ELSA Speak

Build me a focused learning, flashcards and language practice workflow for the personal core of ELSA Speak. Requirements:

- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use. Model lessons, study sessions, progress checkpoints, and user-owned learning material; keep stable source IDs and timestamps.
- Paid product context: Record pronunciation practice and provide limited acoustic feedback without diagnostic claims. Build only this DIY scope: Record pronunciation practice from user-supplied material, provide limited acoustic feedback, schedule retrieval practice, and show progress without diagnostic claims or claiming accredited instruction.
- Import Markdown, text, or user-authored notes and split them into editable learning units.
- Create flashcards and short quizzes only after showing the generated items for approval.
- Implement a transparent spaced-repetition schedule with due, again, hard, good, and easy actions. Add goals, study sessions, streak-free progress charts, notes, and weak-topic review. Support offline use, full export, reset, backup, and deletion of all learning data.
- Use a local web page with input, progress, review, and export views. Required input or access: user-supplied study material; optional speech or language-model API key. Keep credentials in .env.
- Recovery: Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use; do not offer alternative stacks.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A missing audio file must not count as a completed lesson; restoring progress resumes the same chapter and timestamp.
- Out of scope: proprietary speech models, curriculum, scoring data, mobile polish, and coaching; licensed course catalog. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for ELSA Speak

## Project scope
Record pronunciation practice from user-supplied material, provide limited acoustic feedback, schedule retrieval practice, and show progress without diagnostic claims or claiming accredited instruction.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For ELSA Speak, record pronunciation practice and provide limited acoustic feedback without diagnostic claims. The hard boundary is proprietary speech models, curriculum, scoring data, mobile polish, and coaching, plus content, pedagogy, and network.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- modern browser
- user-supplied study material
- optional speech or language-model API key

## Stack and architecture
- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use.
- Model lessons, study sessions, progress checkpoints, and user-owned learning material; keep stable source IDs and timestamps.
- Interface for this learning, flashcards and language practice workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use; do not offer alternative stacks.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: proprietary speech models, curriculum, scoring data, mobile polish, and coaching.

## Agent implementation rules
- Project rule, data: Model lessons, study sessions, progress checkpoints, and user-owned learning material; keep stable source IDs and timestamps.
- Project rule, behavior: Import Markdown, text, or user-authored notes and split them into editable learning units.
- Project rule, recovery: Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use; do not offer alternative stacks.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this learning, flashcards and language practice operation with sample or user-owned data: Import Markdown, text, or user-authored notes and split them into editable learning units.
- Show a concrete result or export: Support offline use, full export, reset, backup, and deletion of all learning data.
- State the practical limit: proprietary speech models, curriculum, scoring data, mobile polish, and coaching.

## Engineering roadmap
1. Phase 1, architecture and data: Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use. Model lessons, study sessions, progress checkpoints, and user-owned learning material; keep stable source IDs and timestamps.
2. Phase 2, implement: Import Markdown, text, or user-authored notes and split them into editable learning units.
3. Phase 3, implement: Create flashcards and short quizzes only after showing the generated items for approval.
4. Phase 4, review and output: Implement a transparent spaced-repetition schedule with due, again, hard, good, and easy actions. Support offline use, full export, reset, backup, and deletion of all learning data.
5. Phase 5, recovery and acceptance: Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use; do not offer alternative stacks. Verify this invariant with a saved fixture: A missing audio file must not count as a completed lesson; restoring progress resumes the same chapter and timestamp. State the practical limit: proprietary speech models, curriculum, scoring data, mobile polish, and coaching.

## Paid-product capabilities outside this build
- proprietary speech models, curriculum, scoring data, mobile polish, and coaching
- licensed course catalog
- expert curriculum
- human feedback
- large learner network and certification

## Implementation prompt
Build me a focused learning, flashcards and language practice workflow for the personal core of ELSA Speak. Requirements:

- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use. Model lessons, study sessions, progress checkpoints, and user-owned learning material; keep stable source IDs and timestamps.
- Paid product context: Record pronunciation practice and provide limited acoustic feedback without diagnostic claims. Build only this DIY scope: Record pronunciation practice from user-supplied material, provide limited acoustic feedback, schedule retrieval practice, and show progress without diagnostic claims or claiming accredited instruction.
- Import Markdown, text, or user-authored notes and split them into editable learning units.
- Create flashcards and short quizzes only after showing the generated items for approval.
- Implement a transparent spaced-repetition schedule with due, again, hard, good, and easy actions. Add goals, study sessions, streak-free progress charts, notes, and weak-topic review. Support offline use, full export, reset, backup, and deletion of all learning data.
- Use a local web page with input, progress, review, and export views. Required input or access: user-supplied study material; optional speech or language-model API key. Keep credentials in .env.
- Recovery: Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and a service worker for offline use; do not offer alternative stacks.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A missing audio file must not count as a completed lesson; restoring progress resumes the same chapter and timestamp.
- Out of scope: proprietary speech models, curriculum, scoring data, mobile polish, and coaching; licensed course catalog. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.