CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudlayer

Cloudlayer integration. Manage data, records, and automate workflows. Use when the user wants to interact with Cloudlayer data.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/cloudlayer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 body is a strong, command-driven integration guide: concrete CLI invocations at every stage, a useful action catalog, and thoughtful connection-state/polling guidance. Its main weaknesses are dangling workflow references (a nonexistent Step 2, an orphaned 1b), no job-status verification step after running async actions, a few content-free sections, and placeholder-heavy examples with one inconsistent CLI invocation. Restructuring the step labels and adding a job-completion checkpoint would lift it substantially.

Suggestions

Fix the broken sequencing: label the numbered steps consistently (there is a "1b" with no "1a" and a reference to a "Step 2" that doesn't exist) or replace them with a single linear checklist.

Add a validation checkpoint after running actions — Cloudlayer jobs are asynchronous, so instruct the agent to poll `get-job` until the job completes before reporting results, mirroring the good polling guidance already present for connection setup.

Delete the content-free "Cloudlayer Overview" bullet tree and reconcile the CLI invocation inconsistency (`npx @membranehq/cli` vs `membrane`); optionally include one fully concrete worked example with real values instead of placeholders.

DimensionReasoningScore

Conciseness

The body is dominated by executable commands, a popular-actions table, and a flag table — lean and mostly earning its tokens. Minor trimmable padding exists: the "Cloudlayer Overview" bullet tree ("Project / Environment / Deployment / Account / API Key") conveys no actionable information, and phrases like "so you can focus on the integration logic rather than auth plumbing" could be cut. Not a 5 because of those few unnecessary passages.

4 / 5

Actionability

Nearly every section gives copy-pasteable commands: `npm install -g @membranehq/cli@latest`, `membrane connection ensure "https://cloudlayer.io/" --json`, `membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json`, plus a full proxy flag table. It falls short of the 5 anchor because commands lean on placeholders (<actionId>, CONNECTION_ID) with no worked end-to-end example, and there's an unexplained CLI invocation inconsistency (`npx @membranehq/cli` vs `membrane` in the polling step).

4 / 5

Workflow Clarity

A rough sequence exists (install → login → connect → poll → search actions → run → proxy) with good connection-state handling (READY / BUILDING / CLIENT_ACTION_REQUIRED with clientAction details), but checkpoints are broken or implicit: "skip to **Step 2**" references a Step 2 that doesn't exist, "1b. Wait for the connection" appears with no 1a, and after running an action there is no instruction to verify job completion — even though get-job/list-jobs actions are listed in the table, the workflow never says to check them. Fits 'steps listed but validation gaps; checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

A single-file skill with no bundle files, organized into clear sections (Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) with tables appropriately inline at this scale. Not a 5 because of organization gaps: the content-free "Cloudlayer Overview" section and the broken step numbering (Step 2, 1b) hurt navigation.

4 / 5

Total

15

/

20

Passed

Description

48%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 leans on the Cloudlayer brand name to carry all its weight while the actual capability text is vague boilerplate that misrepresents the skill (the API does screenshots/PDF conversion, not generic data and records management). It has a valid 'Use when' clause, but neither what nor when is concrete. It reads like a template description with the app name substituted.

Suggestions

State the real capabilities concretely, e.g. "Capture website screenshots, convert URLs and HTML to PDF, generate images/PDFs from templates via the Cloudlayer API" instead of "Manage data, records, and automate workflows".

Add natural trigger terms users would say, e.g. "Use when the user mentions Cloudlayer, wants a screenshot of a webpage, or needs to convert a URL or HTML to PDF".

Align the 'when' clause with the actual use cases (screenshots, PDF generation, website content capture) rather than the generic "interact with Cloudlayer data".

DimensionReasoningScore

Specificity

The description names the domain ("Cloudlayer integration") but its actions are entirely generic: "Manage data, records, and automate workflows" describes no concrete capability — nothing about website screenshots, PDF generation, or content extraction that the body shows the API actually does. This matches the anchor 'Names the domain but actions are minimal or generic'; not a 3 because no concrete action is listed.

2 / 5

Completeness

Both elements exist — the what ("Manage data, records, and automate workflows") and the when ("Use when the user wants to interact with Cloudlayer data") — but the what is vague and actually inaccurate versus the skill's real purpose, and the when is generic. Below the 4 anchor because the 'what' is not clear or concrete; above 2 because neither element is missing.

3 / 5

Trigger Term Quality

"Cloudlayer" is the one genuinely natural keyword a user would say, but the task phrases users actually use — screenshot, PDF, convert webpage, HTML to image — are completely absent, leaving "data" and "records" as generic filler. Fits 'some relevant keywords but missing common variations or synonyms'; not a 2 because the brand term is a real trigger, not pure jargon, and not a 4 because the core task vocabulary is missing.

3 / 5

Distinctiveness Conflict Risk

The brand name "Cloudlayer" carves out a distinct niche with minimal wrong-skill trigger risk, but the generic tail "Manage data, records, and automate workflows" could overlap with any data-management or automation skill. Fits 'mostly distinct; minor overlap risk with closely related skills'; not 5 because the generic phrasing invites overlap.

4 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

membranedev/application-skills

Path

skills/cloudlayer/SKILL.md

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.