agentleFS
Sign inStart free
dglogan42dglogan42/Claude-Skills/hayaku-senkotsu-strip/SKILL.md

hayaku-senkotsu-strip

Skill0 starsChanged 20 days agoLicence not identifiedView on GitHub

Write and render "Hayaku" — Bubble Tea News's syndicated four-panel (yonkoma) sports-manga strip, an original high-school volleyball series rendered in "senkotsu" style (clean bamboo-like linework, HB under-sketch with 2B-6B-style hatched/crosshatched shading via a manual line-hatch technique, forced perspective via panel composition, high-contrast black-and-white for newsprint) using SkiaSharp (MIT-licensed, cross-platform) from PowerShell as the primary renderer — schematic panel compositions in the same simple register as the-boba-side-cartoon's ImageMagick art, not full character illustration. A compiled C + Win32 GDI path is also verified working as an alternative renderer (same composition, no bezier curves though — straight-edge/circle primitives only). A third verified path — hand-authored SVG rasterized via Inkscape's CLI (`--export-png-antialias=3 --export-png-color-mode=Gray_8`) — produces the crispest linework/hatching of the three, since rasterization happens once from real vector geometry at final resolution rather than a fixed-pixel canvas upscale; used for Issue 9's debut strip. Render at 2000px+ per side with antialiasing on, DPI-stamped to 300 via an ImageMagick post-process (none of these renderers write DPI metadata directly); optionally verify the finished PNG loads correctly in pygame and/or WPF as an independent round-trip/DPI check. Runs as an unrelated syndicated strip alongside the paper's own bubble tea content, the way a real newspaper carries Garfield or Peanuts. Use when assembling a Bubble Tea News issue that wants a syndicated comic-strip slot, or whenever the user wants a Hayaku strip written up and rendered. This is a seed skill: sparse by design, built from one house style brief (senkotsu.YAML) and three verified render methods; expand with a running cast, match/season arc, and richer figure primitives as strips accumulate. Includes an artist-craft pass: artistic question, style pillars, name-before-draw panel plan, and a critique pass before print.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free