unix-cli-best-practices

Safe, portable, and efficient command-line patterns for macOS/BSD Unix tools (grep, find, sed, awk, xargs, mdfind, pbcopy, open) and modern alternatives (ripgrep, fd). Covers common shell scripting and one-liner use cases including fast searching, text processing, codebase navigation, and parallel execution.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/agents/reidbaker-agent/skills/unix-cli-best-practices/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-organized CLI reference whose main weaknesses are restated basic-flag padding and — more seriously — destructive batch commands (xargs rm, in-place sed) offered without any validation or dry-run safeguards.

Suggestions

Add explicit safety/validation steps before destructive batch examples, e.g., preview with "grep -rlZ ... | xargs -0 -n1 echo" or run "sed -i '' .bak" with a backup before committing to no-backup in-place edits.

Trim the flag catalogs that restate standard knowledge Claude already has (basic grep -r/-l/-I semantics, rg -i/-w/-C) and keep only the non-obvious or BSD-specific guidance.

Consider moving the macOS-specific tools section (mdfind, pbcopy, open) to a reference file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	The genuinely non-obvious material (BSD sed -i '' syntax, find -prune, grep --exclude-dir, xargs -0) is diluted by flag catalogs restating knowledge Claude already has (e.g., "-r or -R to search recursively", "-l to print only the names of files containing matches"), making it mostly efficient with some unnecessary explanation rather than lean.	3 / 5
Actionability	Every section gives copy-paste-ready, fully executable commands (rg/fd invocations, the prune and exclude-dir one-liners, awk recipes, mdfind/pbcopy/open examples) that directly cover the common cases for each tool.	5 / 5
Workflow Clarity	The skill presents destructive and batch operations — "grep -rlZ ... \| xargs -0 rm", "fd -e log -x rm", and in-place "sed -i ''" edits — with no dry-run, validation, or verification steps, so workflow clarity is capped at 3 despite the individual patterns being unambiguous.	3 / 5
Progressive Disclosure	The single file is well organized into clear, scannable sections (modern alternatives, built-in tools, macOS-specific tools) with no bundle files and no nested references; at ~170 lines it exceeds the under-50-line exception, and sections like the macOS-specific tools could arguably live in a reference file, keeping it just short of 5.	4 / 5
	Total	15 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, tool-specific description that clearly conveys what the skill covers, weakened by the absence of any explicit "Use when..." trigger guidance and a few missing natural keyword variations.

Suggestions

Append an explicit trigger clause, e.g., "Use when running searches, text processing, or file cleanup from the terminal on macOS, or when a command behaves differently on BSD vs GNU utilities."

Include the common aliases users actually type ("rg", "fd") and natural phrases like "search a codebase" or "batch-edit files" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names concrete tools (grep, find, sed, awk, xargs, mdfind, pbcopy, open, ripgrep, fd) and several specific use cases ("fast searching, text processing, codebase navigation, and parallel execution"), but frames them as "patterns" rather than listing comprehensive concrete actions, leaving minor gaps.	4 / 5
Completeness	The "what" is clear (safe, portable, efficient CLI patterns for named tools), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by "for macOS/BSD Unix tools" — which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Tool names like "grep", "sed", "ripgrep", and phrases like "shell scripting" and "one-liner" are natural terms users would say, giving good keyword coverage; a few natural variations are missing (e.g., the "rg"/"fd" aliases, "search a codebase", "replace text in files").	4 / 5
Distinctiveness Conflict Risk	The macOS/BSD portability angle and the specific modern-vs-builtin tool pairing give it a clear niche with distinct triggers; minor overlap risk remains with generic shell-scripting or codebase-navigation skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: flutter/agent-plugins
Path: .agents/agents/reidbaker-agent/skills/unix-cli-best-practices/SKILL.md
Commit: 8da8c54

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.