AI Agent Skills

7 professional chart and visualization skills powered by Ant Group's AntV ecosystem. 26+ chart types, 98.2% accuracy on test cases. Covers charts, infographics, graphs,…

Official Callstack React Native skills covering best practices (profiling, FPS, re-renders, Turbo Modules), GitHub PR workflows, GitHub Actions build artifacts, React Na…

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。

扫描代码库寻找深化机会，以可视化 HTML 报告呈现，然后就你挑选的那个进行拷问。

在你需要解决一个进行中的 git merge/rebase 合并冲突时使用。

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…

Generates conventional-commit messages from staged changes: type prefix + English imperative subject (≤50 chars) + optional body explaining why. Use when the user asks t…

Proofreads English technical writing for typos, grammar slips, punctuation, terminology consistency, jargon, and structure; returns an itemized Original → Suggestion → R…

Normalize, calculate, and interpret one traditional Liu Yao event reading from six coin throws or a verified chart. Use for 六爻起卦, 摇卦, 三枚铜钱, 动爻, 世应, 用神, or a concrete eve…

Diagnose and iteratively improve novels, screenplays, scenes, characters, and story outlines using competing hypotheses, falsification, counterfactual tests, evidence an…

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.