agentleFS
rafapeixerrafapeixer/java-skills/.claude/skills/new-skill/SKILL.md

new-skill

Skill1 starsChanged 14 days agoMITView on GitHub

Scaffold a new java-skills skill from the template, with good and bad examples, then validate it. Use when adding a skill to this repository.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Create the skill $ARGUMENTS in this repository.

    line 10
  2. Very specific:

    Stop if skills/$ARGUMENTS/ already exists, or if the name is not lowercase kebab-case.

    line 12
  3. Very specific:

    Read CLAUDE.md and templates/SKILL.template.md.

    line 13
  4. Very specific:

    Create skills/$ARGUMENTS/examples/good/ and skills/$ARGUMENTS/examples/bad/, each either a Main.java that uses only the JDK, or a minimal …

    line 15
  5. Very specific:

    Add the skill to the index in both README.md and README.pt-BR.md.

    line 17
  6. Very specific:

    Run bash scripts/validate.sh and ONLY=skills/$ARGUMENTS bash scripts/test-examples.sh and fix everything they report.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 16 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

New skill

Create the skill $ARGUMENTS in this repository.

  1. Stop if skills/$ARGUMENTS/ already exists, or if the name is not lowercase kebab-case.
  2. Read CLAUDE.md and templates/SKILL.template.md. Check that the skill is in the catalog in CLAUDE.md; if not, say so and stop.
  3. Copy the template to skills/$ARGUMENTS/SKILL.md and set name: $ARGUMENTS.
  4. Create skills/$ARGUMENTS/examples/good/ and skills/$ARGUMENTS/examples/bad/, each either a Main.java that uses only the JDK, or a minimal Maven project with <maven.compiler.release>25</maven.compiler.release>.
  5. Write the skill following every rule in CLAUDE.md: one decision, a position, a reason for every rule, real mistakes in the bad example with // MISTAKE: comments, and exceptions in "When not to apply". Check every fact against openjdk.org, docs.oracle.com, docs.spring.io or the library's own docs.
  6. Add the skill to the index in both README.md and README.pt-BR.md.
  7. Run bash scripts/validate.sh and ONLY=skills/$ARGUMENTS bash scripts/test-examples.sh and fix everything they report.

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.

Reviews can't be read right now.

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.