菜单
This skill should be used when the user asks to "create a skill", "build a skill", "develop a skill for Claude Code", or mentions "skill structure", "SKILL.md", or "progressive disclosure".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when working with PyMOL for molecular visualization tasks including loading structures, creating representations, coloring, selections, and basic analysis.
Use when connecting Claude to PyMOL, troubleshooting socket errors, or setting up the PyMOL integration for the first time
Use when setting up, configuring, running, or inspecting La-Proteina protein generation tasks including unconditional design and motif scaffolding. Helps build configs and visualize outputs through PyMOL.
Use when setting up, configuring, running, or inspecting Proteina-Complexa protein binder design, ligand binder design, AME motif scaffolding, or monomer motif scaffolding. Helps build configs, select targets, and visualize outputs through PyMOL.
Use when validating protein designs with AlphaFold2/AlphaFold3/ESMFold predictions, coloring by pLDDT or pAE, computing self-consistency RMSD, or screening design candidates through PyMOL.
Use when comparing multiple protein designs, ranking design candidates, tracking design iterations, overlaying before/after structures, or performing batch visual QC through PyMOL.
| name | Skill Development |
| description | This skill should be used when the user asks to "create a skill", "build a skill", "develop a skill for Claude Code", or mentions "skill structure", "SKILL.md", or "progressive disclosure". |
| version | 0.1.0 |
This skill provides guidance for creating effective skills for Claude Code plugins.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. They transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge.
Every skill consists of a required SKILL.md file and optional bundled resources:
Identify concrete examples of how the skill will be used. Ask clarifying questions about functionality and usage patterns. Conclude when there is clear understanding of what the skill should support.
Analyze each example to identify what scripts, references, and assets would help when executing workflows repeatedly. Create a list of reusable resources needed.
For Claude Code plugins, create the skill directory structure:
mkdir -p plugin-name/skills/skill-name/{references,examples,scripts}
touch plugin-name/skills/skill-name/SKILL.md
Writing Style: Use imperative/infinitive form (verb-first instructions), not second person. Write objectively and instructionally.
Description: Use third-person format with specific trigger phrases showing when the skill should be used.
Body Content: Keep SKILL.md lean (1,500-2,000 words). Move detailed content to references/.
Check structure, SKILL.md validity, trigger phrases, writing style, progressive disclosure, and ensure all referenced files exist.
Use the skill on real tasks and improve based on what works well and what struggles occur.
Plugin skills live in the plugin's skills/ directory and are automatically discovered by Claude Code.
Claude Code scans the skills/ directory, finds subdirectories containing SKILL.md, loads metadata always, and loads body and references when needed.
Plugin skills are distributed as part of the plugin. Users get skills when they install the plugin.
Write using verb-first instructions:
Use third person in frontmatter: "This skill should be used when the user asks to..."
Focus on what to do: "Parse the frontmatter using sed" rather than "You can parse..."
DO:
DON'T:
Study existing plugin-dev skills as templates:
hook-development/ - Progressive disclosure, utilitiesagent-development/ - AI-assisted creationplugin-settings/ - Real-world examples