CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudquery

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

Quality

65%

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/cloudquery/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 delivers executable Membrane CLI commands with solid connection-state handling, making it largely actionable. Its main weaknesses are a broken step-numbering scheme (the referenced "Step 2" is never defined), token-wasting filler (the empty Overview list and marketing phrasing), and organizational rough edges such as a "Popular actions" section that lists no actions.

Suggestions

Fix the step references: define explicit "Step 1 / 1b / Step 2" headings (or drop the numbering entirely) so the twice-repeated "skip to Step 2" has an actual target.

Delete the content-free "Cloudquery Overview" bullet skeleton and trim marketing phrasing ("so you can focus on the integration logic rather than auth plumbing", "This will burn less tokens").

Either populate "Popular actions" with the actual commonly-used CloudQuery actions (with example `action run` invocations) or rename it and merge it into "Searching for actions".

DimensionReasoningScore

Conciseness

The body is mostly lean CLI guidance, but includes unnecessary padding: the content-free "Cloudquery Overview" bullet skeleton ("Query / Result / Source / Policy Pack / Schedule" with no explanation), the marketing sentence "Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing", and "This will burn less tokens". Matches anchor 3 ('Mostly efficient but includes some unnecessary explanation or could be tightened'); not 4 because multiple sections add no actionable value, not 2 because the bulk is command-focused rather than explanatory.

3 / 5

Actionability

Concrete executable commands throughout: `npm install -g @membranehq/cli@latest`, `membrane connection ensure "https://www.cloudquery.io/" --json`, `membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json`, plus a complete proxy flag table. Matches anchor 4 ('Mostly executable guidance with minor gaps'); not 5 because the doc twice directs the reader to a "Step 2" that is never defined and there is no worked end-to-end example; not 3 because the guidance is real, copy-paste-ready code rather than pseudocode.

4 / 5

Workflow Clarity

The sequence (install → login → connect → poll → search actions → run → proxy fallback) is present with good state-machine checkpoints ("Keep polling until `state` is no longer `BUILDING`", CLIENT_ACTION_REQUIRED branching, CONFIGURATION_ERROR handling). However, the numbering is incoherent: "skip to **Step 2**" appears twice and there is a "#### 1b" heading with no Step 1 or Step 2 headings, so the reader must reconstruct the flow. Matches anchor 3 (sequence present but with coherence gaps); not 4 because a 'clear sequence' is undermined by the phantom step references.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the ~140-line single-file body has reasonable section headers, but organization is rough: the "Cloudquery Overview" section is an empty bullet skeleton, "Popular actions" contains a discovery command rather than actions, and CLI reference material (proxy flag table, auth variants) is inlined without clear separation. Matches anchor 3 ('Some structure but could be better organized'); not 4 because of these structural defects, not 2 because nothing here demands extraction to a separate file and the sections remain navigable.

3 / 5

Total

13

/

20

Passed

Description

57%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 names the target product and includes an explicit use-when clause, satisfying completeness basics. However, its capability statement is generic marketing filler rather than concrete CloudQuery actions, and trigger coverage relies entirely on the product name with no synonyms or scenario phrases.

Suggestions

Replace "Manage data, records, and automate workflows" with concrete capabilities, e.g. "Query cloud infrastructure as SQL tables, run policy packs, and sync cloud asset inventory across AWS, GCP, and Azure."

Broaden trigger terms beyond the product name with phrases users actually say: "cloud asset inventory", "cloud security posture", "query cloud resources with SQL".

Make the 'when' clause scenario-specific, e.g. "Use when the user wants to inventory, query, or audit their cloud resources with SQL."

DimensionReasoningScore

Specificity

The description names the domain ("Cloudquery integration") but the actions are generic filler — "Manage data, records, and automate workflows" and "interact with Cloudquery data" — with no concrete CloudQuery capabilities such as querying cloud assets with SQL, running policy packs, or syncing resources. This matches anchor 2 ('Names the domain but actions are minimal or generic'); not 3 because not even 1-2 concrete actions are named, and not 1 because the domain is explicitly identified.

2 / 5

Completeness

Both parts are explicitly present: a 'what' ("Manage data, records, and automate workflows") and a 'when' ("Use when the user wants to interact with Cloudquery data"). Matches anchor 4 ('Has both what and when; when could be more explicit or specific'); not 5 because the 'what' is vague rather than concrete capabilities with trigger phrases, and not 3 because the 'Use when' clause is explicit rather than merely implied.

4 / 5

Trigger Term Quality

The only substantive natural keyword is "Cloudquery" itself; the common phrases a user would actually say — "cloud asset inventory", "SQL", "cloud security posture", "sync cloud resources" — are absent, leaving "data", "records", and "workflows" as generic filler. Matches anchor 3 ('Some relevant keywords but missing common variations or synonyms'); not 4 because coverage beyond the product name is thin, not 2 because the product name is itself a strong natural trigger.

3 / 5

Distinctiveness Conflict Risk

The "Cloudquery" name establishes a clear niche with minimal conflict when the product is mentioned, but generic phrases like "Manage data, records, and automate workflows" overlap with virtually any data-management skill. Matches anchor 4 ('Mostly distinct; minor overlap risk'); not 5 because of that generic overlap, and not 3 because the product-specific trigger dominates the description.

4 / 5

Total

13

/

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/cloudquery/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.