domains / families / agent-tooling / claude

claude

combined

Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc). Provides non-interactive automation mode for hands-off task execution without approval prompts. A research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory parchment (never pure white), with near-black slate as the dominant ink.

When to use

• Create a new Skill from scratch from docs/specs/repos
• Refactor an existing Skill (too long, unclear, inconsistent, misfires)
• Design reliable activation (frontmatter + triggers + boundaries)
• Extract a clean Quick Reference from large material
• Split long content into navigable `references/`
• Add a quality gate and a validator

When not to use

• interactive tasks requiring approval prompts

Skill page

Conflict

The four copies are not reproductions of a single procedure. dzhng/skills and LeoYeAI/openclaw-master-skills both describe how to invoke and manage the `claude` CLI as a subagent, but they disagree on defaults, safety mechanisms, and operational details. bergside/awesome-design-skills is a design-system authoring skill that merely uses the name 'claude' for a brand aesthetic, and foryourhealth111-pixel/Vibe-Skills is a meta-skill for creating other skills. Because the copies cover distinct tasks (CLI orchestration vs. design authoring vs. skill creation) and the two CLI-focused copies contain conflicting operational constraints, crowning one would hide real alternatives.