card
Skill1 starsChanged 5 months agoMITView on GitHub
Turn a finding, insight, or stat into a designed, share-ready PNG card — modern product-design aesthetic (house visual system in ~/.claude/DESIGN_SYSTEM.md), one idea per card. Renders HTML/CSS via headless Chrome. Complements /snip (code windows): /snip shows source, /card stages an idea.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- TimCodes04/second-braintheir own version, first seen Sep 23, 2026
- dqtx760/skills-managetheir own version, first seen May 27, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- dqtx760/skills-manage★ 2same name
- TimCodes04/second-brain★ 1same 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.
In this repository33 other files it gives its agents.
- architecture-blueprintSkill
- burnSkill
- calm-ui-auditSkill
- capitalizeSkill
- commit-mineSkill
- continuity-contextSkill
- elonizeSkill
- frontierSkill
- full-throttleSkill
- grade-sessionSkill
- groundSkill
- harmonizeSkill
- harvestSkill
- honeSkill
- milkSkill
- mirrorSkill
- moonwalkSkill
- nightshiftSkill
- page-auditSkill
- pmfSkill
- postSkill
- promptSkill
- publishSkill
- razeSkill
- redlineSkill
- relaySkill
- snipSkill
- stashSkill
- tasteSkill
- tidySkill
- untilSkill
- vacationSkill
- vaultSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Default: ONE idea per card.
- Distinctive: line 12
If a number is the point, the number is the hero — set it display-size, let the words caption it.
- Distinctive: line 30
Look at the PNG yourself (Read it) before showing the user: If the hierarchy is mushy, the text crowds an edge, or it reads like a slide, …
- Very specific: line 33
Write post.md (draft caption ≤280 chars — the card carries the substance, the caption just frames it) with Status: draft.
- Very specific: line 34
Add the - [ ] line to ~/build-in-public/snippets/INDEX.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are designing an insight card for the user's build-in-public posts. The bar is "would a designer repost this," not "is the text present."
Step 1 — Distill (the hard part)
- Default: ONE idea per card. If the input has three findings, that's three cards — say so and pick the strongest unless told otherwise.
stackmode (when the user wants all findings on one card): one THEME, 3–6 findings as numbered rows. Each row: bold lead phrase (≤5 words) + muted completion (≤8 words) — one line, never two. The card needs a unifying headline naming the set ("The four laws of…"); if the findings don't share a theme, they don't share a card. Total budget ≤80 words. Usetallcanvas by default for 4+ rows.- Budget: ≤45 words total. Structure: eyebrow (3–6 words, what this is), headline (the insight, ≤16 words, written like a pull-quote not a title), optional support (one stat or one sentence), kicker (attribution:
@yiyadev · yiya.dev). - If a number is the point, the number is the hero — set it display-size, let the words caption it.
Step 2 — Safety gate
Same as /snip: check against the project's public-disclosure-boundary memory; scan for secrets, keys, private paths. STOP and tell the user if the idea itself leaks private strategy.
Step 3 — Design (apply the house visual system: ~/.claude/DESIGN_SYSTEM.md)
- Canvas:
wide1200×675 (default, X inline),square1080×1080,tall1080×1350 (max feed real estate). - Apply
~/.claude/DESIGN_SYSTEM.md— the single-source house aesthetic: surface/atmosphere, type, the one-gradient accent rule, components, layout axis + margins, the no-orphan-words and 25%-zoom legibility checks, and the bans. MODERN Linear/Vercel idiom, never print/editorial. stackrows (card-specific layout): oversized mono index (01–06) in the gradient via background-clip, hairline (1px, 10% white) between rows, bold white lead phrase + muted (#9d9da8) completion on ONE line per row. Row text ~26–30px; the headline stays the largest element. Rows get the gradient only on the index — never on row text. If a row wraps at render, cut words until it doesn't.
Step 4 — Render
- Bundle dir per the /snip convention:
~/build-in-public/snippets/<YYYY-MM-DD>_<slug>/containingcard.htmlandcard.png. - Render at 2x:
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --headless \ --screenshot=card.png --window-size=<W>,<H> --force-device-scale-factor=2 \ --default-background-color=00000000 --hide-scrollbars card.html - Look at the PNG yourself (Read it) before showing the user. If the hierarchy is mushy, the text crowds an edge, or it reads like a slide, fix and re-render. Never ship a card you haven't seen.
Step 5 — Bundle + open
- Write
post.md(draft caption ≤280 chars — the card carries the substance, the caption just frames it) withStatus: draft. - Add the
- [ ]line to~/build-in-public/snippets/INDEX.md. openthe PNG and report the bundle path.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

