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

85%

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

Quality

Content

87%

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

A well-organized, actionable command-line reference with lean, copy-paste-ready examples and strong section structure. The main gap is the lack of validation/verification checkpoints around its destructive and batch operations, which limits workflow clarity.

Suggestions

Add an explicit verification step before destructive/batch commands, e.g. run the search without '-exec'/'xargs rm' first to preview matches, or include a 'preview then act' pattern for `grep -rlZ ... | xargs -0 rm` and `fd -e log -x rm`.

For `sed -i ''` in-place edits, recommend verifying the result (e.g. a dry-run without -i, or a quick diff/backup check) before committing changes, to add a feedback loop around irreversible edits.

Optionally split the long tool-by-tool reference into a separate reference file (e.g. COMMANDS.md) referenced one level deep, keeping SKILL.md as a tighter overview, though the current single-file organization is already acceptable.

Dimension	Reasoning	Score
Conciseness	The body is a lean bullet-style command reference where each token earns its place; the BSD-vs-GNU portability notes (sed -i '', grep --exclude-dir, find -prune) add genuinely non-obvious value rather than explaining concepts Claude already knows, fitting the score-3 'lean and efficient' anchor rather than the score-2 'could be tightened' anchor.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands with concrete flags (e.g. 'grep -rlZ -I --exclude-dir=node_modules "DEPRECATED_API" . \| xargs -0 rm'), matching the score-3 anchor for specific, executable examples rather than the pseudocode score-2 anchor.	3 / 3
Workflow Clarity	This is a reference collection rather than a sequenced workflow, and the destructive/batch operations (grep \| xargs rm, sed -i, fd -x rm) lack any validation or verification checkpoint; per the judging guidelines, missing validation in batch/destructive contexts caps workflow clarity at 2 rather than 3.	2 / 3
Progressive Disclosure	The skill is self-contained with no external bundle references and is organized into clear ## and ### sections with no nested reference chains, so for a single-file reference with no need for external files progressive disclosure scores 3 on well-organized sections alone.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, well-targeted description that names concrete tools and actions with strong natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause such as 'Use when the user needs portable shell one-liners or BSD/macOS-compatible versions of grep, find, sed, or xargs commands.' to raise completeness from 2 to 3.

Consider pairing each named tool with a one-word use cue (e.g. 'searching (ripgrep, grep)', 'finding files (fd, find)') so the action-to-tool mapping is even more direct.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('fast searching, text processing, codebase navigation, and parallel execution') and names specific tools (grep, find, sed, awk, xargs, ripgrep, fd), matching the score-3 anchor for listing multiple specific concrete actions rather than the partial score-2 anchor.	3 / 3
Completeness	It clearly answers 'what' (safe, portable, efficient patterns for named tools) but offers no explicit 'Use when...' trigger clause; the phrase 'Covers common shell scripting and one-liner use cases including...' only implies when, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes natural terms a user would actually say — 'grep', 'find', 'sed', 'awk', 'xargs', 'ripgrep', 'fd', 'shell scripting', 'one-liner' — giving good coverage of common variations rather than only some relevant keywords (score 2).	3 / 3
Distinctiveness Conflict Risk	The macOS/BSD Unix CLI niche with named tools (mdfind, pbcopy, open) is a clear, distinct trigger set unlikely to conflict with other skills, matching the score-3 anchor.	3 / 3
	Total	11 / 12 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: 8aaa41d

Reviewed: about 13 hours 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.