set-up-openwork-team

Set up OpenWork for a team - sign up for OpenWork Cloud, create the organization, invite teammates, share models through the AI Gateway, and share a skill. Use when a team or company wants OpenWork with shared skills, models, or policies.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 lean, well-structured single-file skill with concrete UI steps, executable shell commands, and appropriate safety constraints around account creation. The main gaps are minor: some headless execution detail lives behind external docs and there is no guidance for handling bootstrap/doctor failures.

Suggestions

Inline the one or two most critical commands from start.md's 'cloud bootstrap-workspace' step (or their exact arguments) so the headless path is executable without fetching an external doc first.

Add a short error-recovery note for the headless flow, e.g. what to check when 'openwork-bootstrap doctor --json' reports failures before proceeding.

Include a quick verification checkpoint for the dashboard path, such as confirming the invited member appears under 'Members' or that the shared skill shows in 'Settings' > 'Library' after install.

Dimension	Reasoning	Score
Conciseness	The 39-line body assumes Claude's competence throughout — no conceptual explanations, just steps, UI paths, URLs, and constraints like 'Don't invent passwords or create accounts for the user without asking'. Every token earns its place.	5 / 5
Actionability	Mostly executable: concrete UI paths ('`Members` > `Add member`, enter an email, pick a role'), a copy-paste shell block with inspect-before-run, and a verification command. However, the headless path defers key execution detail to external docs ('follow https://openworklabs.com/start.md', auth.md) rather than inlining it.	4 / 5
Workflow Clarity	The dashboard flow is a clear numbered sequence and the headless flow includes checkpoints (inspect the install script, run 'openwork-bootstrap doctor --json', human claims ownership later). It falls short of 5 because there is no error-recovery guidance for when doctor or bootstrap fails; no destructive/batch cap applies since the human owns account creation.	4 / 5
Progressive Disclosure	A single well-organized file under 50 lines where every reference is a clearly signaled, one-level-deep external URL (pricing, docs walkthrough, start.md, enterprise) — matching the simple-skill exception with no nested references or inlined bulk content.	5 / 5
	Total	18 / 20 Passed

Description

92%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 enumerates the concrete setup actions, includes an explicit 'Use when...' trigger clause, and is written in third person without padding or over-claims. The only weakness is modest synonym coverage in the trigger phrasing.

Dimension	Reasoning	Score
Specificity	The description lists five concrete actions — 'sign up for OpenWork Cloud, create the organization, invite teammates, share models through the AI Gateway, and share a skill' — giving comprehensive coverage of the setup flow rather than minor gaps.	5 / 5
Completeness	It explicitly answers what ('sign up for OpenWork Cloud, create the organization, invite teammates, share models... and share a skill') and when ('Use when a team or company wants OpenWork with shared skills, models, or policies') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'a team or company wants OpenWork with shared skills, models, or policies' cover the main ways users would phrase the need, though common variations such as 'invite teammates', 'onboard', or 'organization setup' are absent.	4 / 5
Distinctiveness Conflict Risk	The OpenWork-specific niche with product-name triggers ('OpenWork Cloud', 'AI Gateway') makes it clearly distinguishable from generic team-setup or account-management skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: ee/apps/landing/public/.well-known/agent-skills/set-up-openwork-team/SKILL.md
Commit: 417244c

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.