Name: gradeus
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

gradeus

Grade.us integration. Manage Organizations. Use when the user wants to interact with Grade.us data.

Quality

68%

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/gradeus/SKILL.md

Quality

Content

76%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 highly actionable with copy-paste CLI commands, a useful connection-readiness polling loop, and clean section structure. Its main weakness is workflow clarity: destructive delete operations lack validation/verification checkpoints, capping that dimension at 3, and step numbering is inconsistent.

Suggestions

Add a validation/verification step before destructive operations (e.g., confirm the profile UUID via get-profile, then re-list to confirm deletion) so delete actions include a feedback loop.

Fix the step numbering — label 'Step 1: Connect' and 'Step 2: Search & run actions' explicitly instead of an orphaned '1b' and an unlabeled 'Step 2'.

Consider moving the large popular-actions table and proxy flag reference into a separate reference file to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable commands and tables with little padding; the brief opening reputation-management paragraph and a few explanatory sentences are minor over-explanation that could be trimmed, matching 'Efficient; minor instances of over-explanation'; not 5 because of those small trimmable passages.	4 / 5
Actionability	Copy-paste-ready commands with concrete flags (e.g. `membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json`) plus a popular-actions table cover the common cases, matching 'Fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	A sequence exists (install → authenticate → connect → poll until READY → search → run) with a polling checkpoint, but destructive actions (delete-profile, delete-link, delete-user) have no validation/verification steps, which caps workflow clarity at 3 per the destructive-operations rule; step numbering is also muddled ('1b' with an unlabeled 'Step 2').	3 / 5
Progressive Disclosure	No bundle files exist and the skill is a single self-contained file with clear section headers and no nested references, matching 'Good structure; most content is appropriately placed; minor organization gaps'; not 5 because the sizable popular-actions/proxy reference is inlined rather than split out for a >50-line skill.	4 / 5
	Total	16 / 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 names a clear niche (Grade.us) and includes an explicit 'Use when' trigger, satisfying the completeness floor, but the capability list is minimal ('Manage Organizations') and lacks natural synonyms like 'reviews' or 'reputation'. It is distinct and non-conflicting but thinner than the strongest examples.

Suggestions

Expand the 'what' to list 2-3 concrete capabilities (e.g., 'List and respond to reviews, manage profiles, recipients, and links') instead of only 'Manage Organizations'.

Add natural trigger synonyms users actually say, such as 'reviews', 'reputation management', or 'review requests', so the skill surfaces for those phrasings.

Tighten the trigger to concrete situations, e.g. 'Use when the user wants to list, request, or respond to Grade.us reviews or manage Grade.us profiles.'

Dimension	Reasoning	Score
Specificity	Quotes "Grade.us integration. Manage Organizations." name the domain and a single minimal/generic action, matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because only one action is named and coverage is not comprehensive.	2 / 5
Completeness	Both clauses are present — a 'what' ("Manage Organizations") and an explicit 'when' ("Use when the user wants to interact with Grade.us data"), matching 'Has both what and when; when could be more explicit or specific'; not 5 because the 'what' is thin and the trigger phrasing is generic rather than concrete.	4 / 5
Trigger Term Quality	The phrase "Use when the user wants to interact with Grade.us data" supplies the product name as a keyword but omits natural synonyms users would say (reviews, reputation management), matching 'Some relevant keywords but missing common variations or synonyms'; not 4 because keyword coverage is thin and repetitive.	3 / 5
Distinctiveness Conflict Risk	"Grade.us integration" targets a specific named product with distinct triggers and minimal overlap risk, matching 'Clear niche with distinct triggers; minimal conflict risk'; voice is third person so no penalty applies.	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/gradeus/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.