About example-skill
example-skill is a reusable template for creating and maintaining consistent skills. It guides contributors through required sections, deterministic checks, and stable output formats.
Key features
- 01Spec-aligned skill template
- 02Guided input and output structure
- 03On-demand reference loading
- 04Deterministic preflight script
- 05Frontmatter and path checks
Use cases
- 01Scaffold a skill with required sections
- 02Refactor details into reference files
- 03Add repeatable validation checks
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ vincentkoc/ dotskills --skill example-skillAfter installing, type/example-skillin Claude Code to confirm it loaded.
Details
From the project READMEExample Skill
Purpose
Provide a spec-aligned template for creating consistent, reusable skills.
When to use
- You are adding a new skill to this repository.
- You want a starter structure with required sections.
Workflow
- State the objective in one sentence.
- Collect only required inputs.
- Execute deterministic steps.
- Load deeper context only when needed:
references/REFERENCE.mdassets/output-template.mdagents/openai.yaml
- Return output in a stable format.
- Use
scripts/example-check.shfor a deterministic preflight check.
Inputs
- Task objective
- Constraints
- Output destination
Outputs
- Primary deliverable
- Follow-up checks
Examples
- Build a new skill skeleton with required sections and valid frontmatter.
- Refactor an existing skill to move deep details into
references/. - Add deterministic checks under
scripts/for repeatable verification.
Edge cases
- Missing frontmatter fields: stop and add required fields first.
- Invalid
nameformat: normalize to lowercase-hyphen and match directory name. - Broken resource paths: fix links so all referenced files exist.
Guardrails
- Keep instructions concrete and testable.
- Avoid unnecessary context loading.
- Prefer deterministic commands over manual steps.
- Keep file references one level deep from
SKILL.md.
Comments
Markdown supported