AI Agent Skills

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multipl…

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at onc…

Use when starting any conversation - establishes how arkhe skills bootstrap on Claude Code, Antigravity CLI (agy) / Gemini CLI, and Codex CLI, and maps Claude-only tools…

Use when bringing up bare-metal or kernel code on a new architecture, SoC, or board (RISC-V, ARM, x86, ESP32) and it won't boot, hangs after boot, or faults early; cover…

Use when building or debugging a compiler backend, codegen, or assembler and you need to prove the generated machine code is correct by executing it on a real CPU or a f…

Use when writing hardware, firmware, verification, or tooling code that will reach real silicon, and you face a tradeoff between shipping fast and shipping correct; cove…

Route safe 1C:Enterprise development work involving an infobase, configuration metadata, selective object export, configuration extensions, Designer batch mode, BSL chan…

审查自某个固定基点（commit、分支、tag 或 merge-base）以来的改动，沿两条轴进行——标准（代码是否遵循本仓库记录的编码规范？）和规格（代码是否符合源头工单/规格的要求？）。两项审查在并行子 agent 中运行，并把结果并排报告。当用户想审查一个分支、一个 PR、进行中的改动，或要求「审查自 X 以来」时使用。

Use when user says "paleo mode", "save tokens", "be brief", "terse", "compress output", or says "paleo". Switch agent to terse replies that cut output tokens ~50-70% (me…

Control the user's Firefox from a terminal. Use when your task needs the user's browser or authenticated session, page navigation, tab/window control, screenshots, DOM r…

FabRelay is an unofficial JLC China (嘉立创, jlc.com) CLI skill for PCB/Gerber upload, preview, manufacturing parameters, quotes, orders, login and QR login. Use fabrelay f…

Collect and inspect local logs with the log-print Rust CLI. Use for file following, program stdout/stderr capture, existing tmux pane output, bounded stream reads, and r…

Five-axis code review checklist (correctness, security, readability, performance, test coverage) producing actionable comments instead of style nitpicks. Use when the us…

Investigate browser bugs with a StatePort State Card, inspect console and replay evidence, and verify code fixes by reopening and comparing the same saved reproduction.

Replay a StatePort Card's recorded Journey on retained source or current local code, inspect its steps and progress, and explain the terminal outcome.

Investigate StatePort replay mismatches or test frontend behavior with request remaps, replay/block/local-live routes and JSON response overlays, then compare or restore…