Name: tiendanube
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

tiendanube

Tiendanube (Nuvemshop) integration. Manage Recordses. Use when the user wants to interact with Tiendanube (Nuvemshop) data.

Quality

64%

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/tiendanube/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 action-dense and well-structured, with an explicit state-driven connection workflow that includes feedback loops, making it genuinely usable. Its main weaknesses are minor verbosity in introductory prose, a few placeholder/inconsistency gaps in commands, and a dangling 'Step 2' cross-reference.

Suggestions

Trim the generic opener and auth-plumbing prose to lift conciseness toward lean, command-focused content.

Reconcile the `membrane` vs `npx @membranehq/cli@latest` invocation styles and show how to obtain CONNECTION_ID/actionId from prior command output to close actionability gaps.

Fix the dangling 'Skip to Step 2' reference by adding a labeled Step 2 heading or rewriting the pointer.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands, but includes some unnecessary prose such as the generic opener 'is a data management platform... discover its full capabilities' and 'so you can focus on the integration logic rather than auth plumbing', matching the 'Mostly efficient but includes some unnecessary explanation or could be tightened' anchor; it is below 4 due to these padding spots and above 2 because the bulk is concrete.	3 / 5
Actionability	It provides concrete, mostly copy-paste-ready bash commands (login, connection ensure, action list/run, request) covering the common cases, matching 'Mostly executable guidance; concrete code or commands with minor gaps'; it does not reach 5 because placeholders like <actionId> and CONNECTION_ID require substitution and there is inconsistency between `membrane` and `npx @membranehq/cli` invocations.	4 / 5
Workflow Clarity	The connection setup is a clear state-driven sequence with explicit checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and feedback loops (poll until ready, re-poll after user action), matching 'Clear sequence with most checkpoints present; minor validation gaps'; it is capped below 5 by a dangling 'Skip to Step 2' reference with no corresponding Step 2 heading.	4 / 5
Progressive Disclosure	The skill is a single self-contained SKILL.md with well-organized sections and no nested references, matching 'Good structure; most content appropriately placed; minor organization gaps'; it is below 5 because at ~150 lines some content (the proxy options table, clientAction schema) could be split out, and above 3 because sections are clearly headed and navigable.	4 / 5
	Total	15 / 20 Passed

Description

61%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 is well-distinctive thanks to the named platform and dual brand spellings, and covers both what and when, but its capability statement ('Manage Recordses') is generic and the trigger phrasing lacks concrete task-specific keywords. Tightening the action list and trigger terms would raise specificity and trigger quality.

Suggestions

Replace the generic 'Manage Recordses' with enumerated concrete actions (e.g., 'create, read, update, delete, and list records') to lift specificity.

Add concrete natural trigger phrases beyond 'interact with data' (e.g., 'when the user mentions orders, products, or store data') to improve trigger term quality and completeness.

Correct or clarify the term 'Recordses' which appears to be a typo of 'Records'.

Dimension	Reasoning	Score
Specificity	The description names the domain (Tiendanube/Nuvemshop) but only offers the single generic verb 'Manage Recordses' with no enumerated concrete actions, matching the 'Names the domain but actions are minimal or generic' anchor; it does not reach 3 because there are not two listed actions, and it is above 1 because the domain is named.	2 / 5
Completeness	It states both what ('Manage Recordses') and when ('Use when the user wants to interact with Tiendanube (Nuvemshop) data'), matching the 'Has both what and when; when could be more explicit or specific' anchor; it does not reach 5 because the trigger is generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes both brand spellings 'Tiendanube (Nuvemshop)' and the natural phrase 'interact with... data', giving some relevant keywords, but it misses common task variations or synonyms, fitting the 'Some relevant keywords but missing common variations or synonyms' anchor; it falls short of 4 because the keyword set is thin.	3 / 5
Distinctiveness Conflict Risk	Naming a specific platform (Tiendanube/Nuvemshop) with both brand spellings gives a clear niche with distinct triggers and minimal conflict risk, matching the 'Clear niche with distinct triggers; minimal conflict risk' anchor; it is above 4 because the platform identity makes overlap with other skills unlikely.	5 / 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/tiendanube/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.