Skip to content

aiskillstore/marketplace / skills/aaron-he-zhu/performance-monitor

performance-monitor

Verified

Use when the user asks to "generate an SEO report", "出月报", "set SEO alerts", or "排名掉了提醒我"; two modes — report builds multi-metric traffic/ranking/authority/content dashboards, and alert configures threshold notifications for future ranking, traffic, technical, backlink, competitor, and AI-visibility changes. Not for raw position-by-position deltas — use rank-tracker. SEO报告/绩效仪表盘/SEO预警/排名监控

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-12T13:27:49.209Z",
    "slug": "aaron-he-zhu-performance-monitor",
    "source_url": "https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/seo-geo/monitor/performance-monitor",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "f95a3fcbad925ec13267195cf9c90a0385d8d2a1f542e18e8f5edfeac435aeb6",
    "tree_hash": "1e762e298787c3a15a753075886d7b78f9fc0bfd12faa1759dbf38be5b9e254a",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "performance-monitor",
    "description": "Creates source-labeled SEO and GEO performance reports or configures threshold-based monitoring plans for traffic, rankings, technical health, backlinks, competitors, and AI visibility.",
    "summary": "Build SEO performance reports and monitoring alert plans.",
    "icon": "📦",
    "version": "16.0.2",
    "author": "aaron-he-zhu",
    "license": "Apache-2.0",
    "category": "data",
    "tags": [
      "seo-monitoring",
      "performance-reporting",
      "traffic-alerts",
      "ranking-analysis",
      "geo-visibility"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network",
      "filesystem",
      "env_access"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "Most detections are Markdown syntax, documentation links, or metadata URLs without executable behavior. SKILL.md line 63 directs agents to run a Python ledger command with a domain argument. This creates command execution and input-handling risk, but no malicious or exfiltration intent was found.",
    "remediation": [
      {
        "issue": "An executable ledger example accepts a domain placeholder as a command argument.",
        "suggestion": "Invoke ledger.py with an argument array, validate domain values, and require confirmation before recording data.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          },
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 36
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 38,
            "line_end": 38
          },
          {
            "file": "SKILL.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "SKILL.md",
            "line_start": 44,
            "line_end": 44
          },
          {
            "file": "SKILL.md",
            "line_start": 45,
            "line_end": 46
          },
          {
            "file": "SKILL.md",
            "line_start": 46,
            "line_end": 46
          },
          {
            "file": "SKILL.md",
            "line_start": 48,
            "line_end": 49
          },
          {
            "file": "SKILL.md",
            "line_start": 49,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 63,
            "line_end": 63
          },
          {
            "file": "SKILL.md",
            "line_start": 68,
            "line_end": 68
          },
          {
            "file": "SKILL.md",
            "line_start": 80,
            "line_end": 80
          },
          {
            "file": "SKILL.md",
            "line_start": 142,
            "line_end": 142
          },
          {
            "file": "SKILL.md",
            "line_start": 157,
            "line_end": 158
          },
          {
            "file": "SKILL.md",
            "line_start": 158,
            "line_end": 160
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 10,
            "line_end": 10
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 22
          },
          {
            "file": "SKILL.md",
            "line_start": 54,
            "line_end": 54
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 63,
            "line_end": 63
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 129,
            "line_end": 129
          },
          {
            "file": "SKILL.md",
            "line_start": 142,
            "line_end": 142
          },
          {
            "file": "SKILL.md",
            "line_start": 151,
            "line_end": 151
          },
          {
            "file": "SKILL.md",
            "line_start": 157,
            "line_end": 157
          },
          {
            "file": "SKILL.md",
            "line_start": 160,
            "line_end": 160
          }
        ]
      },
      {
        "factor": "env_access",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 76
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "blocker:references/kpi-definitions.md:13:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/kpi-definitions.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "| Organic search | Pages indexed | Valid indexed pages in Search Console | Close to intended indexab"
      },
      {
        "id": "blocker:references/report-templates.md:76:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/report-templates.md",
        "line_start": 76,
        "line_end": 76,
        "snippet": "| Indexation | Valid indexed / excluded errors | [values] | [values] | [change] | [status] | [action"
      },
      {
        "id": "blocker:references/report-templates.md:79:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/report-templates.md",
        "line_start": 79,
        "line_end": 79,
        "snippet": "| Schema | Valid / warning / error pages | [counts] | [counts] | [change] | [status] | [action] |"
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "One monitor skill, two modes. **`report`** builds a stakeholder-facing multi-metric snapshot of what"
      },
      {
        "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": "**Mode set:** `report` (multi-metric snapshot, absorbed from performance-reporter) · `alert` (forwar"
      },
      {
        "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": 36,
        "snippet": "```text"
      },
      {
        "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": 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": "Shortest valid invocation: `performance-monitor <domain>` (mode inferred). Output: **report** return"
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "**Expected output**: mode `report` → a delta-based multi-metric report/dashboard; mode `alert` → an "
      },
      {
        "id": "external_commands:SKILL.md:44:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 44,
        "line_end": 44,
        "snippet": "- **Reads**: prior baselines and current performance data. `report` reads current + prior-period met"
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 45,
        "line_end": 46,
        "snippet": "- **Writes**: a user-facing monitoring deliverable plus a reusable summary storable under `memory/mo"
      },
      {
        "id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 46,
        "line_end": 46,
        "snippet": "- **Promotes**: significant changes, confirmed anomalies, durable thresholds, and follow-up actions;"
      },
      {
        "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": "- `report`: each in-scope section (traffic, rankings, GEO, authority, backlinks, content) is present"
      },
      {
        "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": 54,
        "snippet": "- `alert`: each chosen alert category has a named trigger, threshold, and priority; a Critical/High/"
      },
      {
        "id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 54,
        "line_end": 54,
        "snippet": "> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill"
      },
      {
        "id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 63,
        "line_end": 63,
        "snippet": "**Zero-dependency measurement loop** (both modes): every reported change or fired alert should come "
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 68,
        "line_end": 68,
        "snippet": "- **Mode ambiguous** — the request fits neither past-tense (\"report on last month\") nor future-tense"
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 80,
        "snippet": "**Step 0 — Select mode.** Read `--mode` if given. Otherwise infer: past-tense / \"how did we do\" / \"月"
      },
      {
        "id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 142,
        "line_end": 142,
        "snippet": "Ask \"Save these results?\" If yes, write to `memory/monitoring/` using filename `YYYY-MM-DD-<topic>.m"
      },
      {
        "id": "external_commands:SKILL.md:157:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 157,
        "line_end": 158,
        "snippet": "- After **report** — a change needs ongoing monitoring → run this skill in `alert` mode. A section m"
      },
      {
        "id": "external_commands:SKILL.md:158:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 158,
        "line_end": 160,
        "snippet": "- After **alert** — a reporting cadence is requested → run this skill in `report` mode. Standalone a"
      },
      {
        "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\": \"seo-geo\", \"phase\": \"monitor"
      },
      {
        "id": "filesystem:SKILL.md:22:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 22,
        "snippet": "**Scope guard — what this skill does NOT do:** it does not compute the CORE-EEAT content score or ru"
      },
      {
        "id": "filesystem:SKILL.md:54:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 54,
        "line_end": 54,
        "snippet": "> Emit the standard shape from [skill-contract.md §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": "All integrations optional (see [CONNECTORS.md](../../../CONNECTORS.md)). Tier 1 (keyless) works for "
      },
      {
        "id": "filesystem:SKILL.md:63:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 63,
        "line_end": 63,
        "snippet": "**Zero-dependency measurement loop** (both modes): every reported change or fired alert should come "
      },
      {
        "id": "filesystem:SKILL.md:89:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 89,
        "snippet": "4. **Keyword Rankings** — position ranges, distribution change, top improvements/declines, SERP feat"
      },
      {
        "id": "filesystem:SKILL.md:129:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 129,
        "line_end": 129,
        "snippet": "A reported delta or a fired alert is only evidence if it beats a control over a **fixed readback win"
      },
      {
        "id": "filesystem:SKILL.md:142:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 142,
        "line_end": 142,
        "snippet": "Ask \"Save these results?\" If yes, write to `memory/monitoring/` using filename `YYYY-MM-DD-<topic>.m"
      },
      {
        "id": "filesystem:SKILL.md:151:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 151,
        "line_end": 151,
        "snippet": "- [Measurement & Attribution Protocol](../../../references/measurement-protocol.md) — readback windo"
      },
      {
        "id": "filesystem:SKILL.md:157:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL.md",
        "line_start": 157,
        "line_end": 157,
        "snippet": "- After **report** — a change needs ongoing monitoring → run this skill in `alert` mode. A section m"
      },
      {
        "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": "Termination: the visited-set and `max-depth: 3` rules from [skill-contract.md §Termination rules](.."
      },
      {
        "id": "env_access:SKILL.md:76:configuration-library",
        "category": "env_access",
        "severity": "low",
        "pattern": "Configuration library",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 76,
        "snippet": "- An alert category the user did not mention — leave it unconfigured; do not add alerts they did not"
      },
      {
        "id": "blocker:SKILL.md:38:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 38,
        "line_end": 38,
        "snippet": "Shortest valid invocation: `performance-monitor <domain>` (mode inferred). Output: **report** return"
      },
      {
        "id": "blocker:SKILL.md:76:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 76,
        "snippet": "- An alert category the user did not mention — leave it unconfigured; do not add alerts they did not"
      },
      {
        "id": "blocker:SKILL.md:80:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 80,
        "line_end": 80,
        "snippet": "**Step 0 — Select mode.** Read `--mode` if given. Otherwise infer: past-tense / \"how did we do\" / \"月"
      }
    ],
    "finding_verdicts": [
      {
        "id": "blocker:references/kpi-definitions.md:13:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line defines an SEO indexation KPI using Search Console. It does not inspect the host system or enumerate local resources."
      },
      {
        "id": "blocker:references/report-templates.md:76:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line is a report placeholder for indexed and excluded page counts. It contains no system discovery instruction."
      },
      {
        "id": "blocker:references/report-templates.md:79:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line requests schema validation counts for an SEO report. It does not perform system reconnaissance."
      },
      {
        "id": "external_commands:SKILL.md:18:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Backticks format the report and alert mode names in prose. No Ruby or shell command is present."
      },
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Backticks format two mode identifiers. The line describes behavior and does not execute a command."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This begins a fenced text block containing natural-language prompt examples. It contains no executable shell or Ruby code."
      },
      {
        "id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "This closes a Markdown text fence. It is formatting syntax, not backtick command substitution."
      },
      {
        "id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "Inline backticks document an invocation shape and storage path. The line does not instruct a shell to execute either string."
      },
      {
        "id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Inline backticks identify output modes and a storage directory. They are documentation labels without command execution."
      },
      {
        "id": "external_commands:SKILL.md:44:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line uses inline code formatting for mode names while describing input data. It contains no executable command."
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticked value is a scoped output directory described in prose. It is not shell substitution or an external command."
      },
      {
        "id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Backticks format two Markdown filenames in a storage policy. The line does not execute them."
      },
      {
        "id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticked report label is an inline mode name. The surrounding checklist contains no command."
      },
      {
        "id": "external_commands:SKILL.md:49:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticked alert label is an inline mode name. The line only defines completion criteria."
      },
      {
        "id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line contains inline mode labels and a Markdown link to documentation. Neither is an executable command."
      },
      {
        "id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.93,
        "reason": "The line explicitly directs agents to run a Python ledger command. Its unquoted domain placeholder could become unsafe if passed through a shell.",
        "severity": "medium"
      },
      {
        "id": "external_commands:SKILL.md:68:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Backticks format report and alert option names in a decision prompt. No external process is invoked."
      },
      {
        "id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line documents a mode option and mode values with inline code formatting. It does not execute a shell command."
      },
      {
        "id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "Backticks format a scoped directory and filename template. Writing occurs only after user confirmation, without shell substitution."
      },
      {
        "id": "external_commands:SKILL.md:157:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticked alert value is a mode label. The line contains workflow links, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:158:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticked report value is a mode label. The line describes routing behavior without executing a process."
      },
      {
        "id": "network:SKILL.md:10:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is repository homepage metadata. The skill does not request data from that URL."
      },
      {
        "id": "network:SKILL.md:13:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The URL is repeated inside package metadata as a homepage. It is not a network destination used by the workflow."
      },
      {
        "id": "filesystem:SKILL.md:22:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The parent-directory sequences are static Markdown links to related bundled skills. No user-controlled filesystem traversal occurs."
      },
      {
        "id": "filesystem:SKILL.md:54:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The sequence appears in a Markdown link to a shared contract document. It is not used as a runtime file path."
      },
      {
        "id": "filesystem:SKILL.md:58:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The sequence is a static relative link to connector documentation. It does not process user input or access arbitrary files."
      },
      {
        "id": "filesystem:SKILL.md:63:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Parent-directory sequences only link to bundled protocol and connector documentation. The executable example uses the plugin root variable instead."
      },
      {
        "id": "filesystem:SKILL.md:89:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The sequence is a Markdown link to the related rank-tracker skill. It does not traverse a user-selected path."
      },
      {
        "id": "filesystem:SKILL.md:129:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The sequence links to bundled measurement protocol documentation. It is static documentation navigation, not runtime traversal."
      },
      {
        "id": "filesystem:SKILL.md:142:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The parent sequence belongs to a static documentation link. The proposed write is scoped to memory/monitoring and requires user approval."
      },
      {
        "id": "filesystem:SKILL.md:151:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The sequence appears only in a Markdown reference to a bundled protocol file. No arbitrary file access is requested."
      },
      {
        "id": "filesystem:SKILL.md:157:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The parent-directory paths are static links to two related skills. They do not incorporate user-controlled path components."
      },
      {
        "id": "filesystem:SKILL.md:160:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The sequence is a Markdown link to shared termination rules. It is not used for filesystem traversal."
      },
      {
        "id": "env_access:SKILL.md:76:configuration-library",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line discusses unrequested alert categories. It does not read environment variables or use a configuration library."
      },
      {
        "id": "blocker:SKILL.md:38:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line describes invocation and output formats for a user-supplied domain. It does not inspect the local system."
      },
      {
        "id": "blocker:SKILL.md:76:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line limits configuration to categories requested by the user. It contains no system reconnaissance behavior."
      },
      {
        "id": "blocker:SKILL.md:80:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Reading the supplied mode option means parsing user arguments. It does not discover host configuration or system resources."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "**Zero-dependency measurement loop** (both modes): every reported change or fired alert should come ",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 63,
            "line_end": 63
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.93,
        "confidence_reasoning": "The line explicitly directs agents to run a Python ledger command. Its unquoted domain placeholder could become unsafe if passed through a shell."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 6,
    "total_lines": 651,
    "audit_model": "codex",
    "audited_at": "2026-07-12T13:27:49.209Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Monitor SEO Performance and Configure Alerts",
    "value_statement": "SEO teams struggle to compare performance consistently and detect meaningful declines. This skill creates source-labeled reports and threshold-based alert plans from supplied or connected data.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "SEO performance monitor",
      "SEO report",
      "SEO alerts",
      "GEO visibility",
      "ranking monitor",
      "traffic dashboard",
      "AI citation monitoring"
    ],
    "actual_capabilities": [
      "Infers report or alert mode from the request and asks for clarification when intent is ambiguous.",
      "Compares current and prior SEO or GEO metrics while labeling each value by source.",
      "Produces audience-focused reports covering traffic, rankings, authority, backlinks, content, and AI visibility.",
      "Configures alert thresholds, priorities, delivery routes, cooldowns, maintenance windows, and escalation paths.",
      "Applies fixed readback windows and control comparisons to classify observed outcomes.",
      "Offers to save reusable monitoring summaries in a scoped memory directory."
    ],
    "limitations": [
      "It cannot fetch current metrics unless compatible tools are connected or the user supplies data.",
      "It reports existing CITE and CORE-EEAT scores but does not calculate them.",
      "Reliable reports and alerts require comparison periods, baselines, or clearly labeled estimates.",
      "It proposes alert configurations but does not schedule or send notifications without external automation."
    ],
    "use_cases": [
      {
        "title": "Prepare Monthly Executive Reports",
        "description": "Compare current and prior SEO performance, summarize material changes, and assign prioritized actions with owners.",
        "target_user": "SEO manager"
      },
      {
        "title": "Design Early Warning Alerts",
        "description": "Set baseline-aware alerts for traffic, ranking, technical, backlink, competitor, and AI citation changes.",
        "target_user": "Growth marketer"
      },
      {
        "title": "Build Client Performance Reviews",
        "description": "Create audience-specific dashboards with source labels, missing-data notes, recommendations, and next-period goals.",
        "target_user": "SEO agency consultant"
      }
    ],
    "prompt_templates": [
      {
        "title": "Create a Basic Monthly Snapshot",
        "prompt": "Create an executive SEO report for [domain], comparing the last 30 days with the prior 30 days. Mark unavailable metrics clearly.",
        "scenario": "Use when supplied metrics need a concise monthly summary."
      },
      {
        "title": "Configure Traffic and Ranking Alerts",
        "prompt": "Configure traffic and ranking alerts for [domain] using my baseline data. Include thresholds, priorities, channels, cooldowns, and response plans.",
        "scenario": "Use when a team needs practical monitoring rules."
      },
      {
        "title": "Review Search and AI Visibility",
        "prompt": "Compare AI citations and search KPIs for [domain] across [periods]. Separate observed changes, plausible explanations, missing evidence, and recommended actions.",
        "scenario": "Use when SEO and GEO performance must be reviewed together."
      },
      {
        "title": "Evaluate a Controlled Readback",
        "prompt": "Evaluate [change] against [control] over [readback window]. Classify the result as Promote, Keep-testing, Rollback, or Unproven, with caveats and next-readback date.",
        "scenario": "Use for an advanced outcome review after a measured change."
      }
    ],
    "output_examples": [
      {
        "input": "Create an executive SEO report for example.com using the supplied monthly metrics.",
        "output": [
          "Overall status: Watch. Organic sessions fell 18 percent while conversions remained stable.",
          "Priority action: Review the three declining landing pages and assign an owner before the next readback.",
          "Data status: Rankings and AI citations were not supplied, so those sections remain not evaluated."
        ]
      },
      {
        "input": "Configure alerts for a mature site with stable weekly traffic.",
        "output": [
          "Critical traffic alert: Trigger after a 30 percent weekly decline against the trailing baseline.",
          "High ranking alert: Trigger when a priority keyword drops five positions.",
          "Route critical alerts immediately to email and Slack, with a 24-hour duplicate cooldown."
        ]
      },
      {
        "input": "Assess a content refresh after a 28-day readback period.",
        "output": [
          "Decision: Keep-testing. Organic clicks improved, but the gain did not exceed the control.",
          "Caveat: Conversion data is incomplete, so the business impact remains unproven.",
          "Next step: Continue measurement through day 56 and review the same primary metric."
        ]
      }
    ],
    "best_practices": [
      "Provide current and comparison-period data with source names and freshness dates.",
      "Use measured baselines and normal volatility when setting thresholds.",
      "Separate observed changes from explanations, recommendations, and follow-up investigations."
    ],
    "anti_patterns": [
      "Do not present estimated metrics as measured values.",
      "Do not configure alert categories that the user did not request.",
      "Do not claim causation from a simple before-and-after comparison."
    ],
    "faq": [
      {
        "question": "Can this skill collect SEO data automatically?",
        "answer": "Only when compatible connectors are available. Otherwise, provide analytics exports, Search Console data, ranking data, or KPI summaries."
      },
      {
        "question": "What is the difference between report and alert mode?",
        "answer": "Report mode summarizes past performance. Alert mode defines future thresholds, priorities, routing, and response plans."
      },
      {
        "question": "Does it calculate CITE or CORE-EEAT scores?",
        "answer": "No. It can report existing scores and trends, but specialized auditor skills must calculate them."
      },
      {
        "question": "What happens when required data is missing?",
        "answer": "The skill marks the section as not evaluated and continues without inventing metrics."
      },
      {
        "question": "Can it send alerts directly?",
        "answer": "It creates alert rules and routing plans. Actual delivery requires connected monitoring and notification systems."
      },
      {
        "question": "How does it reduce false alarms?",
        "answer": "It uses trailing baselines, fixed readback windows, cooldowns, maintenance windows, and threshold tuning based on observed volatility."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "alert-configuration-templates.md",
          "type": "file",
          "path": "references/alert-configuration-templates.md",
          "lines": 91
        },
        {
          "name": "alert-threshold-guide.md",
          "type": "file",
          "path": "references/alert-threshold-guide.md",
          "lines": 98
        },
        {
          "name": "kpi-definitions.md",
          "type": "file",
          "path": "references/kpi-definitions.md",
          "lines": 121
        },
        {
          "name": "report-output-templates.md",
          "type": "file",
          "path": "references/report-output-templates.md",
          "lines": 65
        },
        {
          "name": "report-templates.md",
          "type": "file",
          "path": "references/report-templates.md",
          "lines": 115
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 161
    }
  ]
}
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: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated 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: 196kUpdated Claude CodeCodexVerifiedInstall