pi-public

Use when managing per-project backlog folders, feature queues, async agent work items, lifecycle status updates, PR/done/blocked transitions, or status reviews inside an Obsidian vault.

Use when prototyping, authoring agent skills, or asking the agent to zoom out and map unfamiliar code before acting.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Use when reviewing architecture boundaries, hexagonal architecture, clean architecture layers, dependency direction, trust boundaries, uploads, parsers, redirects, or web security risks.

Use when configuring or running hexcheck in a Go repo for hexagonal architecture boundaries, adapter business-logic warnings, and mock discipline.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Use when requesting or receiving code review, dispatching review subagents, running CodeRabbit, deep reviews, simplification/cleanup passes, local branch review, ready-for-PR/finalize intent, finalizer workflow, or preparing work for merge.

Use when running CodeRabbit CLI code reviews, reviewing uncommitted or committed changes, comparing branches, or authenticating with CodeRabbit. Triggers on "code review", "cr review", "coderabbit", "review my changes", "review this branch".

Use when asked for a deep code review, thorough review, security audit, full review of changes, or pre-merge review. Triggers on "deep review", "thorough review", "audit my code", "review for security", "check for bugs", "review before merge".

Use when the user asks to run the Finalizer workflow, execute the finalizer skill, or finalize a branch through the finalizer subagent. Gathers the exact checkout context and then invokes the `finalizer` subagent correctly.

Use as the default instruction set for simplification review subagents after code changes. Dispatches focused reviewers for reuse, quality, and efficiency so changed code gets cleaned up before completion.

Use when finishing an implementation or plan phase and you want an adaptive workflow-driven review before calling the work done, especially to catch logic bugs, legacy/YAGNI leftovers, DI boundary leaks, weak tests, or hot-path waste without launching unnecessary reviewers.

Use when a documentation pass is needed or docs, README, guides, examples, changelogs, or public explanations may be stale before PR.

Use when starting work in an unfamiliar repository, onboarding to a codebase, doing repository reconnaissance, or needing project-wide context before planning, editing, debugging, refactoring, or review.

Use when working with Astro, Svelte, SvelteKit, Svelte 5 runes, htmx, shadcn-svelte, frontend routing, UI forms, web client behavior, or Charm Bubble Tea/Bubbles/Lip Gloss/Huh Go terminal UIs.

Use when building, debugging, migrating, or creatively designing Go terminal UIs with Charm Bubble Tea v2, Bubbles v2, Lip Gloss v2, Huh v2, tea.View, layers, mouse, forms, tables, lists, text input, viewport, spinners, progress, or charm.land imports.

Use when working with GitHub Actions workflows, reusable workflows, Dependabot, pull requests, PR review comments, CodeRabbit review feedback, PR checks, PR diff context, or GitHub GraphQL/API data.

Use when summarizing GitHub PR checks, pending/failing CI status, check links, and suggested gh run commands without downloading noisy logs by default.

Use when gathering compact GitHub pull request diff context, changed files, refs, commits, or a bounded diff for review/verification work.

Use when turning the github-pr-review-comments JSONL index, including CodeRabbit PR review comments captured there, into an action queue with must-fix, verify-first, duplicate, informational, and human-decision buckets.

Use when retrieving GitHub pull request review feedback, inline review comments, review replies, review threads, CodeRabbit comments, or converting PR review discussions to Markdown or searchable JSONL.

Use when verifying PR review findings against the local checkout by producing snippets and a human verification worksheet without claiming automatic truth.

Use when improving visual design, interface quality, dashboards, SaaS positioning, landing page copy, UX text, documentation, explanations, or other human-facing writing.

Use before committing to architecture, interface, migration, rollout, or consequential decisions, especially for critic/red-team passes.

Use when writing or reviewing backend or systems code in Go, Rust, Odin, Zig, or database layers, including idioms, stdlib usage, schema design, queries, transactions, mocks, and tests.

Use when writing, reviewing, or debugging Drizzle ORM code — schema definitions, queries, mutations, relations, migrations, transactions, or any project using drizzle-orm with PostgreSQL, MySQL, SQLite, Turso, Neon, D1, or other supported databases

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

Use when writing, porting, or reviewing Zig code against recent 2026-era Zig versions, including Zig 0.16+ language changes, std.Io, build system changes, stdlib API shifts, testing, and idiomatic modern Zig patterns.

Use when writing, reviewing, debugging, or researching Odin programming language code, packages, tests, memory management, foreign bindings, or standard/vendor library usage.

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.

Use when writing tests, practicing TDD, debugging failures, flaky tests, Go Delve sessions, Go mocks, Rust tests, Go tests, or verifying changes before claiming success.

Use when writing, reviewing, or refactoring Svelte 5 components or SvelteKit apps that use runes, shared state, file-based routing, load functions, remote functions, forms, hooks, navigation, or environment modules.

Use when adding or modifying GitHub Actions workflows, reusable workflows, CI, Go releases, frontend checks, Dependabot updates, Dependabot auto-merge, or Discord notifications in Alex's repositories.

Use when scanning a repo for hexagonal architecture violations, reviewing code placement across layers, auditing dependency direction, or checking port hygiene. Triggers on "hex arch", "ports and adapters", "clean architecture layers", "domain imports infrastructure", "business logic in adapter", "wrong layer", "missing port".

Use when auditing, reviewing, or modifying web applications where untrusted data crosses trust boundaries — including request handlers, parsers, renderers, document importers, file uploads, redirects, API endpoints, webhooks, and multi-step feature chains. Also use when reviewing framework defaults, content-type handling, or feature composition that could chain into vulnerabilities.

Use when building or updating Astro sites, components, content-driven pages, islands, content collections, view transitions, or Astro server features such as SSR, actions, API routes, middleware, and adapters.

Use when writing, reviewing, or debugging htmx code -- building hypermedia-driven UIs with hx-get, hx-post, hx-swap, hx-trigger, hx-target, hx-boost, hx-partial, hx-status, hx-action, morph swaps, SSE, WebSockets, htmx events, htmx extensions, or any project using htmx attributes. Covers htmx 4.x API.

Use when adding, using, or customizing shadcn-svelte components in a Svelte or SvelteKit project, or when you need to look up component APIs, install commands, or underlying package docs for bits-ui, formsnap, paneforge, vaul-svelte, embla-carousel, or svelte-sonner.

Use when building distinctive, production-grade frontend interfaces — components, pages, or full applications. Guides bold aesthetic direction and real working code with exceptional design quality.

Use for interface design -- dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces. NOT for marketing design (landing pages, marketing sites, campaigns).