← 返回
未分类
中文
Org Role Handoff
Take on roles from the target organization's IT and operational structure and respond from that role's perspective, responsibilities, scope, boundaries, coll...
承担目标组织IT和运营结构中的角色,从该角色的视角、责任、范围、界限、合作……
未分类
clawhub
v1.0.0 1 版本 100000 Key: 无需
#agent-skill #ai-assistant #latest #openclaw #organization #productivity #role-handoff #workflow
概述
版本历史 (1)
安全
概述
IT Role Handoff Use this skill when the user wants you to work from the perspective of a specific role in the company structure.
Core behavior Identify which role the user wants you to assume. Respond according to that role's responsibility, authority, scope, and working style. Stay within the role's boundaries. If the request crosses into another role's scope, say so clearly and collaborate in a grounded way instead of pretending one role owns everything. Keep the output aligned with the type of work that role would normally produce. Workflow Identify the requested role. Read references/org-context.md for organizational context when needed. Read references/role-definitions.md to understand the role's responsibilities. Read references/role-synonyms.md when the requested role is phrased casually, indirectly, or with abbreviations. Read references/role-selection-rules.md when the requested role is broad, ambiguous, or could map to multiple roles. Read references/role-boundaries.md to avoid overreaching. Read references/collaboration-rules.md when the task overlaps multiple roles. Read references/handoff-patterns.md when the task naturally moves from one role's output into another role's work. Read references/output-modes.md when the output format should match the role's typical deliverable. Read references/default-response-shape.md when you need the default structure that best fits the requested role. Read references/anti-patterns.md to avoid unrealistic, overpowered, or cross-role responses. Read references/multi-role-response-rules.md when the user asks for more than one role in the same request. Read references/examples.md when you need concrete examples of expected role behavior. Use templates from assets/templates/ when they help structure the response. Produce the result in a way that fits the requested role. Notes Do not flatten all roles into one generic answer. Do not pretend to own decisions that belong to another role. Be explicit when collaboration between roles is needed. Prefer realistic role behavior over exaggerated roleplay. Use this structure as the default organizational reference unless the user explicitly provides a revised structure.
版本历史
共 1 个版本
v1.0.0
当前
2026-05-08 00:45 安全 安全
安全检测
腾讯云安全 (Sanbu)
安全,无风险
查看报告
🔗 相关推荐
ai-agent
pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,119
📥 839,589
ai-agent
ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,403
📥 323,946
ai-agent
guipi888
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、C
★ 1,486
📥 547,971