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

qadeputy

QADeputy integration. Manage data, records, and automate workflows. Use when the user wants to interact with QADeputy 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/qadeputy/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 delivers concrete, executable Membrane CLI commands in a reasonably clear workflow with a state-based polling checkpoint. Its main weaknesses are padding (the overview paragraph and entity list) and slightly inconsistent step numbering.

Suggestions

Trim the opening "what is QADeputy" paragraph and the long bulleted entity list, or move the entity list into a reference file, since Claude does not need QADeputy explained.

Make the connection workflow's step numbering consistent (label the "Connecting to QADeputy" section as Step 1 so the later "Step 2" and "1b" references resolve).

Add one fully worked end-to-end example with real-looking values filled in for CONNECTION_ID and actionId so the run-actions section is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable commands, but the opening "QADeputy is a quality assurance and testing management platform..." paragraph and the long bulleted entity list are padding Claude does not need, fitting the "mostly efficient but includes some unnecessary explanation" anchor.	3 / 5
Actionability	It provides concrete copy-paste commands throughout ("npm install -g @membranehq/cli@latest", "membrane connection ensure", "membrane action run"), but commands rely on placeholders like CONNECTION_ID and actionId without a fully worked example, fitting the "mostly executable; minor gaps" anchor.	4 / 5
Workflow Clarity	There is a clear install→authenticate→connect→poll→search→run sequence with a state-based polling checkpoint (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), but step numbering is inconsistent ("Step 2" appears without a clean "Step 1" label) leaving minor gaps, fitting the "clear sequence with most checkpoints" anchor.	4 / 5
Progressive Disclosure	The single file is well-sectioned (Overview, Working with QADeputy, Authentication, Connecting, Searching, Running actions, Proxy, Best practices) with no nested references and an external docs link, fitting the "good structure; most content appropriately placed" anchor; the inlined entity list is the only content that might belong elsewhere.	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 clearly identifies the QADeputy niche and includes an explicit "Use when" trigger, but its action language is generic and it lacks natural keyword variations. Strengthening the trigger phrasing and listing concrete operations would raise it.

Suggestions

Replace generic verbs with concrete QADeputy operations (e.g., "create test cases, track defects, manage test runs") so the "what" is specific rather than "manage data, records".

Expand the "Use when" clause with natural user phrasings and synonyms (e.g., "Use when the user wants to manage test cases, log defects, or run QA reports in QADeputy").

Add file-extension or entity keywords users actually say (e.g., test cases, defects, test runs) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the QADeputy domain and a few actions, but the actions ("manage data", "records") are generic rather than concrete, matching the domain-plus-minimal-actions anchor; not a 2 because multiple items are listed, not a 4 because none are specific concrete operations.	3 / 5
Completeness	It states what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with QADeputy data") explicitly, but the trigger clause is generic rather than concrete phrases, so it fits the "both what and when, when could be more specific" anchor below the 5.	4 / 5
Trigger Term Quality	The keywords "QADeputy", "data", "records", and "workflows" are relevant but there are no synonyms, natural phrasings, or variations users might say beyond the brand name, fitting the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The QADeputy brand name gives it a clear niche with low conflict risk, but the generic "manage data, records, automate workflows" action language creates minor overlap with other data-management skills, fitting the "mostly distinct; minor overlap risk" anchor.	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/qadeputy/SKILL.md
Commit: f484c82

Reviewed: 5 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.