CtrlK
BlogDocsLog inGet started
Tessl Logo

install-openwork

Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task. Use when someone wants OpenWork, an open-source Claude Cowork alternative, on their own computer.

73

Quality

90%

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

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.

Excellent content for a simple install skill: copy-paste-ready commands covering every OS/arch combination, a lean body with zero padding, and a clear step sequence. The only gap is a post-install validation checkpoint, which is minor for a non-destructive install flow.

DimensionReasoningScore

Conciseness

The body is lean and every token earns its place: the one-line intro and the npm-package warning ("Never run `npx openwork`... The npm package named `openwork` is a different project") convey facts Claude cannot know, and no already-known concepts are explained. Not 4 because there is no over-explanation left to trim.

5 / 5

Actionability

Fully executable guidance: `uname -s`/`uname -m` detection commands, a complete OS/arch install table with concrete commands and download URLs, a copy-paste curl/chmod AppImage block, and a concrete first-run example ("Summarize this folder."). Commands cover the common cases across all platforms.

5 / 5

Workflow Clarity

The four-step sequence (detect OS → install → first run → finish) is clearly ordered, and "Ask the user before installing anything" acts as a checkpoint. It is not 5 because there is no validation step confirming the install succeeded (e.g., a version or launch check) before moving to first-run instructions.

4 / 5

Progressive Disclosure

This is a simple, single-purpose skill under 50 lines with no bundle files, and its sections (Detect, Install, First run, Finish) are well organized with appropriately external links (docs guide, team-skill URL). Per the simple-skill guideline, well-organized sections earn the top score without external file references.

5 / 5

Total

19

/

20

Passed

Description

87%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: it states concrete capabilities with platform coverage and provides an explicit, natural 'Use when' trigger clause. Minor room to broaden trigger synonyms, but it clearly communicates both what the skill does and when to invoke it with essentially no conflict risk.

DimensionReasoningScore

Specificity

"Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task" names concrete actions with explicit platform coverage, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because it lists only install plus first-task onboarding rather than a comprehensive set of capabilities.

4 / 5

Completeness

It explicitly answers both parts: what ("Install the free OpenWork desktop app on macOS, Windows, or Linux and get the user to a first task") and when ("Use when someone wants OpenWork, an open-source Claude Cowork alternative, on their own computer"). Both are concrete and explicit, matching the anchor-5 example; it is not 4 because the 'when' clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

Terms like "OpenWork", "install", "desktop app", "Claude Cowork alternative", and "on their own computer" are natural phrases users would say when wanting this skill. Coverage is good but a few natural variants (e.g., "self-hosted", "local AI agent app") are missing, keeping it below the comprehensive-coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The skill targets a distinct proper-noun application (OpenWork) with a clear niche (installing that specific app) and no generic phrasing that would collide with other skills. Conflict risk is minimal.

5 / 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
different-ai/openwork
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.