fangyuan025/cardlet-skill/cardlet

Claude Code and agent skill by fangyuan025/cardlet-skill

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Generate polished social-media carousel cards (PNG files) from plain text via the Cardlet API. Use when the user wants to turn text, notes, a thread, or an article into carousel cards, social card images, 小红书/RED 图文卡片, Instagram carousel slides, or a shareable card deck. Works with Bash + curl only — no browser automation needed.

Install

npx vskill@latest install fangyuan025/cardlet-skill/cardlet

SKILL.md

Cardlet — text → carousel cards

Cardlet (https://usecardlet.vercel.app) renders styled carousel cards from markdown-lite text. This skill calls its HTTP API and saves finished PNGs into the workspace.

Steps

  1. Write the deck JSON (schema below) to deck.json. Use --- to split cards; let headings/bullets structure each card. Bilingual (EN/中文) content both render well.
  2. Render and save (helper script included):
bash
bash scripts/render.sh deck.json ./cards

Or inline, without the script:

bash
curl -s -X POST https://usecardlet.vercel.app/api/render \
-H "Content-Type: application/json" \
-d '{"deck":{"t":"Title","b":"Intro\n---\n## Point one\nDetail.","tp":"ink","s":"ig45"}}' \
| python3 -c "import json,sys,base64; d=json.load(sys.stdin); [open(f'card-{i+1:02d}.png','wb').write(base64.b64decode(p)) for i,p in enumerate(d['images'])]; print(d['pages'],'cards, watermark:',d['watermark'])"
  1. Report the saved file paths to the user.

Notes: first call may take 10–20 s (cold start). JSON responses cap at 12 cards — for larger decks fetch per-card: GET /api/render?d=p<base64url(utf8(deckJSON))>&page=N returns one binary PNG.

Pro license (watermark removal)

If the user provides a Cardlet Pro code (CDLT.…), pass it: export CARDLET_CODE="CDLT...." before running the script, or add "code":"CDLT...." next to "deck". Without a valid code the cards carry a small footer watermark and Pro-only options (custom footer brand q/QR) are ignored — tell the user this rather than trying to work around it. Codes: $6.9 one-time at https://usecardlet.vercel.app/#pricing

Deck JSON schema

keymeaningvalues (default first)
ttitlestring ≤64
bbody, markdown-lite## heading · - bullet · > quote · **bold** · ==highlight== · `%% 87% \caption (big stat card) · ---` (new card)
aauthor / handlestring ≤40
tptemplatefree: ink cloud noir peach · pro: glass sunset mint press pop night terminal sakura gold blueprint note
ssizeig45 1080×1350 · xhs34 1242×1656 (小红书) · sq11 1080×1080 · story916 1080×1920
ftext size2 · range 0–4
lline spacing1 · 0 compact / 2 relaxed
bfbody fontsans / serif
ccover card (big centered title)0 / 1
fl✦ end ornament1 / 0
pnpage numbers1 / 0
acheading accent bars1 / 0
qQR sign-off URL (Pro only)string ≤200

中文说明

用法相同:把 deck JSON 写入 deck.json(字段见上表;小红书用 "s":"xhs34"),运行 bash scripts/render.sh deck.json ./cards,PNG 直接落盘。正文语法:## 小标题、- 列表、> 引用、**加粗**、==高亮==、%% 87% | 说明(大数字卡)、--- 分页。中文由服务端自动加载宋体/黑体渲染。用户提供 Pro 激活码时 export CARDLET_CODE="CDLT...." 可去水印;没有码就明确告知用户会带水印,不要尝试绕过。完整文档:https://usecardlet.vercel.app/agent

Content guidance

  • One idea per card: heading + 1–3 short lines beats dense paragraphs.
  • A %% 87% | caption stat card mid-deck adds visual variety.
  • End the deck with a call-to-action card (follow / save / link).
  • Full API docs and a browser-automation alternative: https://usecardlet.vercel.app/agent

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/fangyuan025/cardlet-skill/cardlet/badge)](https://verified-skill.com/skills/fangyuan025/cardlet-skill/cardlet)

Something wrong with this skill or its page? Tell us.