[{"data":1,"prerenderedAt":151},["ShallowReactive",2],{"use-case-library:en:social-research":3},[4,26,43,64,82,110],{"slug":5,"category":6,"sourceType":7,"platforms":8,"tools":10,"screenshots":12,"evidence":13,"performedAt":18,"title":23,"description":24,"prompt":25},"grok-for-excel-seo-signal","social-research","authorized-user",[9],"X",[11],"$research-social-signals",[],[14,19],{"title":15,"body":16,"source":17,"capturedAt":18},"Current X retrieval","SignalDig search_x_posts returned 100 results for a Cursor\u002FOpenAI access query and 99 results for a Grok\u002FCursor coding query in recent mode, sorted by relevancy, captured on 2026-08-31. Both responses returned next_token values, so the pages are not exhaustive.","SignalDig MCP: search_x_posts","2026-08-31",{"title":20,"body":21,"source":22,"capturedAt":18},"Observed discussion themes","Returned posts discussed a proposed November 12, 2026 cutoff, Cursor's model mix and a possible shift toward Grok and Claude. These are public X claims and require primary-source confirmation before being stated as confirmed company facts.","Public X posts retrieved through SignalDig MCP","Assess Grok's opportunity after OpenAI limits Cursor model access","A current X research snapshot examining how OpenAI's Cursor access change may affect Grok's position in coding tools, with native post metrics and explicit coverage limits.","@skill:research-social-signals What is Grok's future after OpenAI limits Cursor's GPT model access? Search current X discussions and preserve the evidence boundaries.",{"slug":27,"category":6,"sourceType":7,"platforms":28,"tools":30,"screenshots":31,"evidence":32,"performedAt":18,"title":40,"description":41,"prompt":42},"wechat-seo-keyword-conflict-article-analysis",[29],"WeChat",[11],[],[33,37],{"title":34,"body":35,"source":36,"capturedAt":18},"Target article from the current stream","SignalDig returned appMsgId {app-msg-id} with title \"你沉迷的爆款 AI 视频，原来都是这样生产的...\" and showDesc \"阅读 4450 赞 35\" for account {account-id}.","SignalDig MCP: get_wechat_account_articles",{"title":38,"body":39,"source":36,"capturedAt":18},"Current recent-page range","The latest returned page contained 10 articles with observed read counts from 693 to 15k. The account stream was fetched through repeated next_offset calls; the response remained is_end=false at the capture boundary.","Measure how the latest WeChat official-account article is performing","A Social Signal Retrieval run that resolved the WeChat official account (account id and nickname redacted) behind an article, retrieved its latest 10 articles, and benchmarked the target article against the account baseline.","@skill:Social Signal Retrieval https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002F{article-id}. Analyze how the latest article from this WeChat official account is performing",{"slug":44,"category":6,"sourceType":7,"platforms":45,"tools":47,"screenshots":48,"evidence":49,"performedAt":18,"title":61,"description":62,"prompt":63},"xiaohongshu-account-growth-diagnosis",[46],"Xiaohongshu",[11],[],[50,54,57],{"title":51,"body":52,"source":53,"capturedAt":18},"Profile counters from the current retrieval","The SignalDig Social MCP returned 288 followers, 502 following, 12 public notes, 1,391 received likes, 1,063 received collects and 2,454 interactions; verified was false. These are native profile counters captured on 2026-08-31.","SignalDig MCP: get_xiaohongshu_user_posts",{"title":55,"body":56,"source":53,"capturedAt":18},"Current note coverage","The supplied profile URL returned 12 notes, with has_more=false. The returned publication dates span 2026-02-13 to 2026-08-05. This is the complete response for this retrieval, not a claim about every historical note.",{"title":58,"body":59,"source":60,"capturedAt":18},"Highest-interaction returned note","The note “配置了一下 Codex + Figma 效果奇佳” returned 498 likes, 518 collects, 48 comments and 57 shares. The source URL is redacted as https:\u002F\u002Fwww.xiaohongshu.com\u002Fexplore\u002F{note-id}.","Xiaohongshu native counters via SignalDig MCP","Diagnose why a Xiaohongshu account is underperforming and define its direction","A Social Signal Retrieval snapshot of 12 public Xiaohongshu notes, using native account counters and note-level metrics to identify the account's strongest recent topic and format signals.","@skill:Social Signal Retrieval https:\u002F\u002Fwww.xiaohongshu.com\u002Fuser\u002Fprofile\u002Fxxx. Analyze my own Xiaohongshu account: why is it performing so poorly? What should my follow-up direction and positioning be?",{"slug":65,"category":6,"sourceType":7,"platforms":66,"tools":68,"screenshots":69,"evidence":70,"performedAt":18,"title":79,"description":80,"prompt":81},"zhihu-ai-replacing-programmers-search",[67],"Zhihu",[11],[],[71,75],{"title":72,"body":73,"source":74,"capturedAt":18},"Current retrieval boundary","SignalDig returned 20 raw Zhihu items for \"程序员被AI取代\" with upvote sorting and no time filter; normalization accepted 18 and rejected 2. Captured on 2026-08-31.","SignalDig MCP: search_zhihu_articles",{"title":76,"body":77,"source":78,"capturedAt":18},"Highest-ranked returned items","The returned page included items with 2,791 upvotes \u002F 479 comments, 2,549 \u002F 231, and 1,899 \u002F 141. These are native Zhihu counters from the current response.","Zhihu public results via SignalDig MCP","Search Zhihu for discussions about programmers being replaced by AI","A current Zhihu search for discussions about programmers being replaced by AI, retaining the 20-result retrieval boundary and 18 accepted results without claiming exhaustive coverage.","@skill:Social Signal Research Search Zhihu for discussions about programmers being replaced by AI",{"slug":83,"category":6,"sourceType":7,"platforms":84,"tools":85,"screenshots":86,"evidence":87,"performedAt":106,"title":107,"description":108,"prompt":109},"deepseek-hardness-x-discussions",[9,46,67],[11],[],[88,91,94,97,100,103],{"title":89,"body":90},"The Xiaohongshu query returned 20 posts with the specified settings","The query used “DeepSeek Harness,” limited results to the previous week and sorted by popularity. The leading post—the blue fish turning black logo meme—had 1,138 likes, 140 saves, 144 comments and 101 shares. Other leading posts included the “aircraft carrier” reaction (588\u002F187\u002F62\u002F238), a long-form tutorial announcement (451\u002F205\u002F158\u002F213), release news (390\u002F307\u002F84\u002F429) and a paper analysis (381\u002F403\u002F39\u002F231). All figures are public snapshots from this run.",{"title":92,"body":93},"Xiaohongshu's dominant content pattern was IP memes and fan art, not technical debate","The blue-fish-to-black-fish meme drew nearly twice as many likes as the second-ranked post and appeared three days before the official release. Black-whale drawings, stickers and wallpapers had already formed a distinct content lane with low production cost and high interaction, showing that visual speculation can attract attention before launch.",{"title":95,"body":96},"Save behavior validated tutorial demand, but the first-mover window was closing","The long-form tutorial announcement received 451 likes, 205 saves and 158 comments, indicating that early-access creators had already occupied the first tutorial wave. A separate installation and desktop-icon post had 69 likes but 101 saves—about 1.5 times its likes. The stronger follow-up options were video, Windows-specific guidance, non-developer onboarding or desktop packaging rather than another similar long article.",{"title":98,"body":99},"Contested comparisons and save-oriented depth were two validated sharing templates","A “V4Pro + Harness beats Fable?” comparison generated 214 comments and 333 shares, showing that contested comparisons trigger discussion and redistribution. A paper-analysis post received 403 saves versus 381 likes, supporting durable, reference-style content. The recommended response was therefore a reproducible neutral benchmark, not a “crushes” claim.",{"title":101,"body":102},"The action plan ranked work by timing and effort-to-impact ratio","P0 was same-day black-whale fan art. P1 covered a Zhihu hot-list answer plus differentiated video, desktop or save-oriented tutorials within 24 hours. P2 was a neutral DSH + V4 Flash benchmark and an “everything is a plugin” architecture graphic within three days. P3 was English asset building on X through a plugin-directory submission and useful replies within five to seven days.",{"title":104,"body":105},"The conclusion retained three explicit red lines","Avoid leading with the pricing controversy; keep persona memes at a distance and use the validated logo motif instead; re-check star and plugin counts in the official repository and review existing long tutorials before publishing. The evidence covers only the top 20 posts from one week sorted by popularity, not the full platform, and the run did not inspect every image inside every post.","2026-08-14","Find popular X discussions on DeepSeek Harness","A Social Signal Retrieval run that aggregated X, Xiaohongshu and Zhihu signals around the newly released DeepSeek Harness, and turned them into a priority-ranked posting plan with risk boundaries.","@skill:Social Signal Retrieval What are the popular discussions about DeepSeek hardness on X recently? Provide me with marketing ideas",{"slug":111,"category":6,"sourceType":7,"platforms":112,"tools":114,"screenshots":115,"evidence":126,"performedAt":125,"title":148,"description":149,"prompt":150},"linkedin-post-engagement-analysis",[113],"LinkedIn",[11],[116,121],{"src":117,"alt":118,"caption":119,"capturedAt":120},"\u002Fevidence\u002Flinkedin-post-engagement-analysis\u002Fmonthly-engagement-evolution-95-posts.webp","Monthly average likes and average text length across 95 LinkedIn posts, showing a clear inflection point in June 2026","Monthly trend for the complete 95-post sample: purple is average likes; the dashed orange line is average text length, plotted on a separate axis.","2026-08-19",{"src":122,"alt":123,"caption":124,"capturedAt":125},"\u002Fevidence\u002Flinkedin-post-engagement-analysis\u002Fposts-overview.webp","Overview of 50 posts from a LinkedIn account: total likes, comments, reposts, top posts, content-type breakdown and time trend","The engagement overview of the 50 fetched posts, including the Top 5 posts and the content-type breakdown.","2026-08-12",[127,130,135,139,142,145],{"title":128,"body":129},"The execution established scope, metric definitions, and missing fields","Page one returned 50 posts from 2025-11-07 through 2026-08-07. Each was checked for likes, comments, reposts, publish time, text, and image fields; impressions were null on all 50. Following the page-one token returned 45 posts from May 2024 to October 2025; page three returned zero. The report therefore uses likes+comments+reposts and engagement per day, while explicitly treating readership as unverified.",{"title":131,"body":132,"image":133},"Full pagination revealed a measurable shift in content shape","Across the 45 early posts, average likes were 0.20, 88.9% had zero likes, 95.6% were hashtag-only, mean text length was 139 characters, and image rate was 6.7%. Across the 50 recent posts, the corresponding figures were 5.9, 8.0%, 30%, 1,368 characters, and 68%. The comparison shows engagement and content format changing together; it does not isolate any one field as the cause.",{"src":117,"alt":118,"caption":134,"capturedAt":120},"Trend for the complete sample: purple is monthly average likes; the dashed orange line is average text length on the separate right axis. The visible inflection is temporal association, not a causal conclusion.",{"title":136,"body":137,"image":138},"Fifty posts exposed a clear content-type gap","App-ranking posts averaged 15.3 likes across seven posts and carried 36% of all likes, while fourteen hashtag-only posts averaged 2.1. The comparison identifies a relative high-engagement line inside this account, not a platform benchmark.",{"src":122,"alt":123,"caption":124,"capturedAt":125},{"title":140,"body":141},"The time series corrected the earlier single-post conclusion","June 2026 reached 98 total likes and 12.2 average likes; July average likes reached 13.7. May had 17 total likes and 4.2 average likes. The “Global Mobile App Revenue Top 30” ranking series began in June, and its first post earned 46 likes. With missing impressions and uncontrolled variables, this supports retesting the content line—not a readership, reach, or causal claim.",{"title":143,"body":144},"Grouping and age adjustment produced an actionable, bounded replication target","All eight high-engagement posts included images and had a 2,025-character median length; the 24 low-engagement posts had a 1,034-character median, and 14 hashtag-only posts generated just 30 interactions combined. After age adjustment, a single-App case post ranked first at 1.33 interactions per day. The report prioritizes App rankings and single-App cases and recommends stopping hashtag-only posts; this is account-level evidence, not a LinkedIn algorithm rule.",{"title":146,"body":147},"The deliverable is traceable to post-level data rather than a generic recommendation","The updated Markdown report includes a 95-post appendix ranked by total engagement and engagement per day, content-type summaries, early-versus-recent comparison, a monthly trend table, Bottom 15 counterexamples, key-post text breakdowns, a data anchor → tension → structured points → takeaway → CTA formula, a topic matrix, and three drafts requiring human rewriting and fact checks. It records missing impressions, pagination scope, and the non-causal nature of the comparison.","Analyze 95 LinkedIn posts for a content-strategy shift and replicable engagement patterns","A Social Signal Retrieval run that paginated through all 95 returnable posts of a LinkedIn account, compared early and recent content, and extracted replicable patterns without making readership promises.","@skill:Social Signal Retrieval Analyze the posting activity of this account: https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fxx. The goal is to find a replicable method for producing posts with high readership",1788262611126]