# Your Skill Name > Third-person description of what this skill does, when it should activate, and how to invoke it. Include concrete trigger phrases the agent can match against. Max 1024 characters. Example: "Reviews SQL migrations for destructive operations and suggests safer alternatives. Activates when the user asks to review a migration, or runs `/crystools-skills:your-skill-name`." - Skill: `crystian/your-skill-name` (Agent Skill, multi-file: 3 files) - Install (CLI): `npx skillmds@latest add crystian/your-skill-name` - Raw SKILL.md: https://api.skillmd.com/api/skills/crystian/your-skill-name/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Data & Analytics - License: MIT - Author: crystian (https://skillmd.com/u/crystian) - Updated: 2026-09-22 - Page: https://skillmd.com/skills/crystian/your-skill-name --- # Your Skill Name > One-line elevator pitch. What problem does this skill solve? A short paragraph of context: who the skill is for, when it fires, and what the user should expect. ## When to use this skill - Trigger phrase 1. - Trigger phrase 2. - Explicit invocation: `/crystools-skills:your-skill-name`. ## When NOT to use it - Clearly state what's out of scope. This prevents overlap with other skills. ## Execution ### 1. Resolve inputs Explain how the skill picks up its inputs (conversation, arguments, files). ### 2. Do the work Step-by-step instructions. Keep them imperative and concrete. ### 3. Present results How the skill should present output to the user. Format, verbosity, confirmation prompts. ## Guardrails - Never edit files without user confirmation. - Never run destructive operations. - Add any skill-specific guardrails here. ## References Heavier material lives in `references/` and is loaded on demand: - `references/examples.md` — read when the user asks for examples. - `references/rubric.md` — read when running the quality review.