ask-matt
免费Ask which skill or flow fits your situation. A router over the skills in this repo.
中文简介正在准备中。当前显示原文说明。
Simplify and summarise the last reply to what matters, in plain words, with a confidence letter on every claim.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Rewrite the reply as the answer to the question I asked before it. Keep the answer, then only what changes what I do next: decisions, to-dos, suggestions. Drop the rest; when I want detail, I will ask.
$ARGUMENTS is one of three things. Empty: the target is your whole last
reply. Pasted text: that text is the target. An instruction: it narrows the
target within your last reply, or changes how to treat it, as in
/ss only the paragraph about data.
Both at once: an instruction on the first line, a blank line, then the pasted text it applies to.
Tie-break: a single short line is an instruction; anything longer is pasted text. When still unsure, ask before writing, with AskUserQuestion: quote the part you read as the instruction, offer "Treat as instruction" and "Treat as pasted text", and let me type more instead.
ASD-STE100 Simplified Technical English: one idea per sentence, under 20 words, active voice, everyday words. A technical term appears only as a verbatim reference to something specific: a function, a variable, a file path, a ticket ID.
Wrap a solution, or an interpretation of a problem, whole, with a letter at the start for how sure you are: H, M or L for high, medium, low. Plain information carries no letter. The wrapped text stays inside the flow of the sentence or paragraph it belongs to.
The build fails on the second run only. [M - the cache keeps the old lockfile,
so the install step skips the new package] The fix: [H - clear the cache
before the install step].
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Ask which skill or flow fits your situation. A router over the skills in this repo.
中文简介正在准备中。当前显示原文说明。
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
中文简介正在准备中。当前显示原文说明。
Run comprehensive agent-native architecture review with scored principles
中文简介正在准备中。当前显示原文说明。
Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think through options before deciding what to build. Also use when a user describes a vague or ambitious feature request, asks 'what should we build', 'help me think through X', presents a problem with multiple valid solutions, or seems unsure about scope or direction — even if they don't explicitly ask to brainstorm.
中文简介正在准备中。当前显示原文说明。
Clean up local branches whose remote tracking branch is gone. Use when the user says "clean up branches", "delete gone branches", "prune local branches", "clean gone", or wants to remove stale local branches that no longer exist on the remote. Also handles removing associated worktrees for branches that have them.
中文简介正在准备中。当前显示原文说明。
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
中文简介正在准备中。当前显示原文说明。