Tessl • The package manager for agent skills

Name: yumpu
Rating: 48.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

yumpu

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

Quality

53%

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/yumpu/SKILL.md

Quality

Content

45%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 CLI usage material is executable and the connection workflow has real validation checkpoints, but the document is dominated by a ~300-line inlined enumeration of generic terms that burns tokens without aiding actionability. Moving that catalog to a referenced file would dramatically improve both conciseness and progressive disclosure.

Suggestions

Move the 300-line entity/term list out of SKILL.md into a referenced file (e.g. references/entities.md) and replace it with a one-line pointer, keeping only the categories the agent actually needs at decision time.

Trim redundant or self-evident bullets (e.g. "OK", "Yes", "No", "Save", "Back", "Next") that add no actionable guidance.

Resolve the CONNECTION_ID placeholder in the worked examples with a concrete note on where to obtain it, and keep a single canonical "discover actions" snippet rather than repeating it across sections.

Dimension	Reasoning	Score
Conciseness	Roughly 300 bullet points (lines 23–331) enumerate generic terms like "Document", "User", "Save", "OK", "Yes" with no added value for Claude, making the body severely padded and a heavy token cost despite an otherwise efficient CLI section.	1 / 5
Actionability	Concrete, copy-pasteable commands are given throughout (npm install, membrane login, connection ensure, action list/run, request proxy) covering the common cases, with only minor gaps such as unresolved CONNECTION_ID placeholders.	4 / 5
Workflow Clarity	The connect-to-Yumpu flow is clearly sequenced (install → login → connection ensure → poll state) with an explicit feedback loop polling BUILDING→READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR and re-polling after the user acts; only minor checkpoint gaps remain.	4 / 5
Progressive Disclosure	There are no bundle files, yet the 300-line term enumeration is bulk content that clearly belongs in a separate reference file and is inlined into SKILL.md, leaving that section effectively unstructured despite the otherwise reasonable headers.	2 / 5
	Total	11 / 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 correctly pairs a what with an explicit when clause and is anchored to a distinct named product, but the stated capabilities are generic ("manage data, records, automate workflows") rather than concrete actions. Tightening the action list would lift specificity and trigger-term quality.

Suggestions

Replace generic verbs with concrete Yumpu actions, e.g. "convert PDFs to online magazines, manage magazines and subscriptions, pull statistics".

Expand the trigger with natural synonyms and artifacts, e.g. "Use when the user wants to publish or manage Yumpu magazines, brochures, catalogs, or fetch Yumpu analytics."

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Yumpu domain but the actions are generic and buzzwordy rather than concrete; it is not just "Processes PDF files" level of minimal, but close.	2 / 5
Completeness	Both halves are present: a (somewhat vague) what ("Yumpu integration. Manage data, records, and automate workflows") and an explicit when ("Use when the user wants to interact with Yumpu data"), though the when could be more specific.	4 / 5
Trigger Term Quality	It surfaces the product name "Yumpu" and "Yumpu data", which a user would naturally say, but offers no synonyms or variations beyond the product name itself.	3 / 5
Distinctiveness Conflict Risk	Yumpu is a specific named product and the trigger is tied to it ("interact with Yumpu data"), giving it a clear niche with minimal overlap risk against other skills.	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/yumpu/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.