add-rtk

Install rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token savings on dev commands (git, cargo, pytest, docker, kubectl, etc.).

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-rtk/SKILL.md

Quality

Content

88%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 content is a well-sequenced, fully executable installation workflow with strong validation and troubleshooting support. It respects Claude's competence and stays actionable, with only minor conciseness and progressive-disclosure refinements possible.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's knowledge of docker, jq, and containers, with executable commands throughout; only minor redundancy between the intro, 'What this sets up', and the 'Integration tests' justification could be trimmed.	4 / 5
Actionability	Every step is copy-paste ready executable code (curl install, find/mv, ncl add-mount, a jq one-liner for the hook, docker exec verify, troubleshooting commands), covering the common cases and failure modes.	5 / 5
Workflow Clarity	Five numbered steps plus dedicated Verify and Troubleshooting sections give a clear sequence with explicit validation checkpoints (rtk --version, ncl groups config get, docker exec rtk --version) and feedback loops for error recovery, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	No bundle files exist, and the single SKILL.md is well organized into clearly headed sections that are easy to navigate; at ~110 lines with the full jq snippet and troubleshooting inlined it is slightly long but appropriately structured for a single-file skill.	4 / 5
	Total	18 / 20 Passed

Description

65%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 specific and clearly distinct, naming the tool, its effect, and the affected command surface in third person. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and slightly limits trigger discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up token-saving command proxies for agent containers, or when the user wants to reduce Bash tool token usage.'

Include natural synonyms users might say ('token savings', 'token compression', 'reduce tokens') alongside the existing command list to improve trigger matching.

State the full range of concrete actions (install, mount, hook wiring, restart) rather than compressing them to 'Install' and 'Routes' to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (rtk proxy into agent containers) and concrete actions ('Install', 'Routes Bash tool calls'), and enumerates affected commands, but the skill's own actions are limited to install and route rather than a comprehensive action set.	3 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('Bash tool calls', 'dev commands', 'git, cargo, pytest, docker, kubectl') but omits natural synonyms a user might voice such as 'token savings', 'token compression', or 'reduce tokens'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (rtk proxy wired into agent containers via the Claude Code PreToolUse hook) with distinct triggers and minimal overlap risk with other skills.	5 / 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: nanocoai/nanoclaw
Path: .claude/skills/add-rtk/SKILL.md
Commit: 7902716

Reviewed: 1 day 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.