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

Blog Docs Log in Get started

dub

Dub integration. Manage Links, Workspaces. Use when the user wants to interact with Dub 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/dub/SKILL.md

Quality

Content

68%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 well-structured and highly actionable with executable Membrane CLI commands and a clear connection-state workflow. Its main gaps are missing validation guidance for destructive actions and minor padding in the overview and action tables.

Suggestions

Add an explicit validation/confirmation checkpoint before destructive actions (e.g., 'Before running delete-link, confirm the target linkId with the user or list-links first').

Fill the empty Description column in the Popular actions table so action selection is self-contained, or link to a separate action reference file.

Tighten the opening paragraph and the flat entity list to remove marketing phrasing and keep only what Claude needs to navigate the API.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable commands and tables with clear section headers, but the opening marketing-flavored description ("used by marketers and creators... branded links") and the 16-item undifferentiated entity list are minor padding that could be trimmed, fitting the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	It provides concrete, copy-paste-ready commands covering the common cases (login, connect, search, run, proxy), but uses unsubstituted placeholders (CONNECTION_ID, actionId) and the popular-actions table has blank Description cells, fitting the 'mostly executable guidance; minor gaps' anchor rather than fully complete.	4 / 5
Workflow Clarity	The connection workflow has a clear state-driven sequence with polling checkpoints, but the action workflow exposes destructive operations (delete-link) with no verification step, and 'Step 2' is referenced but never labeled, so the destructive-operation validation cap applies per the rubric.	3 / 5
Progressive Disclosure	With no bundle files present, the single SKILL.md is organized into clear, navigable sections (Install, Auth, Connecting, Searching, Popular actions, Running, Proxy, Best practices); the inlined popular-actions table and entity list are minor bulk that could be split out, fitting the 'good structure; minor organization gaps' anchor.	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 is concise, uses third person, and answers both what and when with a clear app-specific trigger. Its main weakness is generic action vocabulary ("Manage") and limited keyword variation rather than concrete capability verbs.

Suggestions

Replace the generic verb "Manage" with specific concrete actions, e.g., "Shorten, track, and update links; create and organize workspaces."

Expand the trigger clause with natural user phrases, e.g., "Use when the user wants to shorten or track links, manage branded links, or work with Dub workspaces."

Dimension	Reasoning	Score
Specificity	It names the domain (Dub) and two concrete objects ("Manage Links, Workspaces"), but uses a single generic verb ("Manage") rather than listing several specific actions, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It has both a what ("Dub integration. Manage Links, Workspaces.") and an explicit when ("Use when the user wants to interact with Dub data"), but the when is somewhat generic rather than a concrete trigger phrase, matching the 'has both what and when; when could be more specific' anchor.	4 / 5
Trigger Term Quality	It includes relevant natural terms ("Dub", "Links", "Workspaces", "interact with Dub data"), but misses common variations and synonyms users would say (e.g., shorten links, track clicks, branded links), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Dub" is a specific named app with a clear niche and the trigger references it explicitly, giving minimal conflict risk, though "Links, Workspaces" could overlap slightly with generic link-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/dub/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.