Name: thanksio
Rating: 62.4 (1 reviews)
Author: membranedev

thanksio

Thanks.io integration. Manage Persons, Organizations, Addresses, Campaigns, Orders. Use when the user wants to interact with Thanks.io data.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/thanksio/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 executable commands and a clear overview, but it loses workflow-clarity points because destructive/batch actions lack validation checkpoints. Conciseness and structure are strong with minor tightening opportunities.

Suggestions

Add an explicit validation/confirmation checkpoint before destructive commands (cancel-order, delete-recipient, delete-mailing-list): instruct Claude to confirm the target id with the user and verify the returned status before proceeding.

Trim narrative sentences that explain what the CLI does for Claude (e.g. 'Membrane handles authentication and credentials refresh automatically - so you can focus on the integration logic rather than auth plumbing') to keep the body lean.

Move the detailed clientAction type taxonomy and the proxy flag table into a references file, linked from the body, to deepen progressive disclosure and reduce inline length.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with copy-paste-ready CLI commands and tables, but a few sections over-explain what the CLI does (e.g. 'Membrane handles authentication and credentials refresh automatically' narrative) that could be trimmed.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands for install, auth, connection, action search, action run, and proxy requests, with concrete flags and a populated popular-actions table covering common cases.	5 / 5
Workflow Clarity	The connect-to-build-ready polling sequence is laid out, but batch/destructive operations (cancel-order, delete-recipient, delete-mailing-list) lack explicit validation or confirm-before-proceed checkpoints, which caps workflow clarity per the destructive-operations guideline.	3 / 5
Progressive Disclosure	Content is well-sectioned (Overview, Install, Auth, Connecting, Searching, Popular actions, Best practices) with no nested references and no bundle files needed; the only gap is that the inlined client-action taxonomy and proxy flag table could live in reference files for a longer skill.	4 / 5
	Total	16 / 20 Passed

Description

71%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 specific and distinct, naming concrete managed entities and an explicit use-when clause. Its main weakness is generic trigger phrasing and product jargon in the description rather than natural user vocabulary.

Suggestions

Reword the trigger to natural user phrasing, e.g. 'Use when the user wants to send postcards, letters, notecards, or gift cards via Thanks.io' so Claude matches it to common requests.

Lead the description with the concrete verbs users care about ('Send and track direct mail: postcards, letters, notecards, and gift cards') rather than generic object lists like 'Persons, Organizations'.

Add common synonyms/file extensions users say ('direct mail', 'handwritten cards', 'mail campaigns') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Thanks.io integration) and enumerates concrete object types managed ('Persons, Organizations, Addresses, Campaigns, Orders'), which is several specific entities, though it relies on action names rather than explicit verbs.	4 / 5
Completeness	It states both the 'what' ('Manage Persons, Organizations, Addresses, Campaigns, Orders') and the 'when' ('Use when the user wants to interact with Thanks.io data'), but the trigger phrase is generic and could be more specific.	4 / 5
Trigger Term Quality	It surfaces domain terms users might say ('Cards, letters', 'direct mail', 'Thanks.io') only in the body, while the description itself uses product jargon ('Persons, Organizations') and a generic trigger ('interact with Thanks.io data'), missing common variations a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The Thanks.io direct-mail niche, with its named objects, is a clear distinct trigger with minimal overlap risk against other skills.	5 / 5
	Total	16 / 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/thanksio/SKILL.md
Commit: f484c82

Reviewed: ~21 hours 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.