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

72%

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 ./examples/skills/rtk-optimizer/SKILL.md

Quality

Content

57%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.

The body is actionable and decently structured, but carries redundant metrics, time-sensitive fluff, and a batch workflow lacking validation checkpoints. Progressive disclosure is weak with no supporting bundle files.

Suggestions

Deduplicate the reduction percentages — keep them in one place (either the command tables or the Metrics section) and remove the time-sensitive star/release counts that will rot.

Add an explicit validation step to the batch workflow (e.g., verify RTK is installed and dry-run the wrapper before executing multiple commands).

Move the full metrics table and CLAUDE.md template into actual bundle reference files under ./references/ so the body stays a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	Mostly concrete tables and commands, but duplicates the same reduction percentages in both "Supported Commands" and "Metrics (Verified)", and pads with time-sensitive marketing stats ("446 stars", "30 releases in 23 days", version 0.16.0) that age badly.	3 / 5
Actionability	Provides copy-paste-ready command mappings ("git log → rtk git log"), an install check ("rtk --version"), and concrete install commands; minor gaps where the "Usage Pattern" reads as a dialogue script rather than literal commands and tracking is left optional.	4 / 5
Workflow Clarity	"How It Works" gives a detect→suggest→execute→track sequence with an install checkpoint and edge-case handling, but the skill explicitly batches multiple commands ("Batch with RTK wrapper once") without validation/verification steps, capping the score at 3.	3 / 5
Progressive Disclosure	Well-organized section headers, but the file is a monolithic ~140-line body with no bundle files, references two non-bundled paths (docs/resource-evaluations/rtk-evaluation.md, examples/claude-md/rtk-optimized.md), and inlines metrics/tables that could be split out.	3 / 5
	Total	13 / 20 Passed

Description

87%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.

The description is strong: it concisely states a concrete capability, includes an explicit "Use when" clause with natural trigger commands, and carves out a distinct niche. Minor room to broaden trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Wrap high-verbosity shell commands with RTK to reduce token consumption") and enumerates specific command targets (git log, git diff, cargo test, pytest), giving clear coverage with only a single underlying action.	4 / 5
Completeness	Explicitly states what ("Wrap high-verbosity shell commands with RTK to reduce token consumption") and when ("Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural command names users actually type ("git log, git diff, cargo test, pytest") plus the generic catch-all "other verbose CLI output", but misses common synonyms like git status, npm test, or go test.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (RTK token-reduction wrappers) with distinct, specific triggers and minimal overlap risk with general-purpose shell skills.	5 / 5
	Total	18 / 20 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
Path: examples/skills/rtk-optimizer/SKILL.md
Commit: 752edfe

Reviewed: about 9 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.