jiyuu

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Reference for what GitHub issue/PR labels mean in this workspace (S-triage, S-needs-scope, S-impl, prio-p0-critical, A-dev-tools, and others under My Labels). Use when the user asks what a label means, which label to apply, or how to add missing labels to a repo with `gh label create --force`. Secondary: bootstrap labels on a new repo that does not have them yet.

Writes clear pull request descriptions from the current branch diff against a base branch. Defaults to `main`, but supports `dev` or any other user-specified comparison branch. Use when the user asks for a PR description, pull request summary, or a markdown write-up for changes against a base branch.

Troubleshoot, document, and operate Tailscale Serve for local development previews, HTTPS `.ts.net` URLs, MagicDNS, admin-console HTTPS certificate setup, WSL or localhost proxy targets, phone testing over a tailnet, and curl/OpenSSL diagnosis of Serve TLS failures. Use when a user says Tailscale Serve, `tailscale serve`, `.ts.net`, MagicDNS, HTTPS certs, SSL protocol error, TLS alert, Funnel versus Serve, localhost preview, Next.js preview over Tailscale, or sharing a dev server with a phone or another tailnet device.

Query and reconcile Sai perps data across live Perp, Oracle, and SLP Vault contracts; Sai Keeper GraphQL; DexPal REST; sai-keeper Postgres; and referral records. Use for markets, open interest, fees, trades, vault health, oracle prices, REST statistics, database-backed metrics, referral ownership or history, trading-credit balances, app/indexer behavior, or mismatches between chain, APIs, databases, sheets, and operator records. Keep mutations and private operator workflows in sai-ops.

Prefer the nearest relevant `justfile` as the default command surface for build, test, lint, format, run, deploy, and repo automation workflows. Use when a repo or subproject has a `justfile`, or when the user mentions `just`, `justfile`, recipes, or Makefile-to-just migration.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman language", "less tokens", "be brief", or invokes /lang-caveman.

Create new skills, modify and improve existing skills, and run lightweight review loops. Use when users want to create a skill from scratch, edit an existing skill, try realistic test prompts, or improve when and how a skill should trigger.

Watch GitHub PR checks with gh, poll until green/failure/timeout, fetch failed GitHub Actions logs, save logs locally, summarize actionable CI failures, and apply trivial local fixes when safe. Use when the user asks to watch PR checks, wait for CI, inspect failed actions, fix obvious CI failures, or summarize gh pr checks results.

Validate GitHub Actions workflow YAML with actionlint when editing files under `.github/workflows/`, checking CI workflow syntax, diagnosing GitHub Actions expression or schema errors, or when the user asks to lint/check Actions workflows. Prefer `bunx github-actionlint` when `bun` is available and fall back to `npx --yes github-actionlint`; use this proactively after modifying GitHub Actions workflows.

Apply consistent Markdown checkbox task conventions in READMEs, epics/journals, specs, and design docs. Use when the user wants task lists with "- [ ]" / "- [x]", nested subtasks, context sub-bullets under items, or terminal commands (grep/rg) to list open versus completed tasks in Markdown files — especially in repo documentation and planning Markdown.

Query EVM JSON-RPC methods for transaction debugging and endpoint triage, including eth_getTransactionReceipt and debug_traceTransaction. Use when the user asks to inspect tx status, retrieve receipts, run tracers, compare EVM vs Cosmos outcomes, or choose between EVM RPC and Comet RPC endpoints.

Interview the user relentlessly about a plan, spec, or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "drill the spec" or "drill the plan".

Maps and routes between key repositories on my machine (boku, nibi-chain, nibi-geth, nibi-go-hm, nibi-ts-sdk, sai-website, sai-perps, nibi-iac, nibi-home-site, gh-io-ud, wasm-cosmwasm, wasm-go-wasmvm). Use when the user asks which repo to look at, where a feature lives, how repos connect, how services are deployed (Terraform/IaC), when a task spans chain, EVM, indexer, SDK, frontend, and docs, or when the user asks about the personal site, blog posts, official Nibiru docs, or Astro/gh-pages.

Query Nibiru chain state and submit transactions with the `nibid` CLI, including setup via `ud`, config inspection, key discovery with `nibid keys list`, bank transfers, bank balance queries, EVM multi-VM balance checks such as `nibid q evm balance` for Sai USDC, wasm contract queries, wasm execute/instantiate flows, and transaction lookups by hash. Use when the user mentions `nibid`, Nibiru CLI, `nibid keys list`, `--from`, `nibid tx bank`, `nibid tx wasm`, `nibid q bank`, `nibid q evm balance`, `nibid q wasm`, `nibid q tx`, balances, contract-state smart, or tx hashes.

Writes a ready-to-paste prompt for a fresh chat instead of completing the requested task directly. Use when the user asks to start a new chat, move work to a new chat, or says to write a prompt for tackling the task elsewhere.

Improve technical writing for specs, implementation notes, READMEs, engineering references, and agent-authored docs. Use when drafting, editing, reviewing, or polishing technical prose; when the user mentions technical writing, style, clarity, ambiguity, specs, docs, documentation, or Google developer docs; or when docs contain many code symbols, database names, API endpoints, GraphQL schema items, commands, or skills.

Review GitHub pull requests for correctness, design quality, test coverage, security, performance, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

Discover, read, and manage Epics+ markdown documents in the boku repository. Use when asked about active tasks, priorities, epics for specific repos or tags, or when needing to regenerate the epic index (INDEX.md) using the epics-plus CLI.

Queries Nibiru governance proposals (including software-upgrade proposals) using the `nibid` CLI, maps explorer UI fields to on-chain queries, computes quorum/threshold/veto metrics, and correlates validator votes using staking queries. Use when the user mentions `nibid q gov`, governance proposals, software upgrades, votes, deposits, tally, quorum/threshold, validators, proposal status, or `nibid tx gov`.

Queries the Nibiru indexer (Heart Monitor) for user account and balance data. Use when querying user balances by address, the user/users root fields, Token amounts, or HeartMonitor.user/users in the TS SDK.

Use when the user asks about the Nibiru indexer (Heart Monitor), staking GraphQL schema, GQLValidator, GQLDelegation, HeartMonitor, or querying staking data via GraphQL. Explains that staking is under query.staking, not root-level deprecated fields; rewards come from the chain (distribution), not the indexer; amounts are Int in base units (e.g. unibi).

Comprehensive guide for PostgreSQL psql - the interactive terminal client for PostgreSQL. Use when connecting to PostgreSQL databases, executing queries, managing databases/tables, configuring connection options, formatting output, writing scripts, managing transactions, and using advanced psql features for database administration and development.