CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-build-tools

Install build and extraction tools needed for building Claude Desktop Debian packages

75

1.34x
Quality

66%

Does it follow best practices?

Impact

86%

1.34x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/setup-build-tools/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 lean, actionable, and well-organized for a simple installation skill, with a copy-paste command and a clear tool table. Its main gap is the absence of any validation step for what is effectively a batch package install, which caps workflow clarity.

Suggestions

Add a verification step after the install command, e.g. 'Verify with: 7z --help && dpkg-deb --version' or 'Check the script exit code before proceeding to build.sh.'

Remove the redundant opening line that restates the frontmatter description, or merge it into the task instruction.

Clarify or remove the 'Optional Guidance / $ARGUMENTS' placeholder so it does not read as an unfilled template artifact.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (a single command, a compact tool table, short 'When to Use' bullets), with only minor trims possible (the opening line restates the description and the '$ARGUMENTS' placeholder under 'Optional Guidance' is a template artifact), matching the 'efficient; minor instances that could be trimmed' anchor; not a 5 because of those small redundancies.

4 / 5

Actionability

It gives a fully executable, copy-paste-ready command ('bash "$CLAUDE_PROJECT_DIR/.claude/hooks/install-build-tools.sh"') plus a concrete table mapping each tool to its package and purpose, covering the common case, matching the 'fully executable; copy-paste ready' anchor; not a 4 because there are no missing execution details for the primary action.

5 / 5

Workflow Clarity

Although this is a simple single-purpose skill, running the script installs a batch of seven system packages and the body provides no validation/verification step (e.g. checking the script exit code or confirming '7z' is available), so per the batch-operation cap workflow_clarity cannot exceed 3; not a 4 because an explicit verification checkpoint is absent.

3 / 5

Progressive Disclosure

At 38 lines with no need for external references and clearly organized sections (Your Task, Tools Installed, When to Use, Optional Guidance) and no bundle files present, it satisfies the simple-skill exception for progressive disclosure, matching the 'well-organized sections' anchor; not a 4 because structure is clean with no organization gaps.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear, specific purpose and distinct niche but omits any 'Use when...' trigger guidance, which caps completeness and limits trigger-term quality. Adding an explicit usage clause with file-extension synonyms would lift the weaker dimensions.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when preparing to build Claude Desktop .deb/.AppImage packages or when build.sh reports missing dependencies.'

Add natural synonyms and file extensions (e.g. '.deb', 'AppImage', 'package build') so trigger terms match what users actually say.

Lead with a more distinctive verb/phrase than the generic 'Install ... tools' to reduce overlap with other setup skills.

DimensionReasoningScore

Specificity

Names the domain ('building Claude Desktop Debian packages') and one concrete action ('Install build and extraction tools'), but lists only a single action rather than several specific ones, matching the 'domain + 1-2 concrete actions, not comprehensive' anchor; not a 4 because it does not list multiple specific actions.

3 / 5

Completeness

The phrase 'Install build and extraction tools needed for building Claude Desktop Debian packages' gives a clear 'what' but contains no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines; not a 4 because 'when' is entirely absent rather than weakly present.

3 / 5

Trigger Term Quality

Includes relevant terms ('build tools', 'extraction tools', 'Debian packages', 'Claude Desktop') but omits natural synonyms and file extensions a user might say (e.g. '.deb', 'AppImage', 'package build'), matching the 'some relevant keywords but missing common variations' anchor; not a 4 because keyword coverage is incomplete.

3 / 5

Distinctiveness Conflict Risk

The niche ('building Claude Desktop Debian packages') is distinct and unlikely to trigger for unrelated skills, but the generic 'Install ... tools' framing creates minor overlap risk with other setup/install skills, matching the 'mostly distinct; minor overlap risk' anchor; not a 5 because the leading verb is generic rather than uniquely identifying.

4 / 5

Total

13

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aaddrick/claude-desktop-debian
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.