rtk-optimizer

Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is highly actionable and the workflow is clearly sequenced, but it is held back by redundant command tables and broken references to nonexistent files. Removing the duplicated metrics section and the time-sensitive star/release counts would tighten it considerably.

Suggestions

Collapse the 'Supported Commands' and 'Metrics (Verified)' sections into one table to remove duplicated command-to-reduction data.

Delete or fix the broken reference paths (docs/resource-evaluations/rtk-evaluation.md, examples/claude-md/rtk-optimized.md) since no bundle files exist.

Move volatile facts ('446 stars', '30 releases in 23 days', 'rtk 0.16.0+') out of the main body or into a clearly marked version/status note to avoid penalizing conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but duplicates the command-to-reduction data across both the 'Supported Commands' and 'Metrics (Verified)' sections and includes time-sensitive marketing detail ('446 stars', '30 releases in 23 days', 'rtk 0.16.0+') that pads the token budget.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout ('rtk git log', brew/cargo install steps, 'rtk gain') with specific before/after reduction figures.	3 / 3
Workflow Clarity	The 'How It Works' four-step sequence plus the install-check gate and edge-case handling give a clear, ordered process; operations are non-destructive suggestions so no validation feedback loop is required.	3 / 3
Progressive Disclosure	Sections are reasonably organized, but the References point to files that do not exist ('docs/resource-evaluations/rtk-evaluation.md', 'examples/claude-md/rtk-optimized.md') and there are no actual bundle files, so navigation is broken rather than one level deep.	2 / 3
	Total	10 / 12 Passed

Description

90%

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

The description is strong: third person, explicit 'Use when' trigger with concrete natural command names, and a clear distinct niche. Its only gap is specificity, where it names one action rather than several.

Dimension	Reasoning	Score
Specificity	Names a single concrete action ('Wrap high-verbosity shell commands with RTK') and the verbose-CLI domain, but does not enumerate multiple distinct concrete actions like the level-3 anchor does.	2 / 3
Completeness	Clearly answers both what ('Wrap high-verbosity shell commands with RTK to reduce token consumption') and when ('Use when running git log, git diff, cargo test, pytest...') with an explicit 'Use when' trigger.	3 / 3
Trigger Term Quality	Uses natural commands users actually say ('git log, git diff, cargo test, pytest') plus 'verbose CLI output', giving good coverage of trigger terms rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The RTK-token-optimization niche with named verbose commands is distinct and unlikely to trigger for the wrong skill, matching the clear-niche anchor.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Commit: eb4fbbd

Reviewed: 2 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.