CtrlK
BlogDocsLog inGet started
Tessl Logo

cloud-dashboard-walkthrough

Drive the OpenWork Cloud dashboard (Den Web / app.openworklabs.com) as a real user via headless Chrome CDP — sign up, create an org, invite teammates, teams, plugins with skills, marketplaces, team access grants, desktop handoff. Use for cloud tutorials, dashboard screenshots, demo walkthroughs, or when a task says "create an org / invite teammates / create a plugin / assign a marketplace" on OpenWork Cloud.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an excellent operational runbook: dense, executable, and rich with validation checkpoints and error-recovery loops across the full dashboard flow. Its only real weakness is progressive disclosure — everything lives in one ~130-line file with no reference files to offload detail into. Splitting the deeper sub-procedures into referenced files would lift the structure without sacrificing actionability.

Suggestions

Move the verbose sub-procedures into one-level-deep reference files under references/ and link them with clearly signaled pointers, e.g. '**Teammate API join path**: See [join-paths.md](references/join-paths.md)' and '**Desktop handoff grants**: See [handoff.md](references/handoff.md)'.

Relocate the full flows table (routes + exact labels) to references/flows.md and keep SKILL.md as a concise overview, bringing the overview under the ~50-line threshold where sectioning alone earns full progressive-disclosure credit.

Add a short 'References' section near the top listing the bundled files so the disclosure structure and navigation are visible at a glance.

DimensionReasoningScore

Conciseness

The body is information-dense with no conceptual padding — it assumes Claude knows React, Chrome CDP, curl, and Daytona, and every section delivers operational load (commands, routes, gotchas); not 2 because there is no unnecessary explanation to trim without losing value.

3 / 3

Actionability

Provides fully executable bash/JS/curl snippets, exact routes, and exact button labels that are copy-paste ready (e.g. the native-setter input snippet, the curl runtime-config check, the desktop-handoff deep link); not 2 because there is no pseudocode or missing key details.

3 / 3

Workflow Clarity

Flows are sequenced in a route/label table with explicit validation ('curl ... expect "orgMode":"multi_org"') and error-recovery loops (sudo modal, 402 seat limit, preview-URL expiry → regenerate signed URLs → restart stack → re-sign-in); not 2 because checkpoints and feedback loops are present for the risky operations.

3 / 3

Progressive Disclosure

The skill is a single well-sectioned ~130-line file with no bundle files or one-level-deep references, and detail that could be separate (API join paths, handoff deep-link construction, the full flows table) is inline; not 3 because it exceeds the ~50-line simple-skill threshold that would let sectioning alone earn a 3, and not 1 because it is well-organized rather than a monolithic wall of text.

2 / 3

Total

11

/

12

Passed

Description

100%

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 is specific, trigger-rich, and complete, clearly stating both the concrete dashboard operations it drives and the natural-language situations that should invoke it. Voice is third-person/imperative with no first/second-person phrasing, so no specificity penalty applies. It is a strong, low-conflict description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'sign up, create an org, invite teammates, teams, plugins with skills, marketplaces, team access grants, desktop handoff' — matching the 'lists multiple specific concrete actions' anchor; not 2 because the action set is comprehensive rather than partial.

3 / 3

Completeness

Clearly answers both 'what' (drive the dashboard, enumerated actions) and 'when' via an explicit 'Use for...' trigger clause; not 2 because the trigger guidance is explicit rather than implied.

3 / 3

Trigger Term Quality

'Use for cloud tutorials, dashboard screenshots, demo walkthroughs, or when a task says "create an org / invite teammates / create a plugin / assign a marketplace"' are natural phrases a user would actually say, giving good coverage; not 2 because common variations are well represented.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to 'OpenWork Cloud dashboard (Den Web / app.openworklabs.com)' with product-specific triggers, giving a clear niche unlikely to conflict with other skills; not 2 because the domain is unambiguous.

3 / 3

Total

12

/

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.

Validation16 / 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.