yugabyte

Use when scripting, automating, or troubleshooting the YugabyteDB Anywhere (YBA) REST API — the control-plane API for self-managed YBA instances that creates and manages providers, releases, universes, backups, KMS, and DR. Triggers on `/api/v1/`, `/api/v2/`,…

Use when scripting, automating, or querying YugabyteDB Aeon (YugabyteDB Managed cloud) via its REST API — including listing and scaling clusters, managing database users, configuring network allowlists, reading cluster metrics, managing backups, and working…

Offline review of an existing YugabyteDB YSQL schema and data model from evidence captured on the running database: a ysql_dump of the schema, plus pg_stats, pg_stat_statements or a query list, row counts and planner settings when available. Finds key and…

Checks the YugabyteDB-specific performance traps that general database and monitoring knowledge misses, and the evidence required before concluding. Use when an app, site or database on YugabyteDB is slow, latency is up, p99 regressed, someone asks "is the…

Use when writing or reviewing SQL, schema definitions, or application code that targets YugabyteDB's PostgreSQL-compatible YSQL API (port 5433). Triggers on CREATE TABLE, indexes, connections, transactions, sharding, migrations from PostgreSQL, or any mention…

Use this skill when building RAG, semantic search, or hybrid (vector + full-text) search on YugabyteDB with LangChain — including PGVectorStore setup, vector/GIN index creation, hybrid search configuration, metadata filtering, and relational + vector queries.…

Use when provisioning, managing, or troubleshooting YugabyteDB universes on Kubernetes via the YugabyteDB Kubernetes Operator and YugabyteDB Anywhere CRDs (YBUniverse, YBProvider, Release, Backup, StorageConfig, PitrRestore, DrConfig, etc.). Triggers on…

Use when writing, generating, or troubleshooting Terraform that drives YugabyteDB Anywhere (YBA) via the `yugabyte/yba` provider — installing YBA on a VM, registering the first customer, and creating cloud (AWS/GCP/Azure) or on-prem providers, storage…

Create a Pull Request for the current branch's changes. Use when the user wants to publish a branch for review as a GitHub PR.

Choose and run cargo-pgrx commands, pgrx tests, pg_test coverage, and pg_sys boundary checks.

The code style guide for YugabyteDB's PostgreSQL fork: required conventions for ANY change under src/postgres -- follow upstream PostgreSQL's rules, explicit and implicit, while isolating and marking the YB delta so that the diff/merge tooling (git, Phorge,…

Create a YugabyteDB Phorge diff for the current branch's changes. Use when the user wants to publish their changes for review.

Query a running YugabyteDB Anywhere (YBA) control plane using the `yba` CLI (managed/yba-cli) — list/describe universes, tasks, backups, providers, alerts, users, storage/EAR/EIT configs, xClusters, RBAC, runtime config, telemetry providers, and more. Use…

Review YugabyteDB backport diffs by comparing them against their original commits/diffs. Use when the user provides a Phorge backport diff ID (e.g. D51405) and wants to verify the backport is correct, or when reviewing backport revisions.

Create a GitHub issue (or JIRA ticket) tracking a YugabyteDB change or bug. Use when the user needs a tracker reference and doesn't have one yet — e.g. before opening a PR/diff, or to file a standalone bug/feature request.

Instrument YugabyteDB ASH (Active Session History) wait states: add a new WaitStateCode, choose the right macro for synchronous vs asynchronous/callback code paths, register background trackers, plumb ASH metadata through RPCs, and test with…

Behavioral guide for Meko MCP tools on desktop Claude. READ IT BEFORE calling any meko tool — it sets the required agent_id and workflow; calling a meko tool without it produces wrong-bucket writes. Use whenever the user mentions memory, Meko, datapacks,…

Behavioral guide for AI agents using Meko MCP tools. Triggers when calling MCP tools, storing memories, persisting knowledge, managing datapacks, or searching shared knowledge bases through Meko.

Use Meko long-term memory and team knowledge from Kiro. Covers session setup without hooks, recall with memory_search and context_search, saving and correcting memories, datapack routing, knowledge-base search, sharing memories with memory_promote, and error…

Lists the user's Meko datapacks, shows authorization, supports search and pagination, and pins one as the active datapack on Claude Desktop. Triggers when the user says things like "switch datapack", "use the Acme datapack", "list my datapacks", "which…

Lists the user's Meko datapacks, shows authorization, supports search and pagination, and pins one as the active datapack for the current project. Triggers when the user says things like "switch datapack", "use the Acme datapack", "list my datapacks", "which…

Recalls relevant Meko experience for an in-progress BMad workflow. Given a workflow name, the current objective, and an optional focused query, it searches Meko memories and (when a datapack is active) shared knowledge for prior decisions, constraints,…

Publishes finalized BMad artifacts and one concise learning summary to the active Meko datapack after a BMad workflow has written its local output. Uploads permitted files via artifact_put and stores a single deduplicated memory_add summary of the durable…

Sets up, configures, inspects, and uninstalls the Meko integration for the BMad Method. Verifies the installed BMad version, detects the Meko MCP connection, selects a datapack, and wires Meko recall (and, after explicit consent, artifact publishing) into…

Review all code changes on the current branch compared to main, applying the hierarchical AGENTS.md engineering standards from each changed file's directory up to the repo root. Use when the user asks to review a branch, review changes, compare against main,…

Post a single non-blocking GitHub PR review with inline line-anchored comments generated by the agent. Every comment is prefixed with `[AI]` plus a severity tag so reviewers can tell they are AI-generated and triage at a glance. Critical, Warning, and…

Bump YugabyteDB latest_stable in yb-versions.json, coordinate Jenkins migtest cluster upgrades, fix version-gated issue/integration tests, and open a PR only after all GitHub Actions pass. Also covers bumping the bundled CDC connector version in…

Sweep recently updated open GitHub PRs that need an AI review — never reviewed, or with new commits since the last AI review (incremental re-review, at most once per 24h) — running the branch-review skill and posting findings with the post-pr-review skill;…

Create and update GitHub pull request descriptions using the project PR template. Use when the user asks to create a PR, write a PR description, update a PR description, or manage pull requests.

Generate yb-voyager release notes from a commit range, formatted like the YugabyteDB Voyager release-notes docs page. Use when the user asks to draft release notes, summarize a release, or write what's-new entries for a voyager version.

Interactive git rebase workflow with conflict-by-conflict review. Use when the user asks to rebase a branch, rebase onto main, resolve rebase conflicts, or update a branch with upstream changes.

Creates new FeatureBench microbenchmarks for YugabyteDB's benchbase regression pipelines. It turns a plain-language requirement into an approved plan, picks the category and next file name, writes the yugabyte YAML, derives the postgres / yb_colocated /…

Creates new FeatureBench microbenchmarks for YugabyteDB's benchbase regression pipelines. It turns a plain-language requirement into an approved plan, picks the category and next file name, writes the yugabyte YAML, derives the postgres / yb_colocated /…

How a canned agent in this repo should call Meko's MCP tools correctly — the conversation lifecycle (conversation_create then thread conversation_id through every subsequent call), resolving the right MCP endpoint for the deployment's environment instead of…