agentleFS
alvaldesalvaldes/launch-skills/skills/launch-kit/SKILL.md

launch-kit

Skill0 starsChanged 16 days agoMITView on GitHub

Trigger: launch kit, prepare a launch, launch assets, taglines, gallery images. Build the asset kit every launch channel reads from.

  • Installs packages

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use before launching a tool, or when another launch skill finds docs/launch/<slug>/kit.md missing or incomplete.

    line 12
  2. Distinctive:

    Every fact comes from the project: README, code, release notes, the canonical post.

    line 16
  3. Distinctive:

    Do not write the problem or comparison in a voice the maker has not used.

    line 17
  4. Distinctive:

    Never claim a competitor's price, license or status without a source.

    line 18
  5. Distinctive:

    Read the README, release notes, license, the canonical post and existing launch notes.

    line 34
  6. Distinctive:

    Verify the canonical URL and every public asset URL.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Activation Contract

Use before launching a tool, or when another launch skill finds docs/launch/<slug>/kit.md missing or incomplete.

Hard Rules

  • Every fact comes from the project: README, code, release notes, the canonical post. Mark anything inferred (assumption) and ask about it.
  • Do not write the problem or comparison in a voice the maker has not used. Quote or adapt their own text (README, post); if there is none, leave a draft and flag it for rewriting.
  • Never claim a competitor's price, license or status without a source; put the source next to the claim.
  • The canonical post URL must not redirect: check with curl -sIL and record the final URL.
  • Public asset URLs must load without a login: check each with curl -sI.

Decision Gates

SituationAction
No kit yetCopy assets/kit-template.md to docs/launch/<slug>/kit.md
Source images existRun scripts/make-assets.sh (ImageMagick 7) into docs/launch/<slug>/assets/
No magickAsk the user to install it (brew install imagemagick); list the sizes needed meanwhile
Repo has no topicsPropose them; set with gh repo edit <repo> --add-topic a,b only after a yes
A required fact is unknownLeave it under Gaps; do not guess

Execution Steps

  1. Read the README, release notes, license, the canonical post and existing launch notes.
  2. Fill Identity and Copy; keep the tagline under 60 characters and the short description to one sentence ending with a period.
  3. Generate images: scripts/make-assets.sh --out docs/launch/<slug>/assets --icon <1024px icon> --cover <cover> <screenshots in display order>. Put the screenshot that shows the tool in action first.
  4. Verify the canonical URL and every public asset URL.
  5. List Gaps: missing assets, unverified claims, gates the maker must clear.

Output Contract

Return the kit path, the generated files with their sizes, the verified URLs, and the gaps.

References

  • ../../references/launch-folder.md: where launch files live.
  • ../../references/channels.md: asset sizes per channel.
  • scripts/make-assets.sh: image generation; --help for options.

Download now (ZIP)

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.