Name: rosette-text-analytics
Rating: 48 (1 reviews)
Author: membranedev

rosette-text-analytics

Rosette Text Analytics integration. Manage Organizations. Use when the user wants to interact with Rosette Text Analytics data.

Quality

51%

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/rosette-text-analytics/SKILL.md

Quality

Content

61%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 solid, mostly-executable runbook for driving Rosette via the Membrane CLI, with good structure and concrete commands. It loses points for an unnecessary introductory paragraph explaining NLP concepts, inconsistent step numbering, and absent validation checkpoints on run/proxy operations.

Suggestions

Trim the opening overview paragraph that explains what Rosette/NLP is — Claude already knows this.

Add explicit validation/verification for run and proxy steps (e.g. check the `output` field, handle non-2xx from `membrane request`).

Fix the step numbering inconsistency: '1b' appears with no '1a'/'Step 2' label, making the multi-step connection flow harder to follow.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient command-and-output documentation, but the opening paragraph explains what Rosette Text Analytics is (NLP suite, used by businesses to extract information) — concepts Claude already knows — and some sections restate Membrane auth behavior that could be trimmed.	3 / 5
Actionability	Commands are concrete and copy-paste ready (install, login, connection ensure, action run/list, request) with flag tables and JSON examples; the only gap is that action run examples use placeholder action IDs and connection IDs without showing how to resolve them end-to-end.	4 / 5
Workflow Clarity	The connection flow is sequenced with state handling (READY/BUILDING/CLIENT_ACTION_REQUIRED) and polling guidance, but operations like action run and proxy requests lack validation or verification checkpoints, and the step numbering is inconsistent (jumps from '1b' with no explicit 'Step 2').	3 / 5
Progressive Disclosure	Content is well organized into labeled sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) with a clear Popular actions table; no bundle files exist so everything is inline, but the structure is appropriate and navigable for a single-file skill.	4 / 5
	Total	14 / 20 Passed

Description

41%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 identifies the product and includes a 'Use when' clause, but it is thin on concrete capabilities and natural trigger terms, listing only 'Manage Organizations' while the body covers sentiment, entities, translation, and more. It reads as a generic integration hook rather than a well-scoped trigger.

Suggestions

List the concrete capabilities users will request, e.g. 'Extract entities, analyze sentiment, translate names, detect language, tokenize text'.

Add natural trigger terms users would actually say: 'sentiment analysis', 'entity extraction', 'name translation', 'language detection'.

Tighten the 'Use when' clause with specific triggers rather than the generic 'interact with Rosette Text Analytics data'.

Dimension	Reasoning	Score
Specificity	It names the domain ('Rosette Text Analytics integration') and one concrete action ('Manage Organizations'), but the action set is minimal and generic — the body reveals many real capabilities (sentiment, entities, translation, morphology) that the description omits, so it is below the 3-anchor's '1-2 concrete actions' bar.	2 / 5
Completeness	There is a clear 'what' (Rosette Text Analytics integration / Manage Organizations) and an explicit 'Use when' clause, but the trigger is generic ('wants to interact with Rosette Text Analytics data') rather than concrete trigger phrases, which matches the 3-anchor 'what clear, when weakly implied'.	3 / 5
Trigger Term Quality	The only natural phrase is 'Rosette Text Analytics'; otherwise it relies on the product name and the generic 'interact with ... data', missing the natural terms a user would actually say (sentiment, entities, translation, name matching, language detection).	2 / 5
Distinctiveness Conflict Risk	The Rosette Text Analytics niche is fairly specific and unlikely to collide with unrelated skills, though the generic 'interact with data' phrasing leaves minor overlap risk with other analytics integrations.	4 / 5
	Total	11 / 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/rosette-text-analytics/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.