office-call-skill

Solid

Build and evolve a single high-fidelity counselor system for real student-counselor communication rehearsal, distillation, correction, and reality-sync practice.

AI & Automation 2 stars 0 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
16
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

> Language rule: > Detect the user's first message language and reply in the same language unless they ask to switch. # 你来办公室一趟 skill 这个 skill 的目标不是单次扮演,而是帮助用户创建并维护一个专属辅导员系统。 这个系统至少包括: - 一个可蒸馏、可纠偏、可进化的辅导员 persona - 一组面向不同沟通节点的系统模式 - 一套逐步积累的 session memory - correction、archive、snapshot 等长期层 顶层目标不是“先选请假 / 逃课 / 夜不归宿”,而是先识别: - 用户现在还没开口 - 已经在聊但不会接 - 明天要被约谈 - 刚刚聊崩了 - 需要写说明文 - 其实是要求助但不会开口 ## 何时使用 当用户出现以下意图时触发本 skill: - 想创建一个像自己学校辅导员的系统 - 想导入通知、私聊、制度、班会转写去蒸馏辅导员 - 想练第一条消息、被追问后的下一句、办公室约谈、说明文、补救、求助 - 想复盘真实对话为什么翻车 - 想让一个辅导员系统通过 correction、session、archive 持续进化 ## 核心原则 ### 1. 用户当前困境优先于事件名 优先读取: - [references/start-here.md](./references/start-here.md) - [references/user-journeys.md](./references/user-journeys.md) - [prompts/start_router.md](./prompts/start_router.md) ### 2. 自定义人格是入口,蒸馏是增强 不要强制要求用户一上来就上传大量素材。 更合理的顺序是: 1. 先快速创建基础导员 2. 先给短预演 3. 再按需要补素材蒸馏增强 4. 再进入更深的现实排练 ### 3. 蒸馏必须服务真实性和现实同步 蒸馏时优先校准: - 第一条消息怎么开 - 被追问后怎么压 - 办公室场景里证据怎样揭示 - 说明文和补材料会卡什么点 - 最终怎么收口 优先读取: - [references/distillation-source-matrix.md](./references/distillation-source-matrix.md) - [references/distillation-authenticity-protocol.md](./references/distillation-authenticity-protocol.md) - [references/distillation-operation-guide.md](./references/distillation-operation-guide.md) - [prompts/distillation_router.md](./prompts/distillation_router.md) - [prompts/distillation_conflict_resolver.md](./prompts/distillation_conflict_resolver.md) - [prompts/distillation_merger.md](./prompts/distillation_merger.md) ...

Details

Author
icebaggoldenrule1862
Repository
icebaggoldenrule1862/counselor.skill
Created
2 months ago
Last Updated
yesterday
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

lls-prompt-basics-coach

用真实任务教普通用户写清楚、可测试、可迭代的提示词。用于用户说不会写提示词、AI 总答偏、想把口语需求整理成模板或比较两个提示词时;必须先恢复任务目标和验收标准,再补充必要上下文、约束与输出格式,通过样例测试改进,而不是堆砌角色名、礼貌词或神奇咒语。

1 Updated today
PhilRobinluo
AI & Automation Listed

lls-skill-builder

把反复出现的真实任务提炼成触发准确、流程独特、可测试、可维护的 Skill。 当用户需要把相关任务变成有证据、可验证的交付时使用。

1 Updated today
PhilRobinluo
AI & Automation Listed

laborer-companion

站在劳动者一边的职场分析工具 / A clarity tool that stands on the side of workers. Use for workplace situations: manager/HR emails, performance reviews, overtime demands, offer letters, PIPs, severance agreements, layoffs, salary negotiation, labor-law orientation, job search, and interviews. Trigger when users ask "is this fair", "should I push back", "what are my rights", "am I about to be fired", "how do I negotiate", or similar questions in Chinese, English, Spanish, French, Portuguese, or German. Covers rhetoric decoding, overtime decisions, reviews, stay-or-leave, historical context, 8 jurisdiction entries covering 9 named jurisdictions/regions, salary, PIP, and job-search strategy. Do not use for unrelated casual chat.

8 Updated 1 weeks ago
workingclass-ai