pi-go

Index a folder's contents into the MemPalace semantic memory for search and retrieval. Use this skill whenever the user asks to "index a folder", "index a directory", "index memory", "mine a project into memory", "make a folder searchable", "embed a folder", "ingest code into the palace", or "index this directory for semantic search". Covers the full flow: model download, mempalace.yaml room configuration, mining, and verification via search. Also trigger when the user says "memory index", "index memory of folder", or asks how to make a project's code semantically searchable with pi-go's MemPalace.

Lazy senior dev mode — always pick the simplest solution that works. Use this skill whenever writing, refactoring, or reviewing code to keep changes minimal: prefer the standard library, native platform features, and already-installed dependencies over new code or dependencies. Trigger when the user says "ponytail", "keep it simple", "simplest thing that works", "don't over-engineer", "lazy mode", or asks to avoid unnecessary abstractions, boilerplate, or premature complexity. The best code is the code never written.

Before any commit, run linters, vet, tests, and build verification; do not commit until checks pass

Go 1.24–1.26 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2 configuration, slog logging, and manual dependency injection with functional options. Always consult this skill before generating Go code for pi-go, even for small snippets, to ensure every output is idiomatic and modern.

Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.

Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.

Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.

Show MemPalace memory system status — drawer counts, wings, rooms, knowledge graph stats, and embedding model state.

Analyze pi-go session logs (last 24h by default) for tool call errors, deduplicate them, and present a summary table with error patterns and counts.

Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo agent-friendly", "document build/test commands for Claude Code", or uploads a repo and asks Claude Code to learn its conventions. Produces a spec-loose, Claude-Code-optimized AGENTS.md with a shared core section plus short language-specific appendices for the stacks present in the repo.

Rebuild, reinstall and restart the pi binary from source. Use after making changes to pi-go code.

Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm Architecture (Init/Update/View). Also use when the user asks about testing bubbletea components, bubbles, or lipgloss-styled views, or when they need CI-friendly TUI test patterns. Even if they just say "test my TUI" or "add tests to my Bubble Tea app", use this skill.

Pull skills from a remote GitHub repository into the local skills directory. Use when the user wants to install shared skills.

Create a new skill with guided setup. Use when the user wants to create a custom skill for pi-go.