Name: cloudtables
Rating: 56.8 (1 reviews)
Author: membranedev

cloudtables

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/cloudtables/SKILL.md

Quality

Content

67%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 highly actionable with concrete CLI commands and a well-sequenced connection workflow including polling feedback loops. Its main weaknesses are padding in the overview, a dangling "Step 2" reference, missing pre-destructive validation, and an action/flag catalog that could be split into reference files.

Suggestions

Remove the introductory SaaS-description paragraph and the empty CloudTables Overview bullets; lead directly with what the skill does and the CLI workflow.

Add an explicit numbered "Step 2: Search for actions" heading so the "skip to Step 2" reference resolves, and insert a validation/confirmation step before destructive actions such as delete-row.

Move the full Popular actions table and proxy flag reference into a references/ file (e.g. ACTIONS.md) and link to it from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The CLI command sections are efficient, but the opening "CloudTables is a SaaS application that provides a data table solution..." paragraph and the bare "CloudTables Overview" bullet list (Table/Column/Row/User/Group) explain concepts and structure Claude already knows. Not a 4 because those padded sections are clearly trimmable; not a 2 because the bulk is actionable commands rather than pervasive verbosity.	3 / 5
Actionability	Concrete, copy-paste-ready commands cover install, auth, connection, action search/run, and proxying with flag tables. Not a 5 because every example uses placeholders (<actionId>, CONNECTION_ID) and the Popular actions descriptions are truncated, leaving minor gaps in fully-worked examples.	4 / 5
Workflow Clarity	The connection workflow is clearly sequenced with state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) and polling feedback loops ("poll again" after user action). Not a 5 because the referenced "Step 2" has no matching numbered heading and there is no validation/confirmation guidance before destructive actions like delete-row.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clearly headed sections with easy navigation and no bundle files to manage. Not a 5 because at ~150 lines (above the 50-line simple-skill threshold) the action catalog and proxy flag tables are inlined rather than split into reference files.	4 / 5
	Total	15 / 20 Passed

Description

62%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 answers both what and when with an explicit trigger and benefits from a distinct product brand, but its action list and trigger keywords are generic and narrow. Tightening with concrete operations and broader natural synonyms would lift the lower dimensions.

Suggestions

Replace generic verbs with concrete CloudTables operations, e.g. "Create, update, and delete rows; retrieve dataset data and schemas; embed tables via access tokens."

Expand the trigger clause to cover natural phrasings: "Use when the user wants to query, edit, or embed CloudTables data, datasets, or tables."

Add a reference to embedding/access tokens in the description since Get Access Token is a headline capability.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the CloudTables domain plus 2-3 actions, but the actions are generic rather than concrete and coverage is not comprehensive. Not a 2 because more than one action is named; not a 4 because no specific concrete operations (e.g. create/delete rows, embed tables) are listed.	3 / 5
Completeness	Both "what" (manage data, records, automate workflows) and "when" ("Use when the user wants to interact with CloudTables data") are present and explicit. Not a 5 because the trigger is a single narrow condition rather than concrete multi-phrase triggers.	4 / 5
Trigger Term Quality	The trigger "interact with CloudTables data" surfaces "CloudTables" and "data" but misses common natural synonyms a user would say ("tables", "datasets", "records"). Not a 4 because keyword coverage is narrow with no variations or extensions.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to the specific CloudTables brand gives it a clear niche with low conflict risk. Not a 5 because the generic "manage data, records" framing could still overlap with other data-management skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/cloudtables/SKILL.md
Commit: f484c82

Reviewed: ~11 hours 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.