Back to @SuguruKun_ai's profile

すぐる | ChatGPTガチ勢 𝕏 engagement report

@SuguruKun_ai - 105K followers on X

Measured over 3 original posts from a 30-day window, last computed on October 13, 2026.

Engagement

Per follower
0.094%
of 105K followers
Per impression
0.801%
12K views on a typical post
Reach
11.7%
of its followers see a post
Typical post
99
interactions (median)
Saved
0.194%
24 bookmarks on a typical post
Posting rate
0.4/day
active 13% of days
Peak time
03:00 UTC
Sunday

Early reading. We have captured 3 original posts for this account, below the 8 we require before treating a median as settled. The numbers above describe what we have seen so far, not a finished profile of the account.

A typical post picks up 99 interactions against 105K followers, an engagement rate of 0.094%. Posts are seen about 12K times each, and 0.801% of those impressions turn into an interaction. That is about 11.7% of the follower count, which is the gap between an audience on paper and an audience in a timeline. Posting runs at about 0.4 posts a day over the last 30 days, though only 13% of days saw any activity at all. Most posts go out around 03:00 UTC, and Sunday is the busiest day of the week. Of the 3 posts sampled, 100% carry an image or video, 67% are part of a thread and 33% link out. The account's strongest tracked post pulled 2.5K interactions, about 26x its own typical post. Only 3 original posts have been captured so far, fewer than the 8 posts we want behind a median before treating it as settled. Read the figures above as an early measurement of this account, not as a finished profile of it.

Measured over 3 original posts from a 30-day window, last computed on October 13, 2026.

Where this sits in the catalog

At 0.094%, すぐる | ChatGPTガチ勢 𝕏 sits above the 25th percentile of the 201,862 accounts in this comparison. That places it in the below the median band, which runs 0.024% to 0.142%.

p100.004%
p250.024%
p50 (median)0.142%
p750.672%
p902.53%
p9982.4%
Engagement rate as a share of followers, across the 201,862 accounts we have scanned enough to measure. The axis is logarithmic, because the top and bottom of this population are about 22,901 times apart and a linear axis would flatten everything below the median into a single point.
Show the percentile table
Engagement rate percentiles
PercentileEngagement rate
10th percentile0.004%
25th percentile0.024%
50th percentile0.142%
75th percentile0.672%
90th percentile2.53%
99th percentile82.4%

This ruler is the whole measured catalog, not a size-matched group: it shows where the raw rate falls across every account we can measure, all of which are large. For a like-for-like comparison, read the size-band percentile above instead. See how the bands are built

Posting timing

This account posts most often around 03:00 UTC, and Sunday is its busiest day of the week. The bars below are the catalog-wide pattern, with this account's own busiest slot marked. They do not show how this account performs at each hour: we keep one aggregate per account, not one per hour, so that measurement does not exist in our data.

Engagement by hour posted, UTCTwenty-four bars, one per UTC hour. Each bar shows how posts published in that hour compare with their own authors' median engagement. Bars above the centre line ran higher than the median, bars below ran lower. A marker flags Busiest hour: 03:00 UTC.
0003060912151821
Above the authors' own mediansBelowScale: plus or minus 111%Busiest hour: 03:00 UTC
Show engagement by hour posted, utc as a table
Engagement by hour posted, UTC
Hour (UTC)Vs author medianPosts
00:00 UTC-1%89K
01:00 UTC-2%90K
02:00 UTC-3%88K
03:00 UTC-4%94K
04:00 UTC-5%76K
05:00 UTC-4%75K
06:00 UTC-5%86K
07:00 UTC-5%93K
08:00 UTC-4%108K
09:00 UTC-4%124K
10:00 UTC-3%129K
11:00 UTC-3%141K
12:00 UTC-3%154K
13:00 UTC-3%167K
14:00 UTC-4%173K
15:00 UTC-2%176K
16:00 UTC-3%171K
17:00 UTC-3%159K
18:00 UTC-2%149K
19:00 UTC-2%141K
20:00 UTC-1%131K
21:00 UTC0%116K
22:00 UTC-2%100K
23:00 UTC-1%90K
Engagement by day of weekSeven bars, one per weekday, Sunday first. Each bar shows how posts published on that day compare with their own authors' median engagement. Bars above the centre line ran higher than the median, bars below ran lower. A marker flags Busiest day: Sunday.
SunMonTueWedThuFriSat
Above the authors' own mediansBelowScale: plus or minus 111%Busiest day: Sunday
Show engagement by day of week as a table
Engagement by day of week
DayVs author medianPosts
Sunday+5%393K
Monday+1%483K
Tuesday-2%520K
Wednesday-3%472K
Thursday-2%430K
Friday-3%447K
Saturday+2%393K
See what moves engagement across the whole catalogWhat counts as a good engagement rate at this size

Formats this account uses

Its own posting mix on the left, and what each of those formats does across every account we track on the right. Only formats where the effect clears our publish test appear here, so an empty row is a format we could not measure rather than one that does nothing.

This account's posting mix compared with catalog-wide effects
FormatThis accountCatalog effect95% intervalAccounts behind it
Image or video100% of posts+111%+108% to +115%34K
Outbound link33% of posts-41%-42% to -40%32K
Typical length-+15%+14% to +16%32K
  • 100% of this account's sampled posts carry an image or video. Across the catalog, posts with an image or video run 111% above the same accounts' other posts.
  • 33% of its posts carry a link off X. Across the catalog, posts with an outbound link run 41% below the same accounts' other posts.
  • Its average post runs 281 characters, which falls in the over 280 characters band. Across the catalog, posts over 280 characters run 15% above the same accounts' other posts.

These are catalog-wide differences applied to this account's own posting mix, not a measurement of how each format performs for this account specifically. We keep one median per account, not one per format per account, so the second thing is not something this data can tell you.

Best tweets

  • Apr 20, 202626x their median

    Claude Codeで公式サイトを作る ↓ Githubにあげる ↓ Claude Designに連携 ↓ LPの強化版デザインを20種類提案してもらう ↓ よかったやつをClaude Codeに渡す ㅤ コレ、参考にもなるし デザインセンス元より良いからまじでオススメ。 ㅤ 自分の場合はこれがやりたいからClaude Codeで作ったというか、三ヶ月前に作ってたからすぐに連携できた感じです!

    2.3K1671316214K viewsView on X
  • Apr 10, 202619x their median

    Claude Codeの使用制限、、、 毎回あの「limit reached」見るたびにイラッとしてたけど 海外で話題のNotebookLMを活用した解決策がかなり実用的だった! ㅤ ① 重い文書分析をNotebookLMに投げてトークン節約 ② Webリサーチ→そのままスキル化してエージェント構築 ③ セッション終了時の学びを自動保存→次回に引き継ぎ ④ Obsidianと組み合わせてナレッジグラフ化 ㅤ NotebookLMをCLIから操作するOSSを使って Claude Codeと繋げるという発想。 ㅤ 特に③の「永続メモリ」は 自分もまさに同じ仕組み作ってて、、、 セッション間で記憶が消えるのが Claude Codeの最大の弱点なんですよね。 ㅤ 47万ビュー超えてるのも納得の内容。 スレッドで深掘りします👇🧵

    1.7K1391733280K viewsView on X
  • Aug 24, 20269.7x their median

    タイミーが公開した「社内利用1位になったClaude Codeスキルの裏側」資料が有益。Claude Code開発者本人の投稿から実働2〜3時間で生まれたBigQuery分析スキルが、4,400行の社内知識の言語化を経て全社に定着するまでを実データつきで解説している。社内にAIを広めたい人は全員見た方がいい👇🧵 https://t.co/3qr4u3Ctar

    8785717983K viewsView on X
  • Jul 27, 20269.2x their median

    Claude Opus 5でかなりリッチなサイトを作る16分の解説動画が海外で話題に... https://t.co/2dkTN2UtQF ■ 使うツールは4つ ・Pinterest(参考デザイン探し。「real estate award winning website」で検索して1枚コピー) ・Higgsfield(ヒーロー画像の生成と加工。GPT Image 2とNano Banana 2を使い分け) ・Figma(モックを作ってスクショ。Claudeへの指示用) ・Claude Opus 5(サイト本体を実装。Tailwind + パララックス) ㅤ ■ 作る流れ ① Pinterestの参考画像を正面向きに直して素材化 ② 前面(家だけ・背景透過)と背景(8K)を別々に書き出す ③ フォントとTailwind設定を渡してClaudeにヒーローを実装させる ④ Figmaでモックを作り、スクショを渡して修正を指示 ㅤ 肝は④の「言葉で説明しない」指示の出し方👇🧵

    8316412784K viewsView on X
  • Sep 5, 20268.1x their median

    OpenAIがひっそり公開した 「GPT-6 Astraプロンプトガイド」が有益すぎた。 ㅤ トークン単価は上がったのに「タスク単価は下がる」設計など、 GPT-6 Astraの性能を最大限に引き出すテクニックを網羅: ㅤ スレッドに解説をまとめていきます👇🧵 https://t.co/p0frPhtO4R

    717727477K viewsView on X
  • Jul 25, 20267.5x their median

    Anthropic公式がひっそりと 「Opus 5専用のプロンプトガイド」を公開していた: ㅤ ①「最後に検証して」を消すこと(勝手にやる) ②「ダブルチェックして」も消すこと ③レビューは「重大なものだけ報告して」と書かかない ④effortはlow/mediumを主力にする ⑤サブエージェントは大きい独立作業だけ ㅤ 今までの「念のため確認させる」系の指示、 Opus 5では逆効果でトークンが増えるだけらしい ㅤ 要するに「賢くなった分、 指示は足すんじゃなくて引け」ということ ㅤ 中身はリプで👇🧵

    6547510681K viewsView on X
  • Jul 26, 20267.2x their median

    Claude Opus 5が1回の指示だけでCall of Duty級のFPSを作ってしまった... そのプロンプト全文が公開されてる: https://t.co/ktjaECS6nM ①「最新のCall of Dutyと同じレベルで作れ。テクスチャから物理まで全部AAA品質で」と基準だけ書く ②サブエージェントを並列展開して、要素ごとに1体ずつ担当させる ③項目ごとに /loop を回す ④別のサブエージェントを「かなり厳しい批評家」として立てて、見た目を判定させる ⑤本物のCall of Dutyとブラインドで並べて、どっちが上か言わせる ⑥全エージェントが唸るまで止めない ⑦最後に ultracode ㅤ 出てきたのが約55,000行・11サブシステム テクスチャもメッシュも音も全部コードで生成してて、素材ファイルは1つも入ってない ただリポのREADMEには「目標は現代のCall of Dutyに並ぶことだった。並んでいない」と書いてある👇🧵

    599712522188K viewsView on X
  • Jul 26, 20265.7x their median

    Claude CodeやCodexのリサーチ機能をかなり強化してくれる エージェントスキル「Hyperresearch」が良かった。 ㅤ 「AIの調査は都合のいい情報だけ集めてくる」問題を、 仕組みで潰しにいくOSSです。 ㅤ hyperresearchと言って、Claude Codeを 16工程の敵対的リサーチ工場に変えます。 ㅤ ①集めたソース同士の矛盾を地図化 ②「この結論を覆す情報源は何か」をAIが自問して追加調査 ③反証・深さ・広さ・指示逸脱の批評家4体が並列でドラフトを攻撃 ④引用が本文を本当に支えてるか出荷前に監査 ㅤ GitHubスター1,100超・MITライセンスです。 実際にフルで回してみたので、中身と結果は下に👇🧵

    5094213544K viewsView on X
  • Sep 5, 20265.4x their median

    GPT-6 Astraで、こんなローンチ動画まで作れてしまった... ㅤ ・GPT-6のレベルは「最大」がオススメ ・映像はHyperFrames連携 ・Voiceboxでナレーションの自分の声をローカル生成 ㅤ 会話だけでここまで仕上がるのすごすぎる... なんというか、o1 pro以来の衝撃を受けています。本当に良いモデル https://t.co/zKA7oucj76

    496267358K viewsView on X
  • Jul 25, 20264.7x their median

    個人的に大満足しているお金の使い先 ・Oura Ring 睡眠と回復のスコアが出る指輪。夜更かしした翌日に無理な予定を入れない判断ができる。Claude Codeと連携してレポート作ってSlackにHTMLレポート送るとマジで人生変わる ・bmonster 暗闇ボクシングジム。経営はイライラすることも多いので、朝から気持ちを切り替えていける。早朝6:50からの回が一番オススメ。最近恵比寿のやつ無くなって都内の選択肢結構減ったのがきつい笑 ・シェアラウンジ TSUTAYAのラウンジ。多拠点デラックスの月66,000円で、ドリンクもフードも全部込み。あとAIエージェント使う時にはモニター必須だけど結構どこにでもあってモニター使えるのも良い。ちなみに法人にすると半額になる... ・Plaud NotePin 毎日つけてるAIレコーダー。スマホ録音をやめて、商談から議事録・ネクストアクションまでそのまま流れるようになった。 ・SANU 2nd Home 月5.5万円の平日サブスク。山中湖や河口湖の拠点にそのまま入って、合宿もワーケーションもできる。環境を変えると出てくるアイデアが変わる。社内の合宿とかでも使ってるけど法人とかだとかなりオススメ ・MacBook Pro M5 Max 128GB AIエージェントを15体ぐらい同時に動かしても動じない。メモリを積んだ分だけそのまま効いてくる。コレがあればBlenderなりRemotionなりで動画編集しながらビジネスタスクできるので趣味も捗る...笑 趣味にそんな使わん!という人は64GBでOK。ちなみにローカルLLM回す系はそんな期待しない方がいい。 ・月1,000円台のVPS 自分のPCを閉じてもAIが働き続ける環境。86日ノンストップで、毎日120本の定時処理が勝手に回ってます ・メンタルクリニック 経営者には必須な気がする。浮き沈みの激しさに対処法が分からない人は絶対に行ってほしい。 ・サラダチキンの作り置き 作り置きするだけでなんか1日が幸せになる。フォークでグサグサ刺していくだけなので楽。笑 サブスクが増えすぎて追加できない、という人向けの話をリプにも書いておきます👇

    4232610485K viewsView on X

Ranked by total interactions across everything we have tracked for this account, which is a longer history than the 30-day window the rates above use. The multiple compares each post to this account's own median.

Buy or sell Twitter (X) accounts - escrow-protected

PlayerSells is an escrow marketplace for Twitter (X) accounts. Every deal is protected, with no middleman risk.

Reading these numbers

A typical post picks up 99 interactions against 105K followers, an engagement rate of 0.094%. Posts are seen about 12K times each, and 0.801% of those impressions turn into an interaction. That is about 11.7% of the follower count, which is the gap between an audience on paper and an audience in a timeline. Posting runs at about 0.4 posts a day over the last 30 days, though only 13% of days saw any activity at all. Most posts go out around 03:00 UTC, and Sunday is the busiest day of the week. Of the 3 posts sampled, 100% carry an image or video, 67% are part of a thread and 33% link out. The account's strongest tracked post pulled 2.5K interactions, about 26x its own typical post. Only 3 original posts have been captured so far, fewer than the 8 posts we want behind a median before treating it as settled. Read the figures above as an early measurement of this account, not as a finished profile of it.

What is すぐる | ChatGPTガチ勢 𝕏's engagement rate on X?
すぐる | ChatGPTガチ勢 𝕏 (@SuguruKun_ai) has an engagement rate of 0.094%, based on the median interactions across 3 original posts from the last 30 days against 105,398 followers. Replies, reposts and quote-posts of other people are excluded from that sample.
Is that a good engagement rate?
At 0.094%, すぐる | ChatGPTガチ勢 𝕏 sits above the 25th percentile of the 201,862 accounts in this comparison. Those comparison accounts are all large ones, because our scanning cadence is weighted towards big accounts, so this is a ranking among peers of similar scale rather than a ranking across X.
Does @SuguruKun_ai have real engagement?
There is not yet enough sample to rank this account against others of its size.
When does @SuguruKun_ai post?
Most posts go out around 03:00 UTC, and Sunday is its busiest day, at roughly 0.4 posts per day across the measured window.

Keep going