Tessl • The management layer for AI agent skills

SkillPublic

become-claude-master

Onboard a new Claude Code user — set up their ~/.claude/CLAUDE.md, install relevant skills, and start a structured learning program covering best practices. Use when setting up Claude Code for the first time, onboarding someone to Claude Code, or continuing a learning session.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/become-claude-master/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.

A well-structured, actionable three-phase onboarding skill with concrete templates, commands, and a sequenced curriculum. Its main weaknesses are padded inspirational/educational prose, a batch install step without success verification, and heavy inlining of reference material that no bundle files exist to externalize.

Suggestions

Remove or relocate the 'Inspiration quotes' section and trim the user-facing explanation prose to keep the skill lean and token-efficient.

Add a verification checkpoint to Phase 2's skill-install loop (e.g. confirm each install succeeded before moving on) to lift workflow clarity above the batch-validation cap.

Split the curriculum and skill-recommendation mapping into reference bundle files (e.g. references/curriculum.md, references/skills.md) and link to them one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly structured and useful, but the rotating "Inspiration quotes" section and explanatory prose (e.g. telling the user what CLAUDE.md is) pad the skill with content that does not earn its tokens, fitting the mostly-efficient-but-could-be-tightened anchor.	3 / 5
Actionability	Concrete, executable guidance abounds — a fill-in CLAUDE.md template, specific interview questions, a conditional skill-recommendation mapping, the `claude install-skill https://...` command, and a calendar-link format — with only minor gaps where curriculum topics are titles meant to be fetched later.	4 / 5
Workflow Clarity	Phases and session steps are clearly sequenced and Phase 1 includes an existence-check checkpoint, but the batch skill-install loop in Phase 2 has no verification that installs succeeded; per the rubric, a batch operation lacking validation caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Sections are well organized and external URLs are signaled, but substantial reference-like content (the full curriculum, the skill-recommendation mapping, the template) is inlined in a single ~180-line file rather than split into bundle files, fitting the some-structure-but-could-be-better-organized anchor.	3 / 5
	Total	13 / 20 Passed

Description

83%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 that concretely states three setup actions and provides an explicit, multi-condition "Use when" clause covering first-time setup, onboarding, and continued learning. It is held back only by minor gaps in synonym coverage and slight overlap risk from the broad best-practices framing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "set up their ~/.claude/CLAUDE.md", "install relevant skills", and "start a structured learning program" — though it does not enumerate the full breadth of setup or curriculum actions, so it stops short of comprehensive (5).	4 / 5
Completeness	It explicitly answers both what (setup, install skills, learning program) and when ("Use when setting up Claude Code for the first time, onboarding... or continuing a learning session") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases like "setting up Claude Code for the first time", "onboarding someone to Claude Code", and "continuing a learning session" match what a user would say, but a few common synonyms are absent so it is not comprehensive (5).	4 / 5
Distinctiveness Conflict Risk	The Claude Code onboarding/setup/learning niche is mostly distinct with specific triggers, but the broad "best practices" framing creates minor overlap risk with general Claude Code skills, keeping it just below the clear-niche anchor (5).	4 / 5
	Total	17 / 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: razbakov/skills
Path: skills/become-claude-master/SKILL.md
Revision: b82463b

Reviewed: 1 month ago

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.

become-claude-master

Table of Contents

Is this your skill?