Name: sigma
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

sigma

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

Quality

60%

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

Fix and improve this skill with Tessl

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

Quality

Content

70%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 content is well-organized, command-driven, and actionable with a clear connection-state workflow and feedback loop, scoring well on actionability and workflow clarity. It loses points for a dangling 'Step 2' reference and for progressive disclosure, since no reference files exist to split out the inline API/proxy material.

Suggestions

Resolve the undefined 'Step 2' reference (referenced from the READY/CLIENT_ACTION_REQUIRED branches) — either add the section or remove the forward references.

Move the proxy request flag table and detailed clientAction schema into a separate reference file linked from the body to improve progressive disclosure and token efficiency.

Add a brief validation/check step after running actions (e.g. checking the `output` field or error states) to strengthen workflow clarity for batch operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command-focused documentation with executable CLI snippets and minimal conceptual padding, though the opening paragraph and a few explanatory sentences (e.g. what Membrane handles) could be trimmed slightly.	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready CLI commands (membrane login, connection ensure, action list/run, request) with flags and JSON examples, with only minor gaps such as placeholder CONNECTION_ID handling and the dangling 'Step 2' reference.	4 / 5
Workflow Clarity	The connect-to-Sigma flow is clearly sequenced with a state-polling feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/error) and re-poll guidance, though the section references a 'Step 2' that is never defined and batch/destructive validation is not addressed.	4 / 5
Progressive Disclosure	No bundle files (references/scripts/assets) exist and the body is a single self-contained document; structure is reasonable with clear section headers, but there is no file-split or one-level-deep reference structure to elevate it above the inlined-content baseline.	3 / 5
	Total	15 / 20 Passed

Description

51%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 a distinct product and includes an explicit Use-when clause, but the capability and trigger language is generic ('manage data, records, automate workflows', 'interact with Sigma data') rather than concrete Sigma-specific actions and natural terms. It clears a usable baseline but misses the specificity and trigger-term richness of strong examples.

Suggestions

Replace generic verbs with Sigma-specific actions, e.g. 'Query Sigma datasets, build and edit workbooks and dashboards, manage connections, and automate data workflows.'

Add natural trigger terms and synonyms users actually say, e.g. 'Use when the user mentions Sigma, Sigma workbooks/dashboards, Sigma datasets, or wants to query or visualize Sigma analytics.'

Mention concrete object types (workbooks, sheets, datasets, connections) that map to the skill's actions to improve both specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain (Sigma) and concrete actions ('Manage data, records, and automate workflows') but the actions are generic verbs without specifics like 'query', 'build dashboards', or 'refresh datasets', so coverage is partial rather than comprehensive.	3 / 5
Completeness	Has a clear 'what' ('Sigma integration. Manage data, records, and automate workflows.') with an explicit 'Use when...' clause, but the trigger guidance is generic ('interact with Sigma data') and the capping rule for a weakly-specific 'when' keeps it from scoring 4.	3 / 5
Trigger Term Quality	Includes the trigger phrase 'Use when the user wants to interact with Sigma data' but lacks synonyms or natural variants users would say (e.g., 'Sigma dashboards', 'Sigma workbooks', 'Sigma analytics'), keeping it at the some-relevant-keywords level.	3 / 5
Distinctiveness Conflict Risk	Tied to a distinct named product (Sigma analytics), so it is unlikely to trigger for unrelated skills, though the generic verb set ('manage data, records, automate workflows') leaves minor overlap risk with generic data skills.	4 / 5
	Total	13 / 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/sigma/SKILL.md
Commit: f484c82

Reviewed: 4 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.