← ClaudeAtlas

skill-templatelisted

Scaffold a new agent skill, writing the SKILL.md and its frontmatter to the Agent Skills specification, then wrapping it as a plugin in this repo with package.json, plugin.json and a marketplace entry. Use when the user asks to "add a new skill", "create a skill", "write a SKILL.md" or "start a new plugin", and when checking whether an existing skill is portable between agents.
KensioSoftware/kensio.ai · ★ 1 · Data & Documents · score 68
Install: claude install-skill KensioSoftware/kensio.ai
# Skill template A skill is a directory with a `SKILL.md` in it. That directory is the artefact, and every agent reads it. The plugin folder around it in this repository is packaging for one of them. Write the skill first, following the [specification](https://agentskills.io/specification). Then wrap it. ## The skill directory ``` <skill-name>/ ├── SKILL.md ├── references/ # optional, loaded only when linked to ├── scripts/ # optional, anything the skill runs └── assets/ # optional, templates and data files ``` Those three subdirectory names come from the specification. An agent that supports skills at all knows this shape, whether it reads the directory from `.agents/skills/`, `.claude/skills/`, `.github/skills/` or a plugin. **Every path a skill mentions is relative to its own directory.** The directory gets copied out on its own, unzipped somewhere unrelated, and installed under a name this repository never sees. A command written as `node skills/<skill-name>/scripts/check.mjs` works here and nowhere else. Write `node scripts/check.mjs`. `pnpm validate:skills` fails the build on any path that reaches outside the skill, which is the check that caught this after it had already shipped once. ## Frontmatter ```markdown --- name: <skill-name> description: <what it does, then when to use it. Include the words and phrases a user would actually type> license: Apache-2.0 metadata: version: "0.0.0" --- ``` - `name` is