Save flashcard creation feedback proactively. MUST trigger when the user corrects card output ("cards are too easy", "too many cards", "wrong difficulty", "bad formatting") or confirms good output ("these cards are great", "yes, like that"). Also trigger on explicit requests: "save this feedback", "show my feedback", "clear feedback", "card preferences", "mochi settings", "flashcard style", "consolidate feedback", "bake in my preferences". Feedback loaded automatically when creating new Mochi cards.
Persist feedback about flashcard creation across sessions. Stored feedback is automatically loaded when creating new Mochi cards, ensuring quality and style preferences carry forward.
When the user provides feedback on card creation, save it:
echo '{"category": "<category>", "feedback": "<what the user said>", "context": "<optional context>"}' | \
python ${PLUGIN_ROOT}/scripts/feedback_manager.py mochi-creator save-feedback
Categories: card_quality, difficulty, formatting, deck_organization, topics, batch_size, general
Examples:
{"category": "difficulty", "feedback": "Increase difficulty — require deeper recall, avoid questions answerable by surface-level recognition"}{"category": "formatting", "feedback": "Prefer cloze deletion format over Q&A for factual knowledge cards"}{"category": "batch_size", "feedback": "Limit batch creation to 10 cards maximum — easier to review and approve"}{"category": "deck_organization", "feedback": "Add a tag for the source material or topic on every card created"}{"category": "card_quality", "feedback": "Don't create cards for basic definitions — focus on relationships, applications, and edge cases"}{"category": "topics", "feedback": "Current study focus is AWS certification — prioritize cloud architecture and AWS-specific concepts"}Display all stored feedback:
python ${PLUGIN_ROOT}/scripts/feedback_manager.py mochi-creator show-feedback
Present as a readable list grouped by category.
Clear all feedback or feedback for a specific category:
# Clear all
python ${PLUGIN_ROOT}/scripts/feedback_manager.py mochi-creator clear-feedback
# Clear only difficulty feedback
python ${PLUGIN_ROOT}/scripts/feedback_manager.py mochi-creator clear-feedback difficulty
Graduate stable feedback into the actual SKILL.md files, making corrections permanent. This is a Claude-driven operation — no script needed.
When to consolidate: When the user says "update the plugin based on feedback", "consolidate feedback", "bake in my preferences", or "graduate feedback into the skill".
Process:
python ${PLUGIN_ROOT}/scripts/feedback_manager.py mochi-creator show-feedback
Read the target SKILL.md file:
${PLUGIN_ROOT}/skills/mochi-creator/SKILL.mdFor each feedback entry, determine if it should be consolidated:
Present a consolidation plan to the user:
## Consolidation Plan
**Will bake into SKILL.md** (permanent):
- [feedback] → edit [file]: [what will change]
**Will keep as runtime feedback** (situational):
- [feedback] → reason: [why it stays runtime]
Proceed?
On approval:
python ${PLUGIN_ROOT}/scripts/feedback_manager.py mochi-creator clear-feedback <category>
Report what changed and what remains as runtime feedback.
When mochi-creator creates new cards, it loads all feedback entries and applies them:
This ensures the user never has to repeat the same preference twice.