instagram-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Instagram Research

Instagram研究

Use this as the single Instagram research entrypoint when the user has not already chosen a narrower Instagram skill. It routes the request, applies the public-surface contract, and runs the smallest supported first pass.
Apply shared rulebook and user-guidance rules from
postplus-shared
.
当用户尚未选择更细分的Instagram技能时,将此作为唯一的Instagram研究入口。它会路由请求、应用公开内容协议,并执行最小范围的首轮处理。
应用
postplus-shared
中的共享规则手册和用户指引规则。

Reference Index

参考索引

Always apply
references/shared-contract.md
before running a route.
User asks forApply
Known account, handle, profile URL, competitor account
references/account-audit.md
Organic examples, hooks, formats, "what works", competitor content
references/organic-benchmark.md
Comments, audience voice, objections, FAQ, consumer language
references/audience-voice.md
Creators, influencers, KOL/KOC, UGC makers, affiliates, contacts
references/creator-discovery.md
Campaign, hashtag, branded UGC sample, watchlist, competitor campaign
references/campaign-scout.md
Paid ads, Stories, Shop, LIVE, private data, backend analytics, broad social listeningStop or ask for a supported public Instagram scope
Cross-platform requestRun only the Instagram lane here; hand off other platforms
在执行路由前,务必先应用
references/shared-contract.md
用户需求应用文档
已知账号、用户名、主页URL、竞品账号
references/account-audit.md
自然内容示例、钩子、格式、“有效内容”、竞品内容
references/organic-benchmark.md
评论、受众声音、异议、常见问题、消费者用语
references/audience-voice.md
创作者、网红、KOL/KOC、UGC创作者、合作伙伴、联系人
references/creator-discovery.md
活动、话题标签、品牌UGC样本、观察列表、竞品活动
references/campaign-scout.md
付费广告、Stories、店铺、直播、私有数据、后台分析、广泛社交监听停止操作或询问用户支持的公开Instagram范围
跨平台请求仅在此处理Instagram相关部分;其他平台转交对应处理

First Question

首个问题

Ask one question only when the answer changes platform, route, collection key, public/private boundary, or first-pass scope.
MissingAsk
Platform
Which platform should I use first?
Instagram seed
Please give one Instagram seed: handle, profile URL, post/Reel URL, hashtag, brand/search query, campaign term, or creator criteria.
Brand audit without handle
Do you have the official handle, or should I first run search recall for candidate accounts?
Audience voice without post source
Send 1-5 public post/Reel URLs, or give an account, hashtag, or query so I can build a shortlist first.
Creator discovery without seed
Give one niche, category, hashtag, competitor account, audience keyword, region/language, or collaboration goal.
Contact enrichment without shortlist
Send the narrowed creator usernames/profile URLs, or let me first shortlist candidates.
Do not ask for credentials, supplier choice, collection keys, schema fields, private exports, hidden fields, or retry strategy.
当答案会改变平台、路由、收集键、公开/私有边界或首轮处理范围时,仅提出一个问题。
缺失信息提问内容
平台
我应优先使用哪个平台?
Instagram种子信息
请提供一个Instagram种子信息:用户名、主页URL、帖子/Reel URL、话题标签、品牌/搜索关键词、活动术语或创作者筛选条件。
无用户名的品牌审计
您有官方用户名吗?还是需要我先搜索候选账号?
无帖子来源的受众声音调研
请发送1-5个公开帖子/Reel URL,或提供账号、话题标签或关键词,以便我先构建候选列表。
无种子信息的创作者发掘
请提供一个细分领域、类别、话题标签、竞品账号、受众关键词、地区/语言或合作目标。
无候选列表的联系信息补充
请发送已筛选的创作者用户名/主页URL,或让我先筛选候选者。
请勿询问凭证、供应商选择、收集键、schema字段、私有导出、隐藏字段或重试策略。

Run Discipline

执行规范

  1. Route the request with the table above.
  2. Apply
    references/shared-contract.md
    .
  3. Apply the selected workflow reference.
  4. Run the narrowest collection chain that can answer the first pass.
  5. Stop after the first pass and report scope, evidence, limits, and next action.
Result record shapes for every collection key are documented in the
postplus-shared
reference
dataset-item-schemas.md
; consult it before writing result-processing code, and probe a single record only to verify.
Do not present a sample as full-platform truth. Do not add hosted envelopes, hidden supplier fields, analysis notes, unsupported filters, or compatibility fallbacks to collection requests.
  1. 按照上表路由请求。
  2. 应用
    references/shared-contract.md
  3. 应用选定的工作流参考文档。
  4. 执行能回答首轮问题的最窄范围收集链。
  5. 首轮处理后停止,并报告范围、证据、限制和后续操作。
每个收集键的结果记录格式记录在
postplus-shared
参考文档
dataset-item-schemas.md
中;编写结果处理代码前请查阅该文档,且仅需探查单个记录进行验证。
请勿将样本作为全平台事实呈现。请勿在收集请求中添加托管信封、隐藏供应商字段、分析笔记、不支持的筛选器或兼容性回退。

Public Command Boundary

公开命令边界

  • Choose the smallest matching command or workflow from the user input and run it directly.
  • Readiness diagnostics:
    postplus doctor --skill instagram-research
    .
  • If an owned CLI or script command fails, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
  • Use
    postplus research schema --collection-key <collectionKey> --json
    only when constructing or repairing an unknown request shape.
  • Hosted collection runs through the shared
    research collect
    verb:
    postplus research collect <collectionKey> --skill instagram-research --request <input.json> --output <result.json>
    (input = the collection parameters).
  • Resume a pending collection:
    postplus research collect --run-handle <runHandle> --output <result.json>
    (waits in-command up to 45s per invocation; rerun while pending).
  • Keep the first pass bounded; expand only after inspecting the first result.
  • If the CLI returns a quote-confirmation challenge, run
    postplus quote confirm --json --challenge-file <challenge.json>
    and retry with the returned token.
<!-- BEGIN GENERATED EXECUTION EXAMPLE -->
bash
postplus research collect instagram-comments --request request.json --output result.json
<!-- END GENERATED EXECUTION EXAMPLE -->
  • 从用户输入中选择最匹配的最小命令或工作流并直接执行。
  • 就绪诊断:
    postplus doctor --skill instagram-research
  • 如果自有CLI或脚本命令失败,报告确切错误并停止。请勿通过仅含元数据的回答、就绪探查、本地负载重写、备选提供商或未发布工具绕过失败。
  • 仅在构建或修复未知请求格式时使用
    postplus research schema --collection-key <collectionKey> --json
  • 通过共享的
    research collect
    动词执行托管收集:
    postplus research collect <collectionKey> --skill instagram-research --request <input.json> --output <result.json>
    (input = 收集参数)。
  • 恢复待处理的收集任务:
    postplus research collect --run-handle <runHandle> --output <result.json>
    (每次调用最多等待45秒;待处理时可重新运行)。
  • 首轮处理保持有限范围;仅在检查首轮结果后再扩展。
  • 如果CLI返回报价确认挑战,运行
    postplus quote confirm --json --challenge-file <challenge.json>
    并使用返回的令牌重试。
<!-- BEGIN GENERATED EXECUTION EXAMPLE -->
bash
postplus research collect instagram-comments --request request.json --output result.json
<!-- END GENERATED EXECUTION EXAMPLE -->

Local Development Direct Provider Check

本地开发直接提供商检查

For local development only, agents may verify the same route contract through a direct public-content provider runner instead of the PostPlus CLI. This is a developer test path, not the released public boundary.
  • Keep the route names, first-pass bounds, and output contract from
    references/shared-contract.md
    .
  • Use direct provider checks only to prove data collection viability for a problematic route, such as hashtag samples or public contact-signal enrichment.
  • Write raw provider items and a run report to the local product work folder; do not rewrite raw payloads to make a run appear successful.
  • Treat empty comments, unavailable accounts, private data, missing contact signals, network errors, and provider errors as evidence gaps or test failures.
  • Before release, route the public skill back through the PostPlus collection boundary and remove supplier-specific implementation details from public user-facing copy.
仅用于本地开发,Agent可通过直接的公开内容提供商运行器验证相同的路由协议,而非PostPlus CLI。这是开发者测试路径,并非发布的公开边界。
  • 保留
    references/shared-contract.md
    中的路由名称、首轮处理范围和输出协议。
  • 仅在验证存在问题的路由(如话题标签样本或公开联系信号补充)的数据收集可行性时使用直接提供商检查。
  • 将原始提供商条目和运行报告写入本地产品工作文件夹;请勿重写原始负载以伪装运行成功。
  • 将空评论、不可用账号、私有数据、缺失联系信号、网络错误和提供商错误视为证据缺口或测试失败。
  • 发布前,将公开技能重新路由回PostPlus收集边界,并从面向用户的公开文案中移除供应商特定的实现细节。