Guru

Build me a focused enterprise knowledge workflow for the personal core of Guru. Requirements:

- Use exactly this stack: Next.js 15 + TypeScript + SQLite. Model projects, tasks, schedules, status transitions, and completion history; keep stable source IDs and timestamps.
- Paid product context: Verified knowledge cards and AI search embedded in work tools. Build only this DIY scope: Build a single-user enterprise knowledge workspace with projects, tasks, statuses, filters, recurring items, and JSON export.
- For enterprise knowledge, create projects, tasks, statuses, due dates, and recurrence rules with stable IDs.
- Move a task through its workflow and generate only the next valid recurring occurrence.
- Filter the work list and export tasks with state and completion history.
- Use a local web page with input, progress, review, and export views. Required input or access: local or self-hosted runtime.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: Restarting the scheduler must not duplicate recurring tasks; completed items must retain their history.
- Out of scope: mobile capture and notifications; real-time multiplayer. 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 Guru

## Project scope
Build a single-user enterprise knowledge workspace with projects, tasks, statuses, filters, recurring items, and JSON export.

Catalogue verdict: no. Do not mistake the interface for the product. Guru's durable value is collaboration, integrations, polish, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
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
- Node.js 22
- local or self-hosted runtime
- SQLite database
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Next.js 15 + TypeScript + SQLite.
- Model projects, tasks, schedules, status transitions, and completion history; keep stable source IDs and timestamps.
- Interface for this enterprise knowledge workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- Restarting the scheduler must not duplicate recurring tasks; completed items must retain their history.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: mobile capture and notifications.

## Agent implementation rules
- Project rule, data: Model projects, tasks, schedules, status transitions, and completion history; keep stable source IDs and timestamps.
- Project rule, behavior: For enterprise knowledge, create projects, tasks, statuses, due dates, and recurrence rules with stable IDs.
- Project rule, recovery: Restarting the scheduler must not duplicate recurring tasks; completed items must retain their history.

## 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 enterprise knowledge operation with sample or user-owned data: For enterprise knowledge, create projects, tasks, statuses, due dates, and recurrence rules with stable IDs.
- Show a concrete result or export: Filter the work list and export tasks with state and completion history.
- State the practical limit: mobile capture and notifications.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Next.js 15 + TypeScript + SQLite. Model projects, tasks, schedules, status transitions, and completion history; keep stable source IDs and timestamps.
2. Phase 2, implement: For enterprise knowledge, create projects, tasks, statuses, due dates, and recurrence rules with stable IDs.
3. Phase 3, implement: Move a task through its workflow and generate only the next valid recurring occurrence.
4. Phase 4, review and output: Filter the work list and export tasks with state and completion history.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: Restarting the scheduler must not duplicate recurring tasks; completed items must retain their history. State the practical limit: mobile capture and notifications.

## Paid-product capabilities outside this build
- mobile capture and notifications
- real-time multiplayer
- enterprise permissions
- large integration catalog

## Implementation prompt
Build me a focused enterprise knowledge workflow for the personal core of Guru. Requirements:

- Use exactly this stack: Next.js 15 + TypeScript + SQLite. Model projects, tasks, schedules, status transitions, and completion history; keep stable source IDs and timestamps.
- Paid product context: Verified knowledge cards and AI search embedded in work tools. Build only this DIY scope: Build a single-user enterprise knowledge workspace with projects, tasks, statuses, filters, recurring items, and JSON export.
- For enterprise knowledge, create projects, tasks, statuses, due dates, and recurrence rules with stable IDs.
- Move a task through its workflow and generate only the next valid recurring occurrence.
- Filter the work list and export tasks with state and completion history.
- Use a local web page with input, progress, review, and export views. Required input or access: local or self-hosted runtime.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: Restarting the scheduler must not duplicate recurring tasks; completed items must retain their history.
- Out of scope: mobile capture and notifications; real-time multiplayer. 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.