Yihong89/dsh-teacher
Yihong89★ 3JavaScript最后同步: 2026-08-15
DSH teacher plugin: Socratic tutor that leads you to answers from a markdown question set, tracks knowledge gaps in-session, and retests them on a spaced-repetition schedule.
README 摘要
dsh-teacher 🧑🏫 A DeepSeek Harness plugin that turns the agent into a teacher — never answers, always asks. Give it a markdown file of questions. It leads you to the answers with the Socratic method, keeps a quiet ledger of the gaps it notices in your reasoning, and retests those gaps on-demand on a spaced-repetition schedule. The loop Status v0.3.0 — core + Web client + SQLite question store + LLM-free quiz popup; tests passing (83/83). Milestone Status M0 Scaffold (bundle patch, plugin row, zero-build JS) ✅ M1 Core Socratic loop (curriculum parser, policy section, 5 tools) ✅ M2 Gap ledger + persistence (SQLite + JSON fallback, session events) ✅ M3 FSRS-5 spaced retest (official test vector pinned) ✅ M4 Web client (quiz cards, gaps button + panel, gap projection) ✅ M5 Publish (dsh-plugin topic ✓, awesome lists, live e2e) ◐ M6 SQLite question store (courses/questions/quiz runs) ✅ M7 LLM-free quiz popup (MCQ + free-text, POST /dsh-teacher/quiz/submit ) ✅ M8 Post-quiz LLM analysis + Socratic walk ( analyze quiz ) ✅ Design decisions are in docs/PLAN.md (§10 = the v0.3 redesign). Web client Once the plugin is installed and the web profile restarted, the browser bundle ( lib/client.js…
在 GitHub 查看完整 README →分类
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 1,700
Anionex/agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
★ 884
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
★ 405