixed connector guide in the repository; it does not construct or traverse a runtime path."
      },
      {
        "id": "filesystem:SKILL.md:105:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 105 is a fixed relative Markdown reference to skill-contract.md and has no filesystem operation."
      },
      {
        "id": "filesystem:SKILL.md:106:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 106 is a fixed relative Markdown reference to state-model.md and has no runtime path handling."
      },
      {
        "id": "filesystem:SKILL.md:107:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 107 is a repository documentation link to CONNECTORS.md, not an instruction to enumerate or escape directories."
      },
      {
        "id": "filesystem:SKILL.md:108:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 108 is a fixed link to the neighboring performance-analyzer skill, without user-controlled path input."
      },
      {
        "id": "filesystem:SKILL.md:109:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 109 is a fixed link to the neighboring roi-calculator skill and performs no filesystem access."
      },
      {
        "id": "filesystem:SKILL.md:110:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 110 is a fixed repository link to campaign-planner, not dynamic path construction or traversal."
      },
      {
        "id": "filesystem:SKILL.md:111:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 111 is a fixed repository link to content-amplifier and contains no file operation."
      },
      {
        "id": "filesystem:SKILL.md:112:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 112 is a fixed repository link to content-quality-auditor, with no arbitrary path access."
      },
      {
        "id": "filesystem:SKILL.md:116:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 116 repeats a fixed Markdown link to the recommended quality-audit skill; no traversal operation is present."
      },
      {
        "id": "filesystem:SKILL.md:120:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 120 is a fixed link to performance-analyzer for workflow guidance, not a runtime filesystem path."
      },
      {
        "id": "filesystem:SKILL.md:121:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 121 is a fixed link to roi-calculator for workflow guidance, not a traversal primitive."
      },
      {
        "id": "blocker:SKILL.md:20:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 20 discusses paid-ad reporting inputs and output locations; it does not inspect the host, users, processes, or network."
      },
      {
        "id": "blocker:SKILL.md:76:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 76 prescribes report storage and memory promotion, but it does not perform system reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:123:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Line 123 limits skill-chain depth and prevents repeated invocation; it does not discover system information."
      }
    ],
    "semantic_findings": [
      {
        "title": "Campaign Data Persisted Without Confirmation",
        "description": "The skill directs agents to save reports and promote ROI, creator decisions, and campaign learnings into shared memory without checking sensitivity or user consent.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 76
          }
        ],
        "confidence": 0.94,
        "confidence_reasoning": "The persistence instructions and target paths are explicit. The impact depends on host memory scope and whether campaign data is confidential."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Campaign Data Persisted Without Confirmation",
        "description": "The skill directs agents to save reports and promote ROI, creator decisions, and campaign learnings into shared memory without checking sensitivity or user consent.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 76
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.94,
        "confidence_reasoning": "The persistence instructions and target paths are explicit. The impact depends on host memory scope and whether campaign data is confidential."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 2,
    "total_lines": 637,
    "audit_model": "codex",
    "audited_at": "2026-07-12T13:48:05.231Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Create Stakeholder-Ready Campaign Reports",
    "value_statement": "Campaign metrics often lack the structure and context stakeholders need. This skill turns existing influencer data into audience-specific reports with insights and recommendations.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "influencer campaign report",
      "executive summary generator",
      "client performance report",
      "marketing report template",
      "campaign insights",
      "ROI reporting"
    ],
    "actual_capabilities": [
      "Creates executive, client, internal team, and board reports from supplied campaign metrics.",
      "Organizes reach, engagement, conversion, spend, revenue, ROI, and creator results into clear sections and tables.",
      "Pairs metrics with targets, benchmarks, or prior-period comparisons.",
      "Recommends suitable visual formats for each audience and metric.",
      "Summarizes key learnings, top performers, opportunities, and concrete next steps.",
      "Produces action-item tables with owners and deadlines for team and board audiences."
    ],
    "limitations": [
      "It does not calculate raw metrics, attribution, ROI, or ROAS from source data.",
      "It requires existing metrics or user-provided values before creating a complete report.",
      "It does not connect directly to analytics, CRM, or social platforms without host-provided connectors.",
      "Its recommendations depend on the accuracy and completeness of supplied campaign data."
    ],
    "use_cases": [
      {
        "title": "Executive Campaign Review",
        "description": "Summarize business outcomes, ROI, major lessons, and investment recommendations for leadership.",
        "target_user": "Marketing executives"
      },
      {
        "title": "Client Results Delivery",
        "description": "Present campaign performance, creator highlights, audience insights, and next steps in a polished client report.",
        "target_user": "Agency account managers"
      },
      {
        "title": "Team Performance Retrospective",
        "description": "Document detailed metrics, content patterns, budget variance, learnings, and assigned actions for future campaigns.",
        "target_user": "Influencer marketing teams"
      }
    ],
    "prompt_templates": [
      {
        "title": "Create a Basic Campaign Report",
        "prompt": "Create a campaign report for [campaign name]. The audience is [executive, client, team, or board]. Use these metrics: [metrics].",
        "scenario": "Use when campaign metrics are ready and a standard report is needed."
      },
      {
        "title": "Build an Executive Summary",
        "prompt": "Build an executive summary for [campaign and period]. Compare results with [targets or prior period]. Highlight ROI, key outcomes, and one recommendation.",
        "scenario": "Use for leadership updates that require concise business conclusions."
      },
      {
        "title": "Prepare a Client Performance Report",
        "prompt": "Prepare a client report for [campaign]. Include objectives, delivery, performance, top creators, audience insights, recommendations, and next steps. Use [provided data].",
        "scenario": "Use when an agency must explain delivered value and future opportunities."
      },
      {
        "title": "Develop a Detailed Team Retrospective",
        "prompt": "Develop a team retrospective for [campaign]. Analyze results by platform, creator, content format, budget, and efficiency. Add evidence-based recommendations, owners, and deadlines.",
        "scenario": "Use for advanced operational analysis and future campaign planning."
      }
    ],
    "output_examples": [
      {
        "input": "Create an executive report for a holiday campaign with $50,000 spend, $165,000 revenue, and 3.5 million reach.",
        "output": "Holiday Campaign Executive Summary\n\nThe campaign generated $165,000 from $50,000 in spend, producing 230% ROI and 3.3 ROAS.\n\nRecommendation: Increase the next-quarter budget while prioritizing the best-performing creators and product demonstration content."
      },
      {
        "input": "Summarize a client campaign that exceeded its reach target by 20 percent but missed its conversion target by 15 percent.",
        "output": "Client Performance Summary\n\nReach exceeded target by 20%, showing strong awareness delivery. Conversions finished 15% below target, indicating a gap after engagement.\n\nNext step: Test clearer calls to action and improve landing-page alignment."
      },
      {
        "input": "Create an internal team report with creator results, content findings, and next actions.",
        "output": [
          "Top performers: Identify creators that exceeded reach, engagement, and conversion benchmarks.",
          "Content learning: Compare product demonstrations, tutorials, and lifestyle posts using consistent metrics.",
          "Actions: Assign creator renewal decisions, brief revisions, and measurement updates to named owners with deadlines."
        ]
      }
    ],
    "best_practices": [
      "Provide validated metrics, campaign dates, audience, targets, and comparison periods before requesting the report.",
      "Match detail to the audience and explain every important metric with relevant context.",
      "Review confidential data and confirm persistence preferences before saving reports or conclusions."
    ],
    "anti_patterns": [
      "Do not ask the skill to invent missing results, targets, benchmarks, or financial values.",
      "Do not use one report structure for executives, clients, and delivery teams.",
      "Do not present isolated metrics without explaining performance, causes, implications, and next actions."
    ],
    "faq": [
      {
        "question": "Does this skill calculate ROI or ROAS?",
        "answer": "No. It reports supplied values and expects a separate analyzer or calculator to produce validated financial metrics."
      },
      {
        "question": "Which report audiences are supported?",
        "answer": "It supports executive, client, internal team, and board audiences with different detail levels and priorities."
      },
      {
        "question": "What information should I provide?",
        "answer": "Provide the campaign name, period, audience, objectives, targets, spend, revenue, reach, engagement, conversions, and creator results when available."
      },
      {
        "question": "Can it work without live platform connections?",
        "answer": "Yes. Supply the campaign metrics directly, and the skill can create the report without live integrations."
      },
      {
        "question": "Does it create charts?",
        "answer": "It recommends suitable chart types and report layouts. Actual chart rendering depends on the host and available tools."
      },
      {
        "question": "Where can reports be saved?",
        "answer": "The skill proposes workspace memory paths. Confirm the location and remove sensitive information before enabling persistence."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "report-templates.md",
          "type": "file",
          "path": "references/report-templates.md",
          "lines": 513
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 124
    }
  ]
}
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
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: 194kUpdated Claude CodeCodexVerifiedInstall