agentskills.codes
US

using-ito-skills

Use when discovering, finding, invoking, or loading skills. Ensures skills are invoked BEFORE responding.

Install

mkdir -p .claude/skills/using-ito-skills && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13361" && unzip -o skill.zip -d .claude/skills/using-ito-skills && rm skill.zip

Installs to .claude/skills/using-ito-skills

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when discovering, finding, invoking, or loading skills. Ensures skills are invoked BEFORE responding.
105 chars✓ has a “when” trigger

About this skill

Using Ito Skills

If a skill applies to your task, you must invoke it before responding. Even a 1% chance means check.

How to Access Skills

HarnessLoad CommandSkill Locations
OpenCodeskill load <name>.opencode/skills/, ~/.config/opencode/skills/
Claude Codemcp_skill with name="<name>".claude/skills/
CodexRead directly: cat .codex/skills/<name>/SKILL.md.codex/skills/, ~/.codex/skills/

Detecting your harness: OpenCode has the skill tool, Claude Code has mcp_skill, Codex has .codex/ directory.

Red Flags (you're rationalizing)

  • "This is just a simple question" — questions are tasks, check for skills
  • "I need more context first" — skill check comes BEFORE exploration
  • "The skill is overkill" — simple things become complex, use it
  • "I remember this skill" — skills evolve, read the current version

Priority

When multiple skills apply:

  1. Process skills first (brainstorming, debugging) — determine HOW to approach
  2. Implementation skills second — guide execution

Skill Types

Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline. Flexible (patterns): Adapt principles to context. The skill itself tells you which.

Search skills

Search the agent skills registry