Pimsleur

Build me a local study player for audio lessons I already own as a limited substitute for Pimsleur. Requirements:

- Use Python, FastAPI, SQLite, and the browser's audio player. Import user-supplied MP3 or M4A files into a selected local folder and record title, language, duration, lesson order, and source filename.
- Show a course list and player with resume position, playback speed, and a completed flag. Never copy or bundle Pimsleur's licensed lessons.
- After a lesson, let me write five recall prompts and sample answers. Review due prompts with Again, Hard, Good, and Easy buttons using documented intervals stored in SQLite.
- Show the next lesson, due recall count, and a calendar of completed sessions without streak pressure. Let me edit or delete prompts and reset the schedule.
- Export lesson metadata, prompts, reviews, and progress as JSON; keep audio files separately for backup and re-import.
- No accounts, telemetry, speech-scoring claims, licensed curriculum, automated teaching quality, or mobile app parity.
- README: supported audio formats, source-file location, backup and re-import, and the exact spaced-review interval rule.

# AGENTS.md — Build guide for Pimsleur

## Project scope
Organize user-owned audio lessons into a study plan, schedule spaced retrieval practice, and show progress without claiming accredited instruction.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Pimsleur, organize user-owned audio lessons with spaced recall prompts and progress. The hard boundary is licensed audio curriculum, pedagogy, mobile apps, and language catalog, 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
- Python and FastAPI
- SQLite
- HTML5 audio player
- User-owned MP3 or M4A files

## Security and data integrity
- Accept only user-selected local audio files and validate file types
- Keep progress and audio local
- Do not distribute or scrape licensed course content

## Agent implementation rules
- Persist playback position and review history
- Expose the review interval rule and allow corrections

## 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.
- Describe an audio lesson organizer and recall scheduler, without course-content claims

## Engineering roadmap
1. Build audio import, ordered lessons, and resumable playback.
2. Add editable recall prompts and a transparent spaced-review schedule.
3. Export progress and document ownership and curriculum limits.

## Paid-product capabilities outside this build
- licensed audio curriculum, pedagogy, mobile apps, and language catalog
- licensed course catalog
- expert curriculum
- human feedback
- large learner network and certification

## Implementation prompt
Build me a local study player for audio lessons I already own as a limited substitute for Pimsleur. Requirements:

- Use Python, FastAPI, SQLite, and the browser's audio player. Import user-supplied MP3 or M4A files into a selected local folder and record title, language, duration, lesson order, and source filename.
- Show a course list and player with resume position, playback speed, and a completed flag. Never copy or bundle Pimsleur's licensed lessons.
- After a lesson, let me write five recall prompts and sample answers. Review due prompts with Again, Hard, Good, and Easy buttons using documented intervals stored in SQLite.
- Show the next lesson, due recall count, and a calendar of completed sessions without streak pressure. Let me edit or delete prompts and reset the schedule.
- Export lesson metadata, prompts, reviews, and progress as JSON; keep audio files separately for backup and re-import.
- No accounts, telemetry, speech-scoring claims, licensed curriculum, automated teaching quality, or mobile app parity.
- README: supported audio formats, source-file location, backup and re-import, and the exact spaced-review interval rule.

## 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.