菜单
Getting exactly the output you need from CLI tools in one call: JSON flags, slicing, counting, non-interactive flags. Use when inspecting command output, working with JSON, probing HTTP, or when a command might prompt, page, or spew.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Zfinix/aster --skill cli-toolbox命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Reviewing a diff or feature for exploitable vulnerabilities before it ships. Use when asked to do a security review, when code touches auth, input handling, queries, files, URLs, crypto, or payments, and before merging changes that accept untrusted input.
Writing a plan the user can actually judge, and presenting it for approval with exit_plan_mode. Use when the user asks to plan first, when the work is large or irreversible enough that the approach should be agreed before any edit, and whenever you are about to call exit_plan_mode.
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or forcing apps into the foreground.
基于 SOC 职业分类
正在显示 SKILL.md
| name | cli-toolbox |
| description | Getting exactly the output you need from CLI tools in one call: JSON flags, slicing, counting, non-interactive flags. Use when inspecting command output, working with JSON, probing HTTP, or when a command might prompt, page, or spew. |
Read the tool before guessing at it, and never guess twice. First
contact with a CLI you have not used this session: command -v <tool> to
confirm it is installed. When a call fails on usage rather than on the task
("unknown flag", "accepts at most 1 arg(s)", "unknown command"), the next
call is <tool> --help, or <tool> <subcommand> --help for the exact
subcommand that failed. Never re-send a shape that just failed with a small
edit; that is how a turn burns twenty calls and lands nowhere.
When the tool is missing, or its help does not settle the question, go and
read: aster_mcp with action: "execute", name: "web/search" for the
flag, or name: "web/extract" on the tool's documentation URL. Going online
once costs less than four blind retries, and unlike them it ends the
question. Say so plainly if the tool simply is not installed, rather than
quietly substituting a different one.
Ask the tool for structured output. Most modern CLIs have it:
gh pr view 12 --json title,files, cargo metadata --format-version 1,
docker ps --format json, npm ls --json. Parse with jq -r '.field'
instead of eyeballing prose.
Slice files without reading them whole. sed -n '120,160p' file for a
line range, grep -n -m5 "pattern" file for first hits with line numbers,
wc -l file before deciding how to read it.
Count and rank instead of scrolling.
grep -c for how many, sort | uniq -c | sort -rn | head for what
dominates, du -sh */ | sort -rh | head for what is big.
Probe HTTP minimally. Status only:
curl -s -o /dev/null -w "%{http_code}" URL. Content check:
curl -s URL | grep -c "expected". Never dump a whole page to look at
one thing.
Force non-interactive mode. Anything that might prompt hangs the call:
use --yes/-y, --force where safe, GIT_TERMINAL_PROMPT=0,
DEBIAN_FRONTEND=noninteractive, CI=1, </dev/null as a last resort.
Anything that might page gets --no-pager or | cat.
Quiet flags cut noise at the source. npm install --silent,
cargo build -q, git -q variants. Prefer them over filtering noise
afterwards.
Batch transformations with xargs, not loops of calls.
grep -rl "old_name" src | head -20 to see the blast radius, then one
edit per file, not one search per file.
Never sed -i a repository file. Use edit_file: it is exact,
previewed, and audited. sed -i also differs by platform (BSD needs
sed -i '', GNU takes sed -i), which makes it a portability bug on top
of an audit hole. Stream edits (sed -n '10,40p', sed 's/x/y/' in a
pipe) are fine anywhere.
Check the platform line before GNU-only flags. The environment note
says macos or linux. On macos the stock tools are BSD: no grep -P (use
grep -E), different date arithmetic (-v+1d, not -d "+1 day"), no
xargs -d. When a one-liner needs GNU behavior, reshape it around
portable flags instead of assuming Linux.
On Windows there is no sed or grep. Stock tools are PowerShell:
Select-String for grep, Get-Content -Tail 20 for tail. Ask the
environment note, not habit, which world you are in.
