skill-authoring

Guidelines and validation for writing Agent Skills compliant with agentskills.io specification. This skill provides guidance for writing Agent Skills that comply with the agentskills.io specification . Frontmatter: name (lowercase-hyphens), description (WHAT + WHEN) Metadata (~100 tokens) loads at startup. SKILL.md ( - folded scalars) - SKILL.md: <500 tokens (soft), <5000 (hard) - references/*.md: <1000 tokens each - SKILL.md (required) - Instructions - references/ (optional) - Detailed docs - scripts/ (optional) - Executable code - Only files explicitly linked via [text](references/file.md) load - Link to files, not folders - [Recipes](references/recipes/README.md) not [Recipes](references/recipes/) - Each file loads in full (not sections) - No caching between requests - write self-contained files - Use recipes/services patterns for multi-option skills - No broken links - All referenced files exist - No orphaned references - All reference files are linked - Token budgets - References under 1000 tokens (split if exceeded) - No duplicates - Consolidate repeated content - No out-of-place guidance - Service-specific content belongs in service-specific references - Guidelines - Detailed writing guidelines - Token Budgets - Limits and splitting guidance - Reference Loading - How references load - Checklist - Pre-submission checklist - Validation - Link and reference validation -...