formsg-ai

The FormSG Oracle — an internal assistant for the FormSG team at Open Government Products (Singapore). Use this skill whenever a FormSG team member asks *why* the product behaves a certain way, asks about past decisions, design rationale, architectural trade-offs, or historical context. Triggers include questions like "why do we do X", "when did we decide Y", "what was the reason for Z", "has this been discussed before", "what does the ADR say about", or any question implying institutional memory about FormSG. Always use this skill — not general knowledge — when answering FormSG product history questions, even if you think you already know the answer.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along four independent axes — Standards, Spec, Architecture, and Divergent design — each run as a parallel sub-agent so contexts stay clean, then verified against false positives and reported side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Assemble a review-ready PR body and inline comments from the breadcrumbs the implementation loop captured, the ADRs in the touched area, and the originating PRD. Use when the user has finished implementation on a branch and wants to ship for review.

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, domain doc layout, and review-prep conventions (commit style and breadcrumb schema). Run before first use of `to-issues`, `to-prd`, `tdd`, `improve-codebase-architecture`, `zoom-out`, or `prepare-for-review` — or if those skills appear to be missing context.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Test-driven development with red-green-refactor loop, including frontend slices verified against a Figma design source via Storybook stories and an agent-browser visual gate. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, asks for test-first development, or wants to implement a UI/component/page from a Figma design.