Back to Details

performance-analyzer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Performance Analyzer

表现分析工具

Analyze influencer campaign performance past surface metrics — score results vs target/benchmark, rank platforms/creators/content, read engagement quality and sentiment, attribute conversions, and write ranked learnings.
Cross-discipline (paid ads): this is also the cross-channel paid-ads scorecard/anomaly lens — account-wide metric rollups vs target/benchmark that feed ad-test-designer (what to test) and paid-measurement-loop (what to read back). Save paid runs under 
memory/ad/performance-analyzer/
.
深入分析达人营销活动的表现，而非停留在表面指标——将结果与目标/基准对比打分，对平台/创作者/内容进行排名，分析互动质量与情感倾向，进行转化归因，并撰写排序后的洞察结论。
跨领域（付费广告）： 这也是跨渠道的paid-ads评分卡/异常分析视角——全账户指标汇总与目标/基准对比，为ad-test-designer（测试方向）和paid-measurement-loop（复盘内容）提供数据支撑。将付费广告运行数据保存至
memory/ad/performance-analyzer/
。

Quick Start

快速开始

Analyze performance of [campaign name] influencer campaign
Compare creators within one campaign:
Compare performance of these influencers from [campaign]: @handle1, @handle2, @handle3
Analyze performance of [campaign name] influencer campaign
对比同一活动内的创作者：
Compare performance of these influencers from [campaign]: @handle1, @handle2, @handle3

Skill Contract

技能协议

  • Reads: campaign name and date range; native platform analytics (reach, views, engagement); influencer-supplied reports or screenshots; website/GA traffic and conversion data; sales and promo-code redemption data; targets and benchmarks if the user has them; per-creator performance baselines from 
    memory/creators/<handle-slug>.md
    (creator-registry roster records) when present.
  • Writes: a performance analysis to 
    memory/influencer/performance-analyzer/YYYY-MM-DD-<campaign>.md
    covering core-metric scorecards, platform/influencer/content rankings, engagement-quality and sentiment reads, conversion attribution, and ranked learnings.
  • Promotes: durable facts (top-performing creators, winning formats, platform ROI splits, roster renew/drop calls) to 
    memory/hot-cache.md
    .
  • Done when:
    • Core metrics are scored against target and benchmark with a performance verdict.
    • Top and bottom performers are ranked with reasons, and content patterns that worked are named.
    • Conversions are attributed by method (promo code / UTM / direct / estimated) and 3-5 learnings are written.
  • Primary next skill: roi-calculator — turn measured performance into dollar-level return.
  • 读取：活动名称和日期范围；原生平台分析数据（触达量、浏览量、互动量）；达人提供的报告或截图；网站/GA流量与转化数据；销售与促销码兑换数据；若用户提供则获取目标与基准数据；当存在时，从
    memory/creators/<handle-slug>.md
    （creator-registry roster记录）读取每位创作者的表现基线。
  • 写入：将表现分析结果保存至
    memory/influencer/performance-analyzer/YYYY-MM-DD-<campaign>.md
    ，内容涵盖核心指标评分卡、平台/达人/内容排名、互动质量与情感分析、转化归因，以及排序后的洞察结论。
  • 推送：将持久化事实（表现最佳的创作者、成功的内容形式、平台ROI拆分、创作者续约/淘汰建议）推送至
    memory/hot-cache.md
    。
  • 完成条件：
    • 核心指标已与目标及基准对比打分，并给出表现 verdict。
    • 已排名表现最佳与最差的对象并说明原因，明确有效的内容模式。
    • 已按方法（促销码/UTM/直接访问/估算）进行转化归因，并撰写3-5条洞察结论。
  • 主要后续技能：roi-calculator — 将已测量的表现转化为美元级别的回报计算。

Handoff Summary

交接摘要

Emit the standard shape from skill-contract.md §Handoff Summary Format.
按照skill-contract.md §Handoff Summary Format生成标准格式的交接内容。

Data Sources

数据源

This family needs no live integrations (Tier 1). The skill runs entirely on inputs you provide — paste platform exports, influencer report screenshots, GA numbers, and promo-code redemption counts, and it builds the full analysis. Ask the user for whatever is missing rather than blocking.
Where a connector could speed the work, the skill marks it with a 
~~
placeholder:
  • ~~social platform analytics
    — native reach/engagement/video metrics per post.
  • ~~web analytics
    — site traffic, click-through, and on-site conversion data.
Measured YouTube post-performance (free key): when campaign content lives on YouTube, 
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py" videos @creator --limit 20
pulls the actual per-video views/likes/comments for the campaign window — Measured platform metrics without waiting for the creator's screenshot export. Keep both labels honest: API numbers are Measured, creator-supplied numbers are User-provided, and the two can legitimately disagree (display rounding, timing). Free 
YOUTUBE_API_KEY
. See scripts/connectors/README.md.
  • ~~ecommerce / sales platform
    — revenue, orders, AOV, promo-code redemptions.
  • ~~influencer database
    — historical creator benchmarks for comparison.
No placeholder is required to run. See CONNECTORS.md for the verified free/keyless data recipe per category.
该技能无需实时集成（Tier 1）。完全基于你提供的输入运行——粘贴平台导出数据、达人报告截图、GA数据和促销码兑换数量，即可生成完整分析。若缺少必要数据，请向用户索取而非停滞。
在可通过连接器加速工作的场景下，技能会用
~~
标记占位符：
  • ~~social platform analytics
    — 单帖的原生触达/互动/视频指标。
  • ~~web analytics
    — 网站流量、点击率和站内转化数据。
YouTube帖文实测表现（免费密钥）：当活动内容发布在YouTube时，执行
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/youtube.py" videos @creator --limit 20
可拉取活动周期内每条视频的实际浏览量/点赞数/评论数——无需等待创作者提供截图导出，即可获取实测平台指标。请如实标记两类数据：API获取的为实测数据，用户提供的为用户提交数据，两者可能存在合理差异（显示四舍五入、统计时间差）。免费
YOUTUBE_API_KEY
，详见scripts/connectors/README.md。
  • ~~ecommerce / sales platform
    — 营收、订单数、客单价、促销码兑换量。
  • ~~influencer database
    — 用于对比的创作者历史基准数据。
无需占位符即可运行。每个连接器类别的免费/无密钥验证数据方案详见CONNECTORS.md。

Instructions

操作步骤

Work the steps in order. Each fill-in template lives in references/analysis-templates.md — copy the matching block and populate it.
  1. Gather performance data — log campaign/period/influencers/platforms and the available sources (native analytics, influencer reports, web analytics, sales, promo codes). Template: step 1.
  2. Analyze core metrics — score reach, impressions, engagements, ER, video views, clicks, promo uses, conversions, and revenue against target and benchmark; assign a performance verdict and call out over/underperformers. Template: step 2.
  3. Analyze by platform — compare platforms on reach/ER/clicks/conversions/CPA, name the best and worst with reasons, and break out platform-specific formats (IG feed/Reels/Stories, TikTok watch time/completion). Template: step 3.
  4. Analyze by influencer — rank creators on reach/ER/conversions/ROI, deep-dive top performers (why they won, content anatomy, renew call), and explain underperformers. Template: step 4.
  5. Content performance analysis — rank top content, compare formats and themes, and name the winning hook/messaging/visual patterns. Template: step 5.
  6. Engagement quality analysis — break engagement by type and intent, run comment sentiment, surface purchase-intent signals, and score quality /10. Template: step 6.
  7. Conversion & attribution analysis — draw the funnel, score conversion metrics vs benchmark, attribute by method (promo / UTM / direct / estimated), and table promo-code performance. Template: step 7.
  8. Generate insights & recommendations — write the top-5 learnings, what worked / what didn't, optimization opportunities, roster renew/drop calls, and future-campaign guidance. Template: step 8.
Before naming any creator/format/platform a real winner, clear the significance bar in measurement-protocol.md — otherwise mark it Keep-testing. When a structured score is needed, apply per-dimension STAR analysis (Suitability/Trust/Appeal/Return dimension reads) from star-benchmark.md, and hand the measured inputs to roi-calculator for the measured Return (R) evidence — this skill contributes the inputs but does not compute the SQS (the creator-content-auditor gate does).
按顺序执行以下步骤。每个填充模板位于references/analysis-templates.md中——复制对应模块并填充内容。
  1. 收集表现数据 — 记录活动/周期/达人/平台及可用数据源（原生分析、达人报告、网站分析、销售数据、促销码）。模板：步骤1。
  2. 分析核心指标 — 将触达量、曝光量、互动量、互动率（ER）、视频浏览量、点击量、促销码使用量、转化量和营收与目标及基准对比打分；给出表现 verdict，指出表现超出/未达预期的对象。模板：步骤2。
  3. 按平台分析 — 对比各平台的触达量/互动率/点击量/转化量/单次转化成本（CPA），说明最佳与最差平台的原因，并细分平台特定内容形式（IG动态/Reels/快拍、TikTok观看时长/完播率）。模板：步骤3。
  4. 按达人分析 — 按触达量/互动率/转化量/ROI对创作者排名，深入分析表现最佳者（成功原因、内容结构、续约建议），并解释表现不佳者的问题。模板：步骤4。
  5. 内容表现分析 — 排名优质内容，对比内容形式与主题，明确成功的钩子/ messaging/视觉模式。模板：步骤5。
  6. 互动质量分析 — 按类型与意图拆分互动量，进行评论情感分析，挖掘购买意向信号，为互动质量打分（满分10）。模板：步骤6。
  7. 转化与归因分析 — 绘制转化漏斗，将转化指标与基准对比打分，按方法（促销码/UTM/直接访问/估算）进行转化归因，并制作促销码表现表格。模板：步骤7。
  8. 生成洞察与建议 — 撰写Top5洞察结论、成功/失败点、优化机会、创作者续约/淘汰建议，以及未来活动指导。模板：步骤8。
在将任何创作者/形式/平台定为真正的成功案例前，请符合measurement-protocol.md中的显著性标准——否则标记为「持续测试」。当需要结构化评分时，应用star-benchmark.md中的STAR维度分析（适配性/可信度/吸引力/回报维度评估），并将实测数据提交给roi-calculator获取实测回报（R）证据——本技能提供输入但不计算SQS（由creator-content-auditor gate完成）。

Example

示例

User: "Analyze performance of our summer skincare campaign with 10 influencers"
Output (abridged — full version in references/analysis-templates.md):
markdown
undefined
用户：「分析我们与10位达人合作的夏季护肤活动表现」
输出（节选——完整版本见references/analysis-templates.md）：
markdown
undefined

Summer Skincare Campaign Performance Analysis — Above Average (7.5/10)

夏季护肤活动表现分析——良好（7.5/10）

MetricResultTargetStatus
Total Reach2.4M2M✅ +20%
Engagement Rate4.2%3.5%✅ +20%
Conversions1,8472,000⚠️ -8%
Revenue$142,500$150,000⚠️ -5%
ROI2.8:13:1⚠️ -7%
Top 3: @skincaresarah (ROI 4.2:1), @glowwithgrace (ER 6.8%), @beautyreview (reach/$). Key learning: TikTok beat Instagram (3.5:1 vs 2.1:1 ROI) — shift 20% of IG budget to TikTok. Recommendation: Renew top 5; replace bottom 2 with TikTok-native creators.
undefined
指标结果目标状态
总触达量240万200万✅ +20%
互动率4.2%3.5%✅ +20%
转化量1,8472,000⚠️ -8%
营收$142,500$150,000⚠️ -5%
ROI2.8:13:1⚠️ -7%
Top3达人：@skincaresarah（ROI 4.2:1）、@glowwithgrace（互动率6.8%）、@beautyreview（单位成本触达量）。 核心洞察：TikTok表现优于Instagram（ROI 3.5:1 vs 2.1:1）——将20%的IG预算转移至TikTok。 建议：续约Top5达人；替换后2位达人，选用TikTok原生创作者。
undefined

Reference Materials

参考资料

  • references/analysis-templates.md — the eight fill-in step templates plus the full worked example.
  • skill-contract.md — shared contract and handoff format.
  • state-model.md — memory tiers and save-path conventions.
  • CONNECTORS.md — verified free/keyless data recipes per connector category.
  • measurement-protocol.md — preregistered readback windows, outcome unit, alpha, practical-effect boundary, multiplicity/sequential policy, guardrails, and decision owner. Report statistical and practical flags separately; use 
    experiment.py
    for deterministic 
    Calculated
    evidence, and never substitute a universal p-value/lift rule or attribute a business action to the helper.
  • The STAR benchmark at references/star-benchmark.md — scoring architecture when a structured score is needed.
  • Sibling skills: roi-calculator, report-generator, fit-scorer, campaign-planner.
  • references/analysis-templates.md — 8个填充式步骤模板及完整示例。
  • skill-contract.md — 通用协议与交接格式。
  • state-model.md — 内存层级与存储路径规范。
  • CONNECTORS.md — 各连接器类别的免费/无密钥验证数据方案。
  • measurement-protocol.md — 预注册复盘窗口、结果单位、显著性水平、实际影响边界、多重/序贯检验策略、防护规则及决策负责人。分别报告统计与实际标记；使用
    experiment.py
    获取确定性「计算得出」的证据，绝不能用通用p值/提升规则替代，也不能将业务行动归因于辅助工具。
  • references/star-benchmark.md中的STAR基准——需要结构化评分时的评分架构。
  • 关联技能：roi-calculator、report-generator、fit-scorer、campaign-planner。

Next Best Skill

推荐后续技能

Primary: roi-calculator — convert measured performance into dollar-level ROI, cost-per-result, and payback math.
Alternates (same Report family):
  • report-generator — package the analysis into a formal stakeholder report.
  • fit-scorer — feed proven performers back into creator scoring for the next round.
Termination note: Maintain a visited-set. If a skill has already been invoked this session, stop and report chain-complete rather than re-running it. Cap the chain at max-depth 3 hops; if results are inconclusive after that, surface the open loops to the user instead of continuing.
主要推荐：roi-calculator — 将实测表现转化为美元级ROI、单位结果成本与回报周期计算。
备选推荐（同属报告类）：
  • report-generator — 将分析结果整理为正式的利益相关者报告。
  • fit-scorer — 将表现优异的创作者反馈至创作者评分系统，用于下一轮合作筛选。
终止说明：维护已访问技能集合。若某技能在本次会话中已被调用，停止执行并报告流程完成，避免重复运行。流程最大深度限制为3步；若3步后结果仍不明确，向用户反馈未解决的问题而非继续执行。