# Performance Reporter > Use when the user asks to "generate an SEO report" or "出月报"; builds multi-metric stakeholder reports and dashboards spanning traffic, rankings, authority, and content progress. Not for raw ranking deltas — use rank-tracker. SEO报告/绩效仪表盘 - **Type:** Skill - **Install:** `agentstack add skill-aaron-he-zhu-aaron-marketing-skills-performance-reporter` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [aaron-he-zhu](https://agentstack.voostack.com/s/aaron-he-zhu) - **Installs:** 0 - **Category:** [Search](https://agentstack.voostack.com/c/search) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [aaron-he-zhu](https://github.com/aaron-he-zhu) - **Source:** https://github.com/aaron-he-zhu/aaron-marketing-skills/tree/main/monitor/performance-reporter ## Install ```sh agentstack add skill-aaron-he-zhu-aaron-marketing-skills-performance-reporter ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Performance Reporter Aggregates SEO/GEO data, builds stakeholder reports, benchmarks goals/competitors, calculates ROI, and turns deltas into prioritized recommendations. ## Quick Start ```text Create an SEO performance report for [domain] for [time period] Generate an executive summary of SEO performance for [month/quarter] Create a GEO visibility report for [domain] Generate a content performance report ``` ## Skill Contract **Expected output**: a delta summary, alert/report output, and a short handoff summary ready for `memory/monitoring/`. - **Reads**: current and prior-period metrics across traffic/rankings/authority/content, report audience, date range, and any user-provided or tool data. - **Writes**: a user-facing monitoring deliverable plus a reusable summary that can be stored under `memory/monitoring/`. - **Promotes**: significant changes, confirmed anomalies, follow-up actions, and pending decisions to `memory/open-loops.md`. - **Done when**: each in-scope section (traffic, rankings, GEO, authority, backlinks, content) is present or marked "Not yet evaluated"; every metric is source-tagged and compared to the prior period; and recommendations carry owner, priority, and expected impact. - **Primary next skill**: use the `Next Best Skill` below when a change needs action. ### Handoff Summary > Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../references/skill-contract.md). ## Data Sources All integrations optional (see [CONNECTORS.md](../../CONNECTORS.md)). With tools connected, aggregates traffic from ~~analytics, search data from ~~search console, rankings/backlinks from ~~SEO tool, and AI visibility from ~~AI monitor. Without tools, ask user for analytics exports, Search Console data, ranking data, and KPIs. **Zero-dependency measurement loop**: every reported change should come from a computed delta, not an eyeballed estimate. Store each reporting period's KPIs and let the ledger compute period-over-period movement: `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/ledger.py" record --source report --data '{"sessions": ..., "clicks": ..., ...}'`, then `ledger.py diff --source report` for the period delta and `ledger.py trend --source report --field ` for the trend line. Label every figure Measured / User-provided / Estimated accordingly, and attribute outcome movements against a control rather than to the latest change by default — see [references/measurement-protocol.md](../../references/measurement-protocol.md). See [scripts/connectors/README.md](../../scripts/connectors/README.md). ## Decision Gates **Stop and ask the user when:** - No reporting period or comparison period can be determined and none is in context — offer: (1) last 30 days vs prior 30, (2) last calendar month vs prior month, (3) a custom range. A period comparison is required, not optional. **Continue silently (never stop for):** - A section's source data is missing — mark that section "Not yet evaluated" and proceed; do not fabricate the metric. - Audience not stated — default to the executive template and note the assumption. ## Instructions When a user requests a performance report, use [Report Output Templates](references/report-output-templates.md) and cover: 1. **Define Report Parameters** — Domain, period, comparison period, report type, audience, focus areas, and data freshness. 2. **Create Executive Summary** — Overall rating, wins, watch areas, required actions, metrics at a glance (traffic, rankings, conversions, DA/authority, AI citations), and SEO ROI; tag each metric Measured / User-provided / Estimated. 3. **Report Organic Traffic** — Sessions, users, pageviews, engagement/bounce, trend visualization, source/device split, top pages, each figure source-tagged. 4. **Report Keyword Rankings** — Position ranges, distribution change, top improvements/declines, SERP features. For raw position-by-position deltas, defer to rank-tracker rather than recomputing here. 5. **Report GEO/AI Performance** — AI citation overview, citations by topic, GEO wins, and optimization opportunities. 6. **Report Domain Authority (CITE)** — Include CITE dimension scores and veto status when available; otherwise mark "Not yet evaluated." 7. **Report Content Quality (CORE-EEAT)** — Include average scores and trends when available; otherwise mark "Not yet evaluated." 8. **Report Backlinks** — Link profile summary, acquisition trend, notable links, competitive position. 9. **Report Content Performance** — Publishing summary, top content, content needing attention, and content ROI. 10. **Generate Recommendations** — Immediate, short-term, and long-term actions with priority, owner, expected impact, and next-period goals. 11. **Compile Full Report** — Add table of contents, appendix, data sources, methodology, and glossary. Label every metric **Measured** (tool/export), **User-provided**, or **Estimated** (model inference); never present an estimate as measured; if a required metric is unavailable, mark it N/A — do not invent it. Likewise separate an **observed change** from a **plausible explanation** (corroborate before stating it as the cause), an **optimization opportunity**, and **follow-up** needing crawl/SERP/rank/audit — never report an unverified explanation as a confirmed cause. ## Example Sample output: an executive summary with overall status, metrics-at-a-glance for traffic/rankings/conversions/authority/AI citations, SEO ROI, and immediate/month/quarter actions with owners and dates. ## Save Results Ask "Save these results?" If yes, write to `memory/monitoring/` — see [Skill Contract](../../references/skill-contract.md) §Save Results Template. ## Reference Materials - [Report Output Templates](references/report-output-templates.md) — Compact starter blocks for all 11 report sections - [KPI Definitions](references/kpi-definitions.md) — SEO/GEO metric definitions with benchmarks, thresholds, trend analysis, and attribution guidance - [Report Templates by Audience](references/report-templates.md) — Copy-ready templates for executive, marketing, technical, and client audiences ## Next Best Skill Recurring monitoring needed → [alert-manager](../alert-manager/SKILL.md) — turn reporting insights into ongoing monitoring rules. One-off report → Terminal. Visited-set rule applies per [Skill Contract](../../references/skill-contract.md). ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [aaron-he-zhu](https://github.com/aaron-he-zhu) - **Source:** [aaron-he-zhu/aaron-marketing-skills](https://github.com/aaron-he-zhu/aaron-marketing-skills) - **License:** Apache-2.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-aaron-he-zhu-aaron-marketing-skills-performance-reporter - Seller: https://agentstack.voostack.com/s/aaron-he-zhu - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.