CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-output-conventions

Use when designing or testing a command-line tool's output: a new flag, command or error message, CLI assertions, or flaky tests caused by unstable output. Sets the contract for exit codes, stdout vs stderr, --json output, ordering, color and --help, based on the Command Line Interface Guidelines.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is testland/cli-output-conventions

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 well-structured reference skill: concrete, executable bats test patterns for most conventions, an unambiguous failure→fix mapping, and a clean one-level-deep split of conventions 5-8 into a real reference file. The two weaker spots are the trimmable clig blockquotes and the missing code example for Convention 4's golden-file test pattern.

Suggestions

Trim the five clig blockquotes to one-line citations (e.g., 'Per clig.dev: data on stdout, messages on stderr') — the quoted guidelines are concepts Claude already knows, and the anti-pattern table already restates the key rules.

Show a concrete bats example for Convention 4's golden-file comparison (e.g., comparing sorted --plain output against a checked-in fixture) so it matches the executable standard set by Conventions 1-3.

DimensionReasoningScore

Conciseness

The body is mostly tight tables, examples, and terse rules that assume competence (no basic-concept explanations), but the five clig blockquotes (e.g., "Send output to `stdout`... Send messaging to `stderr`") restate guidelines Claude broadly knows, and the anti-pattern table partially repeats the conventions. These are minor trimmable instances, fitting the efficient-with-minor-over-explanation anchor rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Conventions 1-3 come with copy-paste-ready bats test patterns (e.g., "run --separate-stderr mycli list" and the jq assertion on --json output), but Convention 4's test pattern ("golden-file comparison with sorted output") names a technique without showing code — a minor gap versus the fully-executable anchor.

4 / 5

Workflow Clarity

This is a single-purpose reference/contract skill with no multi-step process, and per the simple-skill guidance it scores 5 when the action is unambiguous: each convention pairs rule → example → test pattern, the anti-pattern table maps failure → why → fix → convention, and "Fix the output, not the assertion" gives an explicit decision rule. No destructive or batch operations are involved, so no validation cap applies.

5 / 5

Progressive Disclosure

Scored against the actual bundle: references/conventions-5-8.md exists, is referenced from a clearly signaled dedicated section ("The remaining four conventions and their bats test patterns are in [references/conventions-5-8.md]"), and is one level deep. Core conventions 1-4 stay inline with the remainder appropriately split out, matching the well-signaled one-level-deep-references anchor.

5 / 5

Total

18

/

20

Passed

Description

96%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 description: it states both what the skill does and when to use it with concrete, natural trigger phrases, and covers the domain comprehensively. The only weakness is mild overlap risk with sibling testing skills on the "CLI assertions / flaky tests" triggers.

DimensionReasoningScore

Specificity

The description enumerates concrete contract areas ("exit codes, stdout vs stderr, --json output, ordering, color and --help") plus concrete scenarios ("a new flag, command or error message, CLI assertions, or flaky tests caused by unstable output"), matching the comprehensive-coverage anchor rather than the minor-gaps anchor.

5 / 5

Completeness

It explicitly answers both questions: an explicit "Use when..." clause with concrete trigger phrases, and an explicit what ("Sets the contract for exit codes, stdout vs stderr, --json output, ordering, color and --help"). The when-clause is fully explicit, so it exceeds the anchor-4 example.

5 / 5

Trigger Term Quality

Natural user phrases are comprehensively covered, including the synonym pair "command-line tool"/"CLI", "new flag", "error message", "flaky tests", "exit codes", and "stdout vs stderr"; no commonly-said trigger term for this domain is missing.

5 / 5

Distinctiveness Conflict Risk

The niche (CLI output contract) is clear, but triggers like "CLI assertions, or flaky tests" overlap with closely related test-runner skills — the body itself names sister skills (bats-testing, tui-snapshot-tester) that cover the testing side. This fits "mostly distinct; minor overlap risk with closely related skills" better than the minimal-conflict-risk anchor.

4 / 5

Total

19

/

20

Passed

Validation

100%

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

testland/qa

Path

plugins/qa-cli-tools/skills/cli-output-conventions/SKILL.md

Reviewed

Table of Contents

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.