CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

auto-claude-setup

Complete Auto-Claude installation and setup guide for all platforms. Use when installing Auto-Claude on WSL, Windows, Linux, or macOS, setting up development environment, or troubleshooting installation issues.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 strong, highly actionable installation guide with copy-paste-ready commands for every platform and explicit verification steps. Its weaknesses are repetition across the four platform sections, pervasive hard-coded version numbers that will go stale, and failure to reference the local bundle files that are actually shipped alongside it.

Suggestions

Factor the repeated 'git clone https://github.com/AndyMik90/Auto-Claude.git && cd Auto-Claude && npm run install:all' steps into a single shared 'Clone and build' section, letting each platform section cover only its dependency-install commands.

Reference the bundled files directly (e.g., 'See [README.md](references/README.md)' and '[CONTRIBUTING.md](references/CONTRIBUTING.md)') instead of remote GitHub URLs, so the skill uses its own bundle.

Add an explicit venv-creation step (e.g., 'python3.12 -m venv .venv') before 'source .venv/bin/activate' in the Verification/Run First Task sections, and centralize version-sensitive values (2.7.2, Node 24, Python 3.12) in one clearly marked section so stale values are easy to spot and update.

DimensionReasoningScore

Conciseness

The body is mostly command listings with no conceptual padding, but repeats 'git clone ... npm run install:all' verbatim across four platform sections and hard-codes time-sensitive version numbers throughout ('Auto-Claude-2.7.2.exe', 'nvm v0.40.0', 'setup_24.x', 'claude-opus-4-5-20251101') with no deprecation/old-patterns section, which the guidelines penalize.

3 / 5

Actionability

Every section provides fully executable, copy-paste-ready commands: per-platform install commands (winget, apt, brew, nvm, NodeSource), environment config, verification checks, and a runnable first task via 'python spec_runner.py --task "Add a hello world endpoint"', matching the comprehensive executable anchor.

5 / 5

Workflow Clarity

The sequence prerequisites -> install -> auth -> env config -> verification -> first task is clear, with an explicit Verification section and Common Issues recovery steps. However, the flow instructs 'source .venv/bin/activate' without ever creating a venv in the main path (venv creation only appears under troubleshooting), leaving an implicit gap a reader would hit.

4 / 5

Progressive Disclosure

Good section structure (Quick Start, Platform-Specific Setup, Authentication, Verification, Common Issues, References) at an appropriate length, but the local bundle files references/README.md and references/CONTRIBUTING.md are never referenced by path; the References section links to remote GitHub URLs of the same documents instead of the bundled copies.

4 / 5

Total

16

/

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 well-crafted description that explicitly states what the skill does and when to use it, with natural trigger terms covering all supported platforms. Its only imperfections are slightly generic action verbs and minor overlap with the dedicated troubleshooting sibling skill.

DimensionReasoningScore

Specificity

'installing Auto-Claude on WSL, Windows, Linux, or macOS, setting up development environment, or troubleshooting installation issues' names the domain plus several concrete actions with platform enumeration. It falls short of the 5 anchor because the actions (install, set up, troubleshoot) are themselves fairly generic compared to a list of multiple distinct concrete operations, and well above the 1-2-action 3 anchor.

4 / 5

Completeness

It explicitly answers both: what ('Complete Auto-Claude installation and setup guide for all platforms') and when, with concrete trigger phrases ('Use when installing Auto-Claude on WSL, Windows, Linux, or macOS, setting up development environment, or troubleshooting installation issues'), matching the top anchor exactly.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'installing', 'setup', 'WSL', 'Windows', 'Linux', 'macOS', 'development environment', 'troubleshooting installation issues'. A few natural variants are missing (e.g., 'install errors', 'environment setup'), so it sits between the good-coverage 4 anchor and the comprehensive-with-synonyms 5 anchor, closer to 4.

4 / 5

Distinctiveness Conflict Risk

A clear niche (installing a named product, with platform-specific triggers) gives minimal conflict risk overall, but 'troubleshooting installation issues' slightly overlaps the sibling auto-claude-troubleshooting skill referenced in the body, fitting the 4 anchor (mostly distinct; minor overlap with closely related skills) rather than the 5 anchor.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/auto-claude-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.