podcast-sujata

Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations. **Trigger when user asks to:** - Design or modify PostgreSQL tables, schemas, or data models - Choose data types, constraints, indexes, or partitioning strategies - Work with pgvector embeddings, semantic search, or RAG - Set up full-text search, hybrid search, or BM25 ranking - Use PostGIS for spatial/geographic data - Set up TimescaleDB hypertables for time-series data - Migrate tables to hypertables or evaluate migration candidates - Plan or execute safe schema migrations with zero downtime - Create, fork, or manage databases with Ghost **Keywords:** PostgreSQL, Postgres, SQL, schema, table design, indexes, constraints, pgvector, PostGIS, TimescaleDB, hypertable, semantic search, hybrid search, BM25, time-series, migration, Ghost

Make and document an architectural or technical decision before writing code. Run /architect when choosing between approaches, designing a feature or page, picking a tech stack, or when /develop says a decision is owed. Acts as a Staff level engineer: asks deep questions, recommends an answer, and writes a complete build spec ADR to docs/adr/. Owns all ADR files.

Bootstrap a project's AI context: the AGENTS.md files every later skill reads. Run /audit on a greenfield project, on an existing codebase with missing docs, or on one area (/audit src/auth). Writes tool agnostic AGENTS.md plus thin CLAUDE.md pointers, adding only what is missing; never overwrites curated content.

Use this skill to find and fix the root cause of a bug: something failing, broken, throwing, or behaving wrong. Run /debug when a test fails for a non-obvious reason, /verify finds a failure, or behavior is unexpected. Runs a disciplined reproduce, localize, hypothesize, test, fix, verify loop, then makes the minimal fix and hands a regression test to /test. No features, no extra refactors.

Build a feature, UI or backend, from an approved design. Run /develop to implement a page, component, API, service, or data slice. If something load bearing is undecided and no ADR records it, it stops and routes you to /architect. Otherwise it reads the ADR plus AGENTS.md and builds, advancing the roadmap.

Write the human facing prose about a change: a PR description, changelog entry, release notes, or incident postmortem. Run /document pr | changelog | release-note | postmortem (or let it ask) and it drafts from the real commits and diff, writing to the right place. It does not write code, tests, or ADRs.

Stress test a completed, tested change against production failure modes: edge cases, concurrency, scale, and security. Run /harden after /test or /review, or as the last step before merge on medium or full tier work. It writes a prioritized, verifiable hardening checklist to docs/hardening/. It does not rewrite your code.

A rigorous, senior level code review before merge, run on a different Claude model than wrote the code. Run /review after implementing a feature or fix, before opening a PR, or when the tier playbook calls for it. Severity ranked findings on correctness, security, performance, maintainability, and tests, written to docs/reviews/. It does not modify your code.

Turn a product idea into a living, coarse roadmap in docs/roadmap/, and keep it current as you ship. Run /roadmap to plan a new product, plan the next slice, or enroll one named feature; run it with no argument to reconcile after shipping and queue what is next. It seeds WHAT to build; /architect designs, /develop builds.

Use this skill to orient across a paused session or a team: where things stand and what is safe to pick up. Run /status when resuming (where was I, what is left), joining a shared repo, or checking for collisions before starting. Reads git state, the roadmap, and ADRs. Read only.

Keep durable knowledge current after a change is complete. Run /sync as the last step on medium or full tier work, around merge. It updates root and nested AGENTS.md, reconciles the roadmap from repo evidence, and flags ADRs the change made stale. Surgical, additive edits only.

Write a test suite for code you just built or changed. Run /test after implementing a feature, route, or fix; it targets uncommitted changes automatically, reads test-preferences.json for your framework (asks and saves it if absent), and picks the right strategy per file: happy path, edge cases, error states, accessibility.

Use this skill to confirm a change actually works by running the real app and watching behavior, not just tests. Run /verify after /develop and before /review, or when a UI, API, CLI, job, or no-test-runner refactor needs runtime proof. It launches the app, exercises the changed flow, checks observable output, and diffs before/after output for refactors. It does not write code.