| name | semantic-search |
|---|---|
| description | Search the vault using semantic query expansion and intelligent result ranking. Use when the user asks questions about vault contents, searches for topics, or needs to find related notes. |
| user_invocable | true |
Search using LLM-powered query expansion and intelligent result synthesis. No vector database required.
| name | ast-grep-search |
|---|---|
| description | Syntax-aware code searching that understands code structure rather than just text patterns. Always prefer ast-grep than grep for code searches. |
| allowed-tools | Read, Grep, Bash(ast-grep:*), Bash(sg:*) |
ast-grep allows searching code based on its Abstract Syntax Tree (AST), enabling syntax-aware pattern matching. It is ideal for finding function calls, method invocations, variable declarations, and other code structures while respecting language syntax.
Bit about me: <redacted personal info that is easily googleable anyway lol>
Your role: Functional, TDD-first, curiosity-prodding developer who balances correctness, performance, and clarity. Act as a precise pair programmer; when tradeoffs arise, list brief pros/cons and pause for direction.
Important: Refer to me as "Peter" in conversation, not "the user".
Curiosity cue: after each reasoning step, ask yourself: “What am I missing? What are the alternative designs? What could break, or be broken into? How might this be simpler or more concise?”
| DEVELOPER TASK SPEC (FOR DEVIN) | |
| Project: Build a real Linux terminal emulator “from scratch” inside repo andrewgcodes/mochi. | |
| Goal: A genuine VT/xterm-style terminal emulator that runs a real shell/apps via a PTY, correctly parses escape sequences, maintains a screen model, and renders a GUI. No wrapping an existing terminal widget/library/implementation. | |
| ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ | |
| 0) NON-NEGOTIABLE RULES (READ FIRST) | |
| ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ | |
| R0.1 — No cheating / no “terminal emulator libraries” | |
| - You MUST NOT depend on any library that implements terminal emulation, ANSI/VT parsing, or screen-model logic for you. | |
| - Examples of forbidden dependencies (non-exhaustive): |
| [[Snippets]] | |
| Description = "repeat the previous command" | |
| Output = "" | |
| Tag = [] | |
| command = "!!" | |
| [[Snippets]] | |
| Description = "Runs last command" | |
| Output = "" |
| [colors.bright] | |
| black = "0x7f7f7f" | |
| blue = "0x5c5cff" | |
| cyan = "0x00ffff" | |
| green = "0x00ff00" | |
| magenta = "0xff00ff" | |
| red = "0xff0000" | |
| white = "0xffffff" | |
| yellow = "0xffff00" |
| --- SmartPick - Enhanced file and buffer picker with intelligent highlighting | |
| --- ========================================================================== | |
| --- | |
| --- A unified file/buffer picker for Neovim that combines buffer and file search | |
| --- into one intelligent interface. Built on mini.nvim ecosystem (mini.pick). | |
| --- | |
| --- ## Problem It Solves | |
| --- - Eliminates "picker paralysis" - no more choosing between buffer vs file picker | |
| --- - Shows everything in one list: buffers (by recency) → files (alphabetically) | |
| --- |
FOREWORDS
I don't mean the snippet at the bottom of this gist to be a generic plug-n-play solution to your search needs. It is very likely to not work for you or even break things, and it certainly is not as extensively tested and genericised as your regular third-party plugin.
My goal, here and in most of my posts, is to show how Vim's features can be leveraged to build your own high-level, low-maintenance, workflows without systematically jumping on the plugins bandwagon or twisting Vim's arm.
AGENTS.md has emerged as the de facto open standard for guiding AI coding assistants, now adopted by over 20,000 repositories and formalized in August 2025 through collaboration between OpenAI, Google, Cursor, Factory, and Sourcegraph. This file acts as a "README for machines"—providing structured, technical context that helps AI assistants write better code from the start. For Python + AWS + Terraform projects, a well-crafted AGENTS.md dramatically reduces friction, ensuring generated code follows your conventions, uses the right tools, and adheres to security requirements.
AGENTS.md is a dedicated Markdown file that complements, not replaces, README.md. While README targets human developers with project overviews and quick-start guides, AGENTS.md contains detailed technical instructions specifically for AI coding agents. Think of it as onboarding documentation for an AI team member: ex