creator-discovery-router
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseCreator Discovery Router
创作者挖掘路由
Use this skill when the user wants to:
- find creators or influencers for outreach
- shortlist KOL / KOC candidates
- find mid-tier or micro creators in a niche
- find creators under follower constraints such as
5k-10k - find creators by audience fit, not only by topic keywords
- compare discovery routes across TikTok, Instagram, and X
This skill is a routing layer. It should not be the primary collector.
It decides:
- what kind of discovery problem this is
- which platform skill should collect first
- whether to start from handles, content, or creator graph expansion
- when to hand off to
skills/50-publishing/creator-outreach
Follow shared release-shell and research rules in:
- release-shell rules
postplus-shared - research preferences
postplus-shared
当用户有以下需求时,可使用本技能:
- 寻找可进行触达的创作者或网红
- 筛选KOL/KOC候选人
- 寻找垂直领域的中腰部或尾部创作者
- 寻找符合粉丝量级约束(如)的创作者
5k-10k - 基于受众适配性而非仅话题关键词寻找创作者
- 对比TikTok、Instagram和X平台的挖掘路径
本技能是一个路由层,不应作为主要的采集工具。
它会决定:
- 当前属于哪种类型的挖掘需求
- 应优先调用哪个平台技能进行采集
- 应从账号ID(handles)、内容还是创作者图谱拓展入手
- 何时将任务转交给
skills/50-publishing/creator-outreach
请遵循以下共享发布框架和调研规则:
- 发布框架规则
postplus-shared - 调研偏好
postplus-shared
Execution Rules
执行规则
Inside the product-shell runtime, keep this skill narrow and fast:
- this skill is route selection only, not a collection workflow
- do not enter plan mode
- do not spawn Agent/Task subagents
- do not use just to manage simple routing work
TodoWrite - do not use or any other discovery step to search for this skill's own reference files
Glob - do not use Bash, ,
ls,find, or similar shell exploration to inspect skill directories or referencescat - read only the directly relevant reference files listed in this skill with the tool
Read - treat the reference list in this file as explicit. If you need one reference, read that exact file path directly
- after choosing the route, either:
- explain the route briefly in user-facing language and hand off to the downstream platform skill
- or ask one short clarification question if the route is genuinely ambiguous
- do not end the turn immediately after only reading a reference file
- do not stop at route diagnosis; continue into the downstream skill in the same turn whenever the route is already clear
If the request already clearly maps to one route, do not stop for extra exploration.
在产品框架运行时,需保持本技能的专注性和高效性:
- 本技能仅负责路由选择,不参与采集工作流
- 不要进入计划模式
- 不要生成Agent/Task子代理
- 不要仅为管理简单路由工作而使用
TodoWrite - 不要使用或其他挖掘步骤搜索本技能自身的参考文件
Glob - 不要使用Bash、、
ls、find或类似Shell命令浏览技能目录或参考内容cat - 仅使用工具读取本技能中列出的直接相关参考文件
Read - 将本文件中的参考列表视为明确要求。若需要某个参考文件,直接读取对应的准确文件路径
- 选择路由后,需执行以下操作之一:
- 用用户易懂的语言简要解释路由方案,然后将任务转交给下游平台技能
- 若路由存在明确歧义,提出一个简短的澄清问题
- 不要仅读取参考文件后就立即结束当前轮次
- 不要仅停留在路由诊断阶段;只要路由明确,就在同一轮次进入下游技能
如果请求已明确对应某一路由,无需额外探索。
Same-Turn Handoff Rule
同轮次转交规则
For a clear creator-discovery request, this skill must complete three things in the same turn:
- normalize the request into a brief internally
- choose the discovery route
- hand off to the downstream platform skill
Do not stop after step 1 or step 2.
If the request already names a platform and the route is clear, do not return a route-only answer.
对于明确的创作者挖掘请求,本技能必须在同一轮次完成三件事:
- 内部将请求标准化为简短任务简报
- 选择挖掘路由
- 将任务转交给下游平台技能
不要在步骤1或步骤2后停止。
如果请求已指定平台且路由明确,不要仅返回路由方案。
Default Handoff For TikTok Discovery
TikTok挖掘默认转交规则
When the request is about finding TikTok creators/KOLs with topical fit plus a follower-band preference:
- default to
content-first - explain the plan in plain business language
- hand off directly to in the same turn
skills/20-research/tiktok-research
For requests like:
找 20 个 TikTok 护肤仪 KOL,优先微中腰部账号找 TikTok 上适合做合作的美妆仪器达人
do not pause after reading . Route to immediately unless a missing detail would genuinely change the route.
Do not treat a missing local reference file as a reason to stop or fail this handoff.
If the route is already clear from the user request, skip extra reference reads and continue into .
brief-schema.mdskills/20-research/tiktok-researchskills/20-research/tiktok-research当请求为寻找符合主题适配性且有粉丝量级偏好的TikTok创作者/KOL时:
- 默认采用模式
content-first - 用通俗的业务语言解释方案
- 同一轮次直接将任务转交给
skills/20-research/tiktok-research
对于以下类型的请求:
找 20 个 TikTok 护肤仪 KOL,优先微中腰部账号找 TikTok 上适合做合作的美妆仪器达人
读取后无需停顿。除非缺失的细节会真正改变路由,否则立即将任务路由至。
不要将缺失本地参考文件作为停止或转交失败的理由。
如果从用户请求中已明确路由,跳过额外的参考文件读取,直接进入。
brief-schema.mdskills/20-research/tiktok-researchskills/20-research/tiktok-researchUser-Facing Explanation Rule
面向用户的解释规则
When explaining the plan to the user before collection, do not expose internal route labels such as:
handle-firstcontent-firstgraph-firstmixed
Use business language that a marketer can understand.
Good examples:
- "我会先从最近真的在发这类内容的人里找,再补他们的主页和联系方式。"
- "我会先从竞品已经合作过的人和相关内容里拉一批候选,再筛掉不适合联系的账号。"
- "我会先用你现有的达人名单补资料,再按内容、互动和合作价值做一轮筛选。"
- "如果平台后台已经有达人池,我会先用那个做第一轮过滤,再补公开资料。"
Avoid explanations like:
- "我会先走 content-first"
- "这次更适合 graph-first"
- "我准备 mixed route"
Internal route labels are for system reasoning, not for user-facing communication.
Read these references before implementation:
- research preferences
postplus-shared skills/10-routing/creator-discovery-router/references/brief-schema.mdskills/10-routing/creator-discovery-router/references/routing-modes.mdskills/10-routing/creator-discovery-router/references/iteration-loop.mdskills/10-routing/creator-discovery-router/references/candidate-schema.mdskills/10-routing/creator-discovery-router/references/instagram-candidate-mapping.mdskills/10-routing/creator-discovery-router/references/x-candidate-mapping.md
在采集前向用户解释方案时,不要暴露内部路由标签,例如:
handle-firstcontent-firstgraph-firstmixed
使用营销人员能理解的业务语言。
正面示例:
- "我会先从最近发布这类内容的创作者中筛选,再补充他们的主页信息和联系方式。"
- "我会先从竞品已合作的创作者及相关内容中筛选一批候选人,再剔除不适合联系的账号。"
- "我会先用你现有的达人名单补充资料,再按内容、互动数据和合作价值进行一轮筛选。"
- "如果平台后台已有达人池,我会先用它进行第一轮过滤,再补充公开资料。"
避免以下类型的解释:
- "我会先走 content-first"
- "这次更适合 graph-first"
- "我准备 mixed route"
内部路由标签仅用于系统推理,不用于面向用户的沟通。
在实施前请阅读以下参考文件:
- 调研偏好
postplus-shared skills/10-routing/creator-discovery-router/references/brief-schema.mdskills/10-routing/creator-discovery-router/references/routing-modes.mdskills/10-routing/creator-discovery-router/references/iteration-loop.mdskills/10-routing/creator-discovery-router/references/candidate-schema.mdskills/10-routing/creator-discovery-router/references/instagram-candidate-mapping.mdskills/10-routing/creator-discovery-router/references/x-candidate-mapping.md
Core Rule
核心规则
Do not treat all "find creators" requests as keyword-based profile search.
First extract the real constraints:
- platform
- follower range
- recall range
- topic or niche
- audience
- geo or language
- creator type
- recency / activity
- contactability
Then choose the route.
Default assumption:
- do not use the user's target follower band as the first-pass recall band when the platform search is noisy
- use a wider recall band first, then tighten in shortlist scoring
不要将所有「寻找创作者」的请求都视为基于关键词的主页搜索。
首先提取真实约束条件:
- 平台
- 粉丝量级范围
- 召回范围
- 话题或垂直领域
- 受众群体
- 地域或语言
- 创作者类型
- 活跃度/近期发布情况
- 可触达性
然后选择路由。
默认假设:
- 当平台搜索结果噪音较大时,不要将用户指定的目标粉丝量级范围作为首轮召回范围
- 先采用更宽泛的召回范围,然后在候选名单评分阶段缩小范围
Discovery Modes
挖掘模式
handle-first
handle-firsthandle-first
handle-firstUse when the user already has:
- seed creators
- competitor handles
- account usernames
- brand watchlists
Route:
- collect profiles from platform skills
- enrich recent content if needed
- rank and shortlist
- hand off to if partnership prep is needed
creator-outreach
当用户已有以下资源时使用:
- 种子创作者
- 竞品账号ID
- 账号用户名
- 品牌监测名单
路由流程:
- 从平台技能采集主页信息
- 必要时补充近期内容
- 排序并筛选候选名单
- 若需要合作准备,将任务转交给
creator-outreach
content-first
content-firstcontent-first
content-firstUse when the user wants:
- creators in a niche
- creators under a follower band
- real creators who are actively posting a topic
- partnership candidates based on what they post, not only what they claim in bio
Route:
- collect topic-relevant videos / posts / reels first
- extract authors from the content set
- enrich author profiles
- classify creator type
- filter by follower range and creator fit
- shortlist and hand off
This should be the default when the user asks for combinations like:
5k-10k AI tools creatorssmall study creators who post productivity workflowsmid-tier creators with overseas student audiences
当用户有以下需求时使用:
- 垂直领域的创作者
- 符合特定粉丝量级范围的创作者
- 持续发布特定话题内容的真实创作者
- 基于发布内容而非仅主页简介筛选合作候选人
路由流程:
- 优先采集与话题相关的视频/帖子/短视频内容
- 从内容集中提取作者信息
- 补充作者主页信息
- 分类创作者类型
- 按粉丝量级范围和合作适配性筛选
- 筛选候选名单并转交任务
当用户提出以下组合需求时,默认采用此模式:
5k-10k AI tools creatorssmall study creators who post productivity workflowsmid-tier creators with overseas student audiences
graph-first
graph-firstgraph-first
graph-firstUse when the best creators are unlikely to be found by simple search ranking.
Examples:
- micro creators
- local-language creators
- creators in a narrow subculture
- creators around a specific seed account or hashtag cluster
Route:
- start from one or more seed creators, hashtags, or posts
- expand through related accounts, tagged mentions, repeated collaborators, or creator clusters
- enrich candidate profiles
- filter and shortlist
当难以通过简单搜索排名找到优质创作者时使用。
示例场景:
- 尾部创作者
- 本地语言创作者
- 小众亚文化领域的创作者
- 特定种子账号或话题标签集群周边的创作者
路由流程:
- 从一个或多个种子创作者、话题标签或帖子入手
- 通过相关账号、提及标签、重复合作者或创作者集群进行拓展
- 补充候选人主页信息
- 筛选并生成候选名单
mixed
mixedmixed
mixedUse when discovery needs multiple passes.
Example:
- content-first to get real active creators
- graph-first to expand around the best seeds
- handle-first to enrich the final shortlist
当挖掘需要多轮次操作时使用。
示例流程:
- 采用content-first模式获取真实活跃创作者
- 采用graph-first模式围绕优质种子创作者拓展
- 采用handle-first模式补充最终候选名单信息
Routing Heuristics
路由启发规则
If the user strongly cares about :
follower range- do not default to keyword-only profile search
- prefer or
content-firstgraph-first - widen recall before tightening shortlist
If the user strongly cares about :
content relevance- collect content before ranking creators
If the user strongly cares about :
audience fit- do not trust bios alone
- use recent content patterns, language, and repeated framing as evidence
If the user strongly cares about :
creator type- classify candidates before final shortlist
- separate:
individual creatorbrand/product accounteducator/consultantaggregator
If the user already has seeds:
- use
handle-first
If the user wants contact-ready leads:
- collect first
- enrich second
- score third
- only then use
creator-outreach
如果用户非常关注:
粉丝量级范围- 不要默认采用仅基于关键词的主页搜索
- 优先选择或
content-first模式graph-first - 先扩大召回范围,再缩小候选名单
如果用户非常关注:
内容相关性- 在对创作者排序前先采集内容
如果用户非常关注:
受众适配性- 不要仅信任主页简介
- 将近期内容模式、语言风格和重复主题作为判断依据
如果用户非常关注:
创作者类型- 在最终筛选候选名单前对候选人进行分类
- 区分以下类型:
- (个人创作者)
individual creator - (品牌/产品账号)
brand/product account - (教育者/顾问)
educator/consultant - (内容聚合账号)
aggregator
如果用户已有种子创作者:
- 使用模式
handle-first
如果用户需要可直接触达的潜在合作方:
- 先采集信息
- 再补充资料
- 然后评分
- 最后才使用
creator-outreach
Platform Handoff
平台转交
Use the narrowest useful platform skill:
- TikTok data ->
skills/20-research/tiktok-research - Instagram accounts ->
skills/20-research/instagram-account-research - X accounts ->
skills/20-research/x-research - Outreach prep ->
skills/50-publishing/creator-outreach
Do not use public web search as the primary route for platform creator discovery unless platform collection is blocked.
使用最贴合需求的平台技能:
- TikTok数据 ->
skills/20-research/tiktok-research - Instagram账号 ->
skills/20-research/instagram-account-research - X账号 ->
skills/20-research/x-research - 触达准备 ->
skills/50-publishing/creator-outreach
除非平台采集被限制,否则不要将公开网页搜索作为平台创作者挖掘的主要路径。
Default Output
默认输出
Return:
- chosen discovery mode
- why this route was chosen
- collection plan by platform
- filtering logic:
- recall range
- follower range
- relevance signals
- creator type rules
- exclusion rules
- whether the next skill should be collection, enrichment, or outreach
When returning creator candidates, normalize them into the shared candidate schema in .
references/candidate-schema.mdKeep:
- a stable core schema across platforms
- optional fields for platform-specific or request-specific extensions
Do not let each platform return a completely different downstream shape if the outputs are meant to be merged.
返回内容应包含:
- 选定的挖掘模式
- 选择该路由的原因
- 分平台的采集计划
- 筛选逻辑:
- 召回范围
- 粉丝量级范围
- 相关性指标
- 创作者类型规则
- 排除规则
- 下一步应调用的技能是采集、资料补充还是触达
返回创作者候选人时,需将其标准化为中的共享候选人 Schema。
references/candidate-schema.md需保持:
- 跨平台的稳定核心Schema
- 针对平台特定或请求特定需求的可选字段
如果输出需要合并,不要让每个平台返回完全不同的下游数据格式。
Good Brief
优质任务简报
Use the shared brief shape in .
references/brief-schema.mdIf the user gives a vague request, infer the smallest sufficient brief and proceed.
If the request is ambiguous in a way that changes the route, ask one short question.
Examples:
你是更希望我先从最近在发这类内容的人里找,还是先从你已有名单和竞品名单里找?你这次更在意达人粉丝量级,还是更在意内容和目标受众的贴合度?
使用中的共享任务简报格式。
references/brief-schema.md如果用户的请求模糊,推断最小可行的任务简报并继续执行。
如果请求存在会改变路由的歧义,提出一个简短的澄清问题。
示例:
你是更希望我先从最近发布这类内容的创作者中筛选,还是先从你已有名单和竞品名单中筛选?你这次更在意达人粉丝量级,还是更在意内容与目标受众的贴合度?
Failure Pattern To Avoid
需避免的错误模式
Bad route:
- user asks for
5k-10k AI tools creators - agent runs keyword-based user search
- agent filters follower counts afterward
- result quality is poor and sparse
Better route:
- recognize that follower band plus niche fit needs
content-first - collect relevant content first
- extract and enrich authors
- classify creator type before final shortlist
- apply follower and fit filters after author expansion
When telling the user this plan, translate it into plain language:
- first find people who are already posting the right content
- then补主页和公开资料
- then按粉丝量、内容贴合度和账号类型筛 shortlist
错误路由示例:
- 用户请求
5k-10k AI tools creators - 代理执行基于关键词的用户搜索
- 代理随后筛选粉丝量级
- 结果质量差且数量稀少
更优路由示例:
- 识别到粉丝量级范围加垂直领域适配性需要模式
content-first - 先采集相关内容
- 提取并补充作者信息
- 在最终筛选候选名单前对创作者类型进行分类
- 在作者拓展后应用粉丝量级和适配性筛选
向用户解释此方案时,需转化为通俗语言:
- 先找到正在发布对应内容的创作者
- 再补充主页和公开资料
- 然后按粉丝量级、内容贴合度和账号类型筛选候选名单
Default Filtering Pattern
默认筛选模式
Unless the user explicitly requires strict first-pass filtering:
- use a wider recall band such as
3k-15k - score relevance and creator type
- tighten to the target band such as
5k-10k - return:
research pooloutreach-ready shortlist
Do not collapse these into one list.
除非用户明确要求严格的首轮筛选:
- 使用更宽泛的召回范围,如
3k-15k - 对相关性和创作者类型进行评分
- 缩小至目标范围,如
5k-10k - 返回:
调研池可触达候选名单
不要将这两个列表合并为一个。
Iteration Rule
迭代规则
Do not assume one collection pass is enough.
Creator discovery is an iterative loop:
- collect a small but valid dataset
- evaluate the result quality
- diagnose where the failure or weakness is
- change one or two key variables
- run the next pass
Typical variables to change:
- route
- queries
- recall range
- creator type filters
- platform
- seed set
Do not change everything at once unless the current route is clearly invalid.
After each pass, decide whether the next step is:
continue on the same platformchange route on the same platformexpand from seedsswitch or add platformstop and synthesize
Use for the evaluation and optimization checklist.
references/iteration-loop.md不要假设单次采集就能满足需求。
创作者挖掘是一个迭代循环:
- 采集少量但有效的数据集
- 评估结果质量
- 诊断失败或不足的原因
- 修改一两个关键变量
- 执行下一轮采集
典型可修改变量:
- 路由模式
- 查询关键词
- 召回范围
- 创作者类型筛选条件
- 平台
- 种子创作者集合
除非当前路由明显无效,否则不要一次性修改所有变量。
每轮采集后,决定下一步操作:
继续在同一平台采集在同一平台更换路由模式基于种子创作者拓展切换或新增平台停止采集并汇总结果
请使用中的评估和优化 checklist。
references/iteration-loop.md