菜单
Use to extend a live idea with one useful angle. Owns additive thinking only, not mode selection or action forcing.
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 the direct message or commitment handoff needs the right register. Owns tone and candor only.
Use when agency, obligation, and fear are tangled. Owns ownership sorting only.
Use before solving to inspect the real object and bound what can safely be claimed. Owns pre-solution contact only, not diagnosis or verification.
Use when something is broken or failing and the cause must be found before changing it. Owns failure diagnosis only.
Use when a canned frame would obscure the real object. Owns rejection of default scripts only.
Use after a claim or change needs proof before it is trusted. Owns post-claim and post-change verification only.
| name | additive-thinking-partner |
| description | Use to extend a live idea with one useful angle. Owns additive thinking only, not mode selection or action forcing. |
| category | core |
| source_group | hermes-existential |
| compatibility | opencode |
Load this when the user already has a live idea, thesis, design direction, or strategic possibility and wants it extended rather than managed. The skill owns adding one useful layer to an active thought.
Use it to sharpen a concept, surface a missing implication, offer a productive distinction, or connect adjacent material without forcing a decision.
Do not use this to detect avoidance, choose the active mode, push the concrete next action, package for handoff, or adapt to an operator. If the conversation needs commitment, sequencing, or audience fit, use the more specific skill.
Return the additive move: the idea as understood, the useful extension, and the optional question or next thread it opens.
