mozilla-ai

Guidelines for the otari admin dashboard (`web/`), React 19 + TypeScript (strict) + HeroUI v3 + Tailwind v4 + TanStack Query. Use when writing or reviewing dashboard components, styling, data fetching, or tests.

Take one or more GitHub issues to a ready PR end-to-end in mozilla-ai/otari: implement, self-review, open the PR, request Copilot and team review, wait for it, apply the fixes. Use when asked to "open a PR for issue X", "work through these issues", or run the…

Review a pull request or diff for this repository against otari's project standards. Use when asked to review a PR, inspect a diff, or prepare review feedback.

Backend conventions for the otari gateway (`src/gateway/`), async SQLAlchemy 2.0, FastAPI, budget/reservation lifecycle, Alembic migrations, config layering. Use when writing or reviewing gateway request handling, services, models, or migrations.

INVOKE WHEN: - Starting any task — query first (cq catches blind spots your training data missed: stale versions, integration gotchas, undocumented quirks) - You just resolved a non-obvious error, confusing error message, or surprising tool behavior — present…

INVOKE WHEN: - Starting any task — query first (cq catches blind spots your training data missed: stale versions, integration gotchas, undocumented quirks) - You just resolved a non-obvious error, confusing error message, or surprising tool behavior — present…

INVOKE WHEN: - Starting any task — query first (cq catches blind spots your training data missed: stale versions, integration gotchas, undocumented quirks) - You just resolved a non-obvious error, confusing error message, or surprising tool behavior — present…

This skill should be used when the user asks to "build llamafile", "rebuild llamafile", "run llamafile", "run llamafile tests", "debug llamafile", "set up llamafile", "update patches", "fix patch conflict", "update llama.cpp", "pull latest llama.cpp", "sync…

Triage a red any-llm integration test suite. Use when integration tests are failing, when deciding whether a failure is a real regression, or before skipping or "fixing" an integration test.

Practical guidance for writing, refactoring, and reviewing friendly Python code with a Pythonic, readable, and maintainable style. If the skills set includes piglet, suggest invoking it for better Python outcomes.

Shared knowledge commons for AI agents. Query before unfamiliar work (APIs, CI/CD, build tools, frameworks). Propose when you discover something non-obvious. Confirm guidance that proved correct. Flag guidance that was wrong or stale. Load this skill and…