Short video performance review
Agent Skills workflow for Chinese talking-head video operations, scripting, production, publishing preparation, and review.
npx -y skills add slalomboy/talking-head-video-suite --skill short-video-performance-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 21 days oldThe repository was created 21 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when comparable short-video samples need diagnosis across content, audience, conversion, and delivery metrics or a bounded next experiment.
SKILL.md
1.5 KB, 485 tokens by cl100k_base, as published. Nobody here has run it
Short Video Performance Review
核心原则
复盘连接内容指标和经营指标；观察可以立即记录，长期规则需要多个可比样本和明确采纳门。
触发与边界
用于周复盘、月复盘、异常诊断、素材回收和下一实验设计。不用一条视频自动改变定位、模板或团队长期规则。
方法
- 对齐样本的主题、受众、版本、时间窗、流量来源和指标口径。
- 分析
contentMetrics：停留、平均观看、留存、互动内容。 - 分析
audienceMetrics：来源、相关性、咨询质量和错误人群信号。 - 分析
conversionMetrics：点击、线索、成交、获客成本与贡献利润。 - 分析
deliveryMetrics：履约、退款、投诉、复购和承诺一致性。 - 记录观察；只有多个可比样本支持且通过
adoptionGate，才形成素材库、模板或规则候选。 - 每轮输出一个主要判断和一个
nextExperiment，避免同时改动全部变量。
输出契约
只写 metrics 和 nextActions：四层指标、观察、证据强度、可比样本、adoptionGate、候选更新与 nextExperiment。冲突和口径缺口进入 reviewItems。
常见错误
播放高即成功；互动等于购买；销售额等于利润；只看前端不看退款履约；从单次波动总结永久模板。
Gives 0 of the 12 instructions most review quality skills give in 485 tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-06
- ask questions one at a timein 82 of 1048, across 54 files
- provide a recommended answer for each questionin 73 of 1048, across 45 files
- explore the codebase instead of asking answerable questionsin 66 of 1048, across 37 files
- resolve dependencies between decisions one-by-onein 42 of 1048, across 15 files
- interview the user relentlessly about the planin 39 of 1048, across 12 files
- order findings by severityin 29 of 1048
- resolve each branch of the decision treein 28 of 1048, across 5 files
- run a grilling sessionin 26 of 1048, across 5 files
- update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 9 files
- propose precise canonical terms for vague languagein 25 of 1048, across 6 files
- create documentation files lazilyin 24 of 1048, across 5 files
- use the domain-modeling skillin 22 of 1048, across 3 files
Said here and by no other author read
- align samples before comparing metrics
- analyse content metrics
- analyse audience metrics
- analyse conversion metrics
- analyse delivery metrics
- record observations without forming rules
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.