show
Skill0 starsChanged 57 days agoMITView on GitHub
Use when 需要把資訊變成看得懂的東西——用戶要圖表、圖解、流程圖、架構圖、比較表、儀表板、資訊圖，或說「畫一張」「視覺化」「幫我看一下這份資料」「這個怎麼呈現比較清楚」；也用於 explain skill 判定需要視覺化時的調用，以及 AI 自己準備畫任何圖之前。涵蓋圖表選型、圖解選型、非圖形視覺化（表格／版面階層／標示）、感知編碼選擇、產出管線調度與成品回讀驗收。不用於純程式碼繪圖函式庫的用法查詢。
6 other projects use a version of this.
Adopted by
Most recently taken up by
- NazmusSayad/skillstheir own version, first seen Nov 1, 2026
- NazmusSayad/offsitetheir own version, first seen Oct 25, 2026
- ZimoLiao/scholaraiotheir own version, first seen Oct 8, 2026
- ohm41321/luciazerotheir own version, first seen Aug 12, 2026
- bonez-io/re_genttheir own version, first seen May 14, 2026
- regent-vcs/re_genttheir own version, first seen May 14, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- regent-vcs/re_gent★ 789same name
- ZimoLiao/scholaraio★ 585same name
- NazmusSayad/offsite★ 9same name
- ohm41321/luciazero★ 6same name
- bonez-io/re_gent★ 4same name
- NazmusSayad/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
show：先讀懂資訊，再決定怎麼說，然後真的做出來
六段依序執行。第六段不通過退回第三或第四段，回修至多兩輪。
| 段 | 做什麼 | 讀哪裡 |
| ① 剖析 | 讀懂這份資訊，落出清單 | references/01-profiling.md |
| ② 意圖 | 寫下讀者要看出什麼 | 本檔下方 |
| ③ 形式 | 選圖表、圖解或非圖形 | references/02-form-and-encoding.md |
| ④ 編碼 | 決定誰承載主訊息 | references/02-form-and-encoding.md |
| ⑤ 管線 | 選工具並產出 | references/03-pipelines.md |
| ⑥ 驗收 | 回讀成品，比對兩個基準 | references/04-readback.md |
兩種觸發方式
使用者直接叫（/show 或說要畫圖） | 若也裝了 explain：其判定需視覺化時呼叫 | |
| 起點 | 從 ① 剖析開始跑滿六段 | explain 已完成理解缺口定位，直接從 ③ 形式開始 |
| 第 ② 段 | 自己寫意圖句 | 沿用 explain 已確定的理解目標當意圖句 |
| 第 ⑥ 段 | 比對意圖句與使用者原始需求 | 比對 explain 的理解目標與使用者原始需求 |
| 深度 | 依需求，可外派 codex CLI（可選，需已安裝） | 通常停在 inline widget 或表格，不外派 |
判斷不出是哪一種時，走左欄，跑滿六段比較安全。
② 溝通意圖（本檔自帶）
寫下一句可證偽的話：讀者看完要看出 ___ 比 ___ 更 ___。
寫不出來代表關係還沒想清楚，回第一段。
同時記錄「不必看出什麼」，這是後續刪減元素的依據。
剖析結果顯示有兩種以上合理讀法時，先把這句話給使用者確認再往下走。 只有這種情況才打斷。
需要圖片素材時，先問使用者要真實照片、AI 生成或佔位圖，不預設佔位圖。
明確不做
- 不重寫配色系統：若環境有 dataviz skill 就路由它，否則守
references/02-form-and-encoding.md的一致配色與「顏色不得作為唯一辨識」原則。 - 不重寫 Artifact 內的 inline SVG 技法：若環境有 artifact-diagramming skill 就路由它。
- 不封裝繪圖函式庫或預製繪圖腳本。當場寫排版或繪圖碼不受此限。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.