Install build and extraction tools needed for building Claude Desktop Debian packages
73
62%
Does it follow best practices?
Impact
86%
1.34xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/setup-build-tools/SKILL.mdQuality
Discovery
40%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 identifies a clear and narrow niche (Claude Desktop Debian package building), which gives it strong distinctiveness. However, it lacks an explicit 'Use when...' clause and doesn't enumerate the specific tools or actions involved, making it harder for Claude to confidently select this skill from a large pool. Adding trigger guidance and more concrete details would significantly improve it.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when setting up a build environment for Claude Desktop .deb packages or when the user needs packaging dependencies installed.'
List specific tools or actions, e.g., 'Installs dpkg-deb, fakeroot, ar, and other extraction/build tools needed for constructing Claude Desktop Debian packages.'
Include common user-facing trigger terms like 'deb', 'dpkg', 'package build environment', or 'build dependencies'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Claude Desktop Debian packages) and a general action (install build and extraction tools), but doesn't list specific tools or concrete actions beyond 'install'. | 2 / 3 |
Completeness | Describes what the skill does (install build and extraction tools) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also fairly thin, bringing it to 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'build', 'Debian packages', 'Claude Desktop', and 'extraction tools', but misses common variations users might say such as 'deb', 'dpkg', 'packaging dependencies', or 'build dependencies'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche — building Claude Desktop Debian packages — is unlikely to conflict with other skills. The combination of 'Claude Desktop' and 'Debian packages' creates a distinct trigger profile. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill for a simple single-purpose task. The core instruction is clear and executable. Minor verbosity exists in the tools table explaining concepts Claude already knows (e.g., what wget or imagemagick do), but overall the skill is effective and appropriately scoped.
Suggestions
Consider trimming the 'Purpose' column in the tools table to only include non-obvious purposes, or remove it entirely since Claude knows what these common tools do.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The tools table provides useful reference but the 'Purpose' column largely explains things Claude already knows (e.g., what wget does). The 'When to Use' section is somewhat obvious. However, the core instruction is lean. | 2 / 3 |
Actionability | The primary action is a single, copy-paste ready bash command. The skill clearly specifies exactly what to run and where the script is located. This is fully executable guidance. | 3 / 3 |
Workflow Clarity | This is a simple single-task skill (run one script). The single action is unambiguous, and the 'When to Use' section provides clear context for when to invoke it. No multi-step validation is needed for an installation script. | 3 / 3 |
Progressive Disclosure | For a simple, short skill under 50 lines, the content is well-organized with clear sections (task, tools reference, when to use). No external references are needed and the structure is clean. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
814cd52
Table of Contents
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.