CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

claude-code-setup

Set up or configure Claude Code for a project or machine — scaffold CLAUDE.md, wire up settings.json (permissions, env, hooks), add MCP servers, configure the status line, and create personal or project skills. Use when the user wants to set up, configure, initialize, or onboard Claude Code, or asks how to add hooks, permissions, MCP servers, or skills.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 an exemplary lean routing skill: concrete paths, commands, and delegate skills throughout, with no token waste and clean section structure. Workflow clarity is solid but the verification step ('show the diff') could be strengthened with explicit validation of config correctness.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — e.g., 'Keep it tight: build/test commands, conventions, and gotchas — not everything' — with no padded explanations of concepts Claude already knows; every section adds project-specific guidance (file locations, precedence, routing decisions).

5 / 5

Actionability

As an instruction-only skill it gives fully concrete guidance: exact paths ('.claude/settings.local.json', '~/.claude/skills/<name>/SKILL.md'), a runnable command ('/init'), and named delegates (update-config, fewer-permission-prompts, statusline-setup, skill-creator, keybindings-help) for each task category.

5 / 5

Workflow Clarity

The Approach section gives a clear ordered sequence (inspect existing files → smallest change → no secrets in committed files → show diff and explain) with the inspect step acting as a checkpoint, but explicit validation of the result (beyond showing the diff) is only implicit.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external reference files; it is organized into clear, well-scoped sections (Scope first, What this can configure, Approach) and routes depth to specialized skills, which is the appropriate structure for an entry-point skill.

5 / 5

Total

19

/

20

Passed

Description

88%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: concrete, third-person, and comprehensive on capabilities with an explicit trigger clause. The only gaps are a few missing natural trigger synonyms (status line, CLAUDE.md) and slight overlap with the specialized skills it routes to.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'scaffold CLAUDE.md, wire up settings.json (permissions, env, hooks), add MCP servers, configure the status line, and create personal or project skills' — giving comprehensive coverage of the setup domain with no vague filler.

5 / 5

Completeness

It explicitly answers both 'what' (the enumerated configuration actions) and 'when' ('Use when the user wants to set up, configure, initialize, or onboard Claude Code, or asks how to add hooks, permissions, MCP servers, or skills') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Triggers include natural phrases users would say ('set up, configure, initialize, or onboard Claude Code', 'add hooks, permissions, MCP servers, or skills'), but a few natural terms like 'status line', 'CLAUDE.md', or 'settings' are absent from the trigger clause, so coverage is short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche (Claude Code setup/onboarding) is clear with distinct triggers, but configuring settings.json overlaps with the closely related update-config skill, presenting minor conflict risk rather than minimal.

4 / 5

Total

18

/

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

BigSimmo/PsychSift

Path

.claude/cloud-profile/skills/claude-code-setup/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.