dsh-ai-teacher
适用于 dsh Web GUI 的 AI老师 (ai-teacher) agent 预设：功能完整的教学 agent，专注于阅读 PDF 文档并帮助用户掌握文档内容。预设文件会在主机启动时同步到 ~/.dsh/.agent-presets。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:hatter123/dsh-ai-teacher#1214ca4d751beeb064c1eb387d353c600145d7e4Ai Teacher 以 dsh-ai-teacher 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
AI老师 (ai-teacher) agent preset for DeepSeek Harness. Installing this plugin syncs the ai-teacher preset into ~/.dsh/.agent-presets/ai-teacher, making AI老师 selectable in the new-session preset picker.
A full-capability teaching agent that masters PDF documents and explains them as objective truth:
read_pdf), digests the content, and explains it as "this is how it is", never as "the book says…"It also has the full standard preset capability (shell, filesystem, search, skills, plan mode, goals, subagents, workflows).
dsh plugin --profile web add dsh-ai-teacher
Or from a local checkout:
dsh plugin --profile web add link:D:/VSCode_/Project/dsh/dsh-ai-teacher
The preset appears in the new-session preset picker as AI老师.
read_pdf tool.On host startup the plugin syncs two trees into the harness home:
presets/ai-teacher → ~/.dsh/.agent-presets/ai-teacher — the preset compositionskills/* → ~/.dsh/skills/ — the teaching methods as dsh skillsThe preset's agent.cordis.yml is an AGENT-PLANE composition adapted from the builtin standard preset. Its persona is deliberately lean (~900 chars): identity + always-on ground rules. Specific teaching methods live in skills that the agent loads on demand:
| Skill | Loaded when |
|---|---|
teach-new-concept | teaching a new concept — guess-before-prove, definition-motive-justification |
derive-step-by-step | doing a derivation/proof — one step per message, motive + justification each step |
answer-confusion | student is confused or asks — locate the stuck point, SOCRATES guidance |
frankel-study | studying Frankel's The Geometry of Physics — book-specific notation & structure |
The persona lists these skills with their trigger conditions, so loading is reliable while keeping the always-on prompt small.
MIT