Name: upwave
Rating: 51.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

upwave

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

Quality

56%

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/upwave/SKILL.md

Quality

Content

66%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 an actionable, well-structured CLI guide with concrete commands for installing, authenticating, connecting, searching, running, and proxying Upwave actions. Its main weakness is workflow clarity — the destructive/batch proxy path lacks validation checkpoints — and minor conciseness/organization slack.

Suggestions

Add an explicit validation/verification checkpoint before running mutating actions or proxy requests (e.g. confirm the resolved action/inputSchema and dry-run or echo the request before POST/PUT/DELETE), so workflow_clarity can exceed 3.

Trim redundant prose (e.g. the 'Membrane handles auth... so you can focus on integration logic' sentence) and collapse the 'Popular actions' section, which repeats the action-list command already shown under 'Searching for actions'.

Provide one concrete worked example (a real actionId and --input payload) so the run/proxy commands become fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete CLI commands and tight sections, but it includes a few unneeded explanations ('Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing') and a slightly redundant 'Popular actions' section that repeats the action-list command, fitting 'Efficient; minor instances of over-explanation'.	4 / 5
Actionability	Nearly all guidance is executable: install, login, connection ensure/get with --wait, action list/run with --input, and a proxy table of flags. Minor gaps (e.g. CONNECTION_ID placeholder handling, no example action id) keep it just below fully copy-paste-ready, matching 'Mostly executable guidance; concrete code or commands with minor gaps'.	4 / 5
Workflow Clarity	The connection setup sequence (ensure → poll state → handle CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) is well laid out, but there is no validation step before running actions or proxy requests, and the destructive/batch proxy path (POST/PUT/DELETE via `membrane request`) has no verify-before-proceed checkpoint, capping workflow_clarity at 3 per the destructive/batch validation guideline.	3 / 5
Progressive Disclosure	Content is well organized into clear sections (Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices) with no bundle files present and references kept inline and shallow; only minor gaps (the overview's entity list and 'Popular actions' could be trimmed) keep it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

46%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 anchors the skill to a distinct platform (Upwave) and includes a 'Use when' trigger, giving it reasonable distinctiveness and completeness. Its weakness is specificity and trigger-term coverage — the stated actions ('manage data, records, automate workflows') are generic and lack the concrete, natural phrases a marketing user would say.

Suggestions

Replace generic actions ('Manage data, records, and automate workflows') with concrete Upwave-specific capabilities, e.g. 'create surveys, fetch study responses, manage target groups and workspaces'.

Broaden trigger terms to the natural phrases users say, e.g. 'Use when the user wants to run surveys, check campaign/ad measurement, or pull Upwave study and response data'.

Add at least one concrete trigger phrase tied to Upwave's domain (surveys, brand studies, ad impact analytics) to push completeness above 3.

Dimension	Reasoning	Score
Specificity	The description names the domain (Upwave) and a few generic action categories ('Manage data, records, and automate workflows') but these are abstract and not concrete, platform-specific actions — matching 'Names the domain but actions are minimal or generic' rather than the 3 anchor which requires 1-2 truly concrete actions.	2 / 5
Completeness	It has a clear 'what' (Upwave integration for managing data/records/workflows) and a 'Use when...' clause, but the 'when' is generic ('wants to interact with Upwave data') and lacks concrete trigger phrases, capping completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	'Upwave' and 'interact with Upwave data' provide the core natural term a user would say, but coverage is thin — no synonyms or variations like 'surveys', 'ad performance', or 'campaign analytics' that a marketing user might naturally say, fitting 'Some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Tying the skill specifically to 'Upwave' gives it a clear niche unlikely to trigger for other skills; it is mostly distinct with only minor overlap risk against generic data-management skills, fitting 'Mostly distinct; minor overlap risk'.	4 / 5
	Total	12 / 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/upwave/SKILL.md
Commit: f484c82

Reviewed: 3 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.