agentleFS
niksavisniksavis/handily/.agents/skills/cli-tools/SKILL.md

cli-tools

Skill2 starsChanged 32 days agoMITView on GitHub

Picks the fast tool for a shell task: rg to find each file that mentions a word, fd to list files, jq or yq for a JSON or YAML field, curl for an HTTP endpoint.

4 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md
<!-- Generated by `basicly skills-build` from skill.yaml. Do not edit; edit the source. -->

Command-line tools

Pick the tool for the task, then read its reference for the flags, the rules and the output. When a tool is missing, say so and use the fallback in the last column.

TaskToolReferenceFallback
Search text in filesrgripgrepgrep -rn
Find files by name or typefdfdfind
Read a file with line numbersbatbatcat -n
Read or reshape JSONjqjqa script
Read or reshape YAML or TOMLyqyqa script
Replace text in filessdsdsed
Search or rewrite code structureast-grepast-greprg
Call an HTTP APIxh, curlxh, curlcurl
Download a filewgetwgetcurl -O
Read a diffdeltagit-deltagit diff
Run a project recipejustjustthe README command
Run with the project variablesdirenv exec .direnvset them by hand
Large binary files in gitgit lfsgit-lfsnone
Check a shell scriptshellcheckshellchecknone
Find spelling mistakestypostyposnone
Show a directory treetreetreefd
Git commandsgitgitnone
Review and stage by handlazygitlazygitgit
Pick a line from a listfzffzfrg
Python projects and scriptsuvuvpip
Wait for a command or CIHost wait toolsbounded waitingOne CLI watcher and the same execution handle
Sessions and panestmuxtmuxnone
Shell startup and config errorszshzshnone
Shell prompt segmentsstarshipstarshipnone
Terminal tabs, panes and keysweztermweztermnone

To give every repo on this machine this skill and its references, run basicly skills-user cli-tools once.

Rules

  • Never start an interactive tool. fzf, lazygit and tmux wait for a person; their references say which forms are safe.
  • Prefer the tool over a custom script. It is faster, and a person can read the command.
  • Read the output before you act on it. An empty result is not proof of absence; run a search that must match first.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.