Name: sendowl
Rating: 60 (1 reviews)
Author: membranedev

sendowl

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

Quality

70%

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/sendowl/SKILL.md

Quality

Content

78%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 and well-sequenced with validation checkpoints in the connection flow, but it inlines reference-grade detail that would benefit from being split into separate files. It is concise enough though slightly padded in a few spots.

Suggestions

Move the proxy flag table and the full clientAction state reference into separate reference files (e.g. PROXY.md, CONNECTION_STATES.md) and link to them from the body.

Drop or trim the 'Popular actions' section that repeats the action-list command already shown in 'Searching for actions'.

Add an explicit error-recovery checkpoint for CONFIGURATION_ERROR/SETUP_FAILED (e.g. read the error field, surface it to the user, then retry) to close the workflow gap.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, with only minor over-explanation such as the 'Popular actions' section restating the action-list command and the introductory platform description.	4 / 5
Actionability	It provides copy-paste-ready, executable commands throughout (install, login, connection ensure, action list/run, request) plus a concrete proxy flag table, covering the common cases.	5 / 5
Workflow Clarity	The connection flow is clearly sequenced with state-checking checkpoints and a poll-after-action feedback loop, with only minor gaps in explicit retry/error-recovery guidance.	4 / 5
Progressive Disclosure	Sections are present and reasonably organized, but the ~143-line body inlines detail that could live in separate files (the proxy flag table, the full clientAction state reference) and references no bundle files for deeper material.	3 / 5
	Total	16 / 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 branded and includes both a 'what' and a 'when' clause, but its action language is generic and the trigger coverage relies almost entirely on the SendOwl name. Tightening the actions to concrete SendOwl entities and adding natural synonyms would lift it.

Suggestions

Replace generic actions with concrete SendOwl capabilities, e.g. 'Manage products, orders, subscriptions, customers, and discounts'.

Expand the trigger clause with natural phrasings a user would say, e.g. 'Use when the user wants to query SendOwl orders, manage products, or look up customers'.

Mention the data entities already documented in the body (Product, Order, Bundle, Subscription) so the description previews the actual scope.

Dimension	Reasoning	Score
Specificity	The description names the SendOwl domain and lists a few actions ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete — it stops short of naming specific SendOwl capabilities like orders, products, or subscriptions.	3 / 5
Completeness	Both 'what' (SendOwl integration managing data, records, workflows) and 'when' ('Use when the user wants to interact with SendOwl data') are present, though the 'when' clause is somewhat generic and could be more specific.	4 / 5
Trigger Term Quality	The natural keyword 'SendOwl' appears, but coverage is thin — only 'SendOwl data' as the trigger phrase, with no common variations or synonyms a user might actually say.	3 / 5
Distinctiveness Conflict Risk	The SendOwl brand name is a clear, distinct trigger with a narrow niche, leaving only minor overlap risk because the surrounding action language ('manage data, records') is generic.	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/sendowl/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.