claude-codeskill

# Claude Code Skills Development Reference for developing effective skills. The context window is a public good - only include information Claude doesn't already possess. ## Arguments Run a check against a skill path in `$ARGUMENTS`, defaulting to the skill you just edited: - `--validate`: run `skill-lint` (`bun run skill-lint <path>`) for frontmatter, naming, and reference-depth validation. - `--structure`: run the directory-structure check (`${CLAUDE_SKILL_DIR}/scripts/check-structure.ts`) for the SKILL.md, `scripts/`, `references/`, `assets/` layout. With neither flag, use the skill as an authoring reference. See [Validation](#validation). ## Core Principles - **Conciseness**: Keep `SKILL.md` under 500 lines. Use progressive disclosure. - **Appropriate Freedom**: Text for flexible tasks, pseudocode for moderate variation, scripts for error-prone operations. ## Skill Structure ```yaml --- name: plugin-name:skill-name description: Third-person capability description with trigger terms argument-hint: "[--flag] [<positional>]" # Optional: arguments shown in slash menu allowed-tools: [Read, Grep, Glob] # Optional: tool restrictions model: sonnet # Optional: override model effort: low # Optional: reasoning effort context: fork # Optional: run in isolated subagent agent: Explore # Optional: agent type for fork background: false ...