# AGENTS.md — Build guide for LingQ Premium

## Project scope
Import text and optional aligned audio, mark words as known or learning and create review cards with their original sentence. Show reading progress and schedule retrieval practice without promising fluency.

Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For LingQ Premium, import permitted text and audio, mark known words, and review vocabulary in context. The hard boundary is content library, import pipeline, multi-device sync, community, tutors, and polish, 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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first.
- Implementation components: Node.js, TypeScript and Express with server-rendered HTML and small browser modules. SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Scope boundary: content library, import pipeline, multi-device sync, community, tutors, and polish; licensed course catalog

## Stack and architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.
- Domain model: permitted lessons, token offsets, vocabulary lemmas, known-word states, audio segments and review schedules

## Security and data integrity
- Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.
- Correctness boundary: Word offsets refer to a specific lesson revision; ambiguous tokenization can be corrected manually and audio alignment is not guessed as exact.
- Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
- Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

## Agent implementation rules
- Project rule — data model: permitted lessons, token offsets, vocabulary lemmas, known-word states, audio segments and review schedules
- Project rule — preserve this invariant: Word offsets refer to a specific lesson revision; ambiguous tokenization can be corrected manually and audio alignment is not guessed as exact.
- Project rule — acceptance evidence: Edit a lesson and review affected highlights; marking a word known removes future learning cards while retaining its past review history.

## Optional agent skills and references
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

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 the actual LingQ Premium-inspired workflow with owned or clearly labeled sample data: Import text and optional aligned audio, mark words as known or learning and create review cards with their original sentence. Show reading progress and schedule retrieval practice without promising fluency.
- Publish a reproducible walkthrough with this observable result: Edit a lesson and review affected highlights; marking a word known removes future learning cards while retaining its past review history.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: content library, import pipeline, multi-device sync, community, tutors, and polish; licensed course catalog Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import text and optional aligned audio, mark words as known or learning and create review cards with their original sentence. Show reading progress and schedule retrieval practice without promising fluency. Record prerequisites, select representative user-owned fixtures and document the unsupported features: content library, import pipeline, multi-device sync, community, tutors, and polish; licensed course catalog
2. Phase 2 — Durable model. Model permitted lessons, token offsets, vocabulary lemmas, known-word states, audio segments and review schedules Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Word offsets refer to a specific lesson revision; ambiguous tokenization can be corrected manually and audio alignment is not guessed as exact.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Edit a lesson and review affected highlights; marking a word known removes future learning cards while retaining its past review history. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- content library, import pipeline, multi-device sync, community, tutors, and polish
- licensed course catalog
- expert curriculum
- human feedback
- large learner network and certification

## Implementation prompt
WORKING SLICE
Import text and optional aligned audio, mark words as known or learning and create review cards with their original sentence. Show reading progress and schedule retrieval practice without promising fluency.

Build this scoped LingQ Premium-inspired workflow with a documented data model and visible failure states.

Architecture
- Node.js, TypeScript and Express with server-rendered HTML and small browser modules.
- SQLite through better-sqlite3 with migrations, prepared statements and a single background worker.

Prerequisites and limits
A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first.
Outside this release: content library, import pipeline, multi-device sync, community, tutors, and polish; licensed course catalog

Data model and correctness
permitted lessons, token offsets, vocabulary lemmas, known-word states, audio segments and review schedules
Invariant: Word offsets refer to a specific lesson revision; ambiguous tokenization can be corrected manually and audio alignment is not guessed as exact.
Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.

Security and privacy
Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs.

Recovery and export
Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import text and optional aligned audio, mark words as known or learning and create review cards with their original sentence. Show reading progress and schedule retrieval practice without promising fluency. Record prerequisites, select representative user-owned fixtures and document the unsupported features: content library, import pipeline, multi-device sync, community, tutors, and polish; licensed course catalog
2. Phase 2 — Durable model. Model permitted lessons, token offsets, vocabulary lemmas, known-word states, audio segments and review schedules Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Word offsets refer to a specific lesson revision; ambiguous tokenization can be corrected manually and audio alignment is not guessed as exact.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them.
4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. Edit a lesson and review affected highlights; marking a word known removes future learning cards while retaining its past review history. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
Edit a lesson and review affected highlights; marking a word known removes future learning cards while retaining its past review history.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: permitted lessons, token offsets, vocabulary lemmas, known-word states, audio segments and review schedules
Project rule — preserve this invariant: Word offsets refer to a specific lesson revision; ambiguous tokenization can be corrected manually and audio alignment is not guessed as exact.
Project rule — acceptance evidence: Edit a lesson and review affected highlights; marking a word known removes future learning cards while retaining its past review history.

## 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.