dsh-momo-learning
Run the following command in DeepSeek Harness:
dsh plugin install ryukirin/dsh-momo-learning
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install ryukirin/dsh-momo-learning in your terminal to add this plugin to DeepSeek Harness; source code is available at https://github.com/ryukirin/dsh-momo-learning
About this plugin
Momo handles spaced-repetition scheduling well, but there is a gap between "I recognize this word" and "I can actually use it." This plugin closes that gap by testing you with question types that appear in real English exams: context fill-the-blank, synonym substitution, collocation completion, look-alike disambiguation, and rare-sense multiple choice. The stem never shows Chinese; you only see the definition and explanation after you answer, forcing you to rely on intuition rather than lookup.
The workflow syncs your Momo study data read-only into a local SQLite mirror, then picks 20 questions (cap 50) each day from a candidate pool ranked by staleness and stubbornness. Questions are presented one at a time via a popup; mistakes accumulate in an error ledger; a Markdown daily report with weakness summaries is generated at the end. Words you already know and words newly learned today are excluded. Nothing is written back to your Momo account.
Best for Windows learners who use Momo for exam prep or want to push vocabulary from passive recognition to active command. It does not replace the app review schedule; it adds a deeper comprehension check after your daily grind, with all records kept locally for review whenever you want.
Use Cases
- Do 20 context-based multiple-choice questions after daily Momo review to push words from recognition to active use
- Test true mastery with look-alike disambiguation and rare-sense items that probe syntactic role, not just meaning
- Track weak vocabulary through a running mistake ledger and a daily Markdown report with weakness summaries
Best For
- English learners using Momo for CET, graduate entrance, or TOEFL-IELTS preparation
- Vocabulary learners who want to graduate from passive recognition to active command
- Privacy-conscious users who prefer local-first data over cloud-synced storage
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.