Name: tradogram
Rating: 50.4 (1 reviews)
Author: membranedev

tradogram

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

Quality

55%

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/tradogram/SKILL.md

Quality

Content

50%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 content is highly actionable with concrete Membrane CLI commands and a clear connection state machine, but it is dragged down by a bloated inline entity list and a lack of validation feedback loops for action execution. There are no external reference files despite content that would benefit from splitting.

Suggestions

Move the ~110-line entity enumeration into a references/ file (e.g. ENTITIES.md) and summarize it in SKILL.md with a one-level-deep link, cutting the bulk of the token cost.

Add a validation step after running actions, e.g. re-query or inspect the output field to confirm the operation succeeded before reporting completion to the user.

Prune generic entities from the overview (User, Address, Note, Tag, File, Image, Video, Audio, Link, Comment) that do not aid action discovery, or fold line-item sub-entities into their parents.

Dimension	Reasoning	Score
Conciseness	The ~110-line 'Tradogram Overview' entity enumeration (Purchase Order through Subscription, including generic noise like User, Address, Note, Tag, File, Image, Audio) is a noticeably padded section that inflates the token budget, fitting 'noticeably verbose; several unnecessary explanations or padded sections' better than the mostly-efficient anchor at 3.	2 / 5
Actionability	Concrete, copy-paste-ready commands are provided throughout (npm install, membrane login, connection ensure, action list/run, request proxy) with a flags table, fitting 'mostly executable guidance; concrete code or commands with minor gaps'; it stops short of 5 only because identifiers are placeholders (CONNECTION_ID, actionId) and a worked end-to-end example is absent.	4 / 5
Workflow Clarity	A reasonable sequence exists (install -> authenticate -> connect -> poll for READY -> search -> run/proxy) with good state-checkpointing on connection state, but running actions performs potentially batch/destructive data operations with no post-run verification step, so per the destructive/batch cap it cannot exceed the 'steps listed but validation gaps' anchor at 3.	3 / 5
Progressive Disclosure	Sections are organized, but the large entity list is inlined in SKILL.md rather than split into a one-level-deep reference file, and no external references exist, matching 'some structure but could be better organized; content that should be separate is inline' rather than the well-split anchor at 4.	3 / 5
	Total	12 / 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 identifies a distinct product niche and includes both a what and a when clause, but its action verbs are generic and the trigger phrase lacks concrete variations. It is solid but padded with vague terms like 'manage data' and 'automate workflows'.

Suggestions

Replace generic verbs with concrete operations, e.g. 'Create and track purchase orders, manage suppliers, and approve requisitions' instead of 'Manage data, records, and automate workflows'.

Expand the 'Use when' trigger with concrete phrases users would actually say, such as 'Use when the user wants to create purchase orders, manage suppliers, or query Tradogram records'.

Drop buzzword padding like 'automate workflows' unless a specific automation capability is being advertised.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Tradogram integration") but its actions are generic and minimal — "Manage data, records, and automate workflows" are vague nouns/buzzwords rather than concrete operations, fitting the 'names the domain but actions are minimal or generic' anchor better than the '1-2 concrete actions' anchor at 3.	2 / 5
Completeness	Both 'what' ("Manage data, records, and automate workflows") and 'when' ("Use when the user wants to interact with Tradogram data") are present, but the 'when' trigger is fairly generic rather than concrete, fitting 'has both what and when; when could be more explicit or specific' rather than the fully explicit anchor at 5.	4 / 5
Trigger Term Quality	The only natural keyword is the product name itself ("Tradogram", "interact with Tradogram data"), giving some relevant coverage but no synonyms or variations, matching the 'some relevant keywords but missing common variations' anchor; it is not below it (jargon-only) nor above it (broad natural-term coverage).	3 / 5
Distinctiveness Conflict Risk	Naming a specific commercial product ("Tradogram") with an explicit "interact with Tradogram data" trigger creates a clear niche with minimal conflict risk against other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	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/tradogram/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.