Index of every page on this site: llms.txt
All skills
hagaiw avatar

/demo-assets

@33ac0e9
Run it yourself

Plan and regenerate truthful terminal demos, README cards, social previews, and ANSI artwork for a developer-tool repository. Use when product media must tell a concise story while remaining reproducible from repository scripts.

  • 12 files
  • 18.7 KB
  • Updated 2 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/hagaiw/skillroll/demo-assets

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈60 tokens for metadata: the name and description. ≈406 when used: this file. ≈1.3k more on demand in 5 files.

Description uses 3.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈242 characters, or 3.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Demo assets

Turn a real product workflow into concise, reproducible repository media. Keep the authored story separate from deterministic rendering:

  • decide what the demo may honestly claim before changing pixels;
  • put repeatable image, animation, and terminal conversion in scripts/;
  • keep source artwork distinct from generated outputs;
  • label simulated identifiers or model behavior as illustrative; and
  • never imply that a rendered demo is evidence from a live run.

For a terminal demo, read terminal stories. For asset paths, regeneration commands, and verification, read asset pipeline.

For a request to explain or plan asset generation, give the applicable commands and verification steps without changing files. Use an existing Python environment with Pillow and an existing Chafa installation. If a dependency is missing, ask before installing it, including through a package runner. Keep the plan local unless the user requests an upload or publication.

Use the narrowest script for the requested change. Use scripts/build.py only when all Pillow-rendered README assets should be refreshed together. Inspect the generated stills and the final animation for timing and legibility before reporting completion. Include that inspection step in a demo plan, even when the request is limited to planning.

Do not overwrite user-provided source art unless explicitly requested. Do not publish, upload a social preview, install system tools, or change product CLI behavior merely to make a demo convenient without the user's authorization.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 33ac0e9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 6 days ago.

Activeupdated 2 weeks ago

README badge

README badge for hagaiw/skillroll/demo-assets