Name: onna
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

onna

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

Quality

63%

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/onna/SKILL.md

Quality

Content

61%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 concrete CLI commands and a solid connection-state feedback loop, but it is padded with marketing/background prose, has a broken 'Step 2' navigation reference and redundant sections, and keeps some content inline that could be better organized. It is a competent integration guide with room to tighten.

Suggestions

Delete the background paragraph and marketing phrasing ('auth plumbing', 'burn less tokens') so only integration-relevant detail remains.

Fix the workflow numbering: replace the dangling 'Step 2' references with a coherent numbered sequence (install -> authenticate -> connection ensure -> wait -> search -> run) and merge the redundant 'Searching for actions' and 'Popular actions' sections.

Explain how to obtain CONNECTION_ID inline (from the connection ensure output) so the run/request examples are fully self-contained.

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but includes unnecessary background ('Onna is a knowledge integration platform...') and marketing phrasing ('so you can focus on the integration logic rather than auth plumbing', 'burn less tokens'), fitting the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean level 4.	3 / 5
Actionability	It provides many copy-paste-ready commands (install, login, connection ensure, action list/run, request) with flags and a full proxy-options table, but uses placeholders like CONNECTION_ID whose sourcing is only implicit, fitting 'mostly executable guidance with minor gaps' below the fully-covered level 5.	4 / 5
Workflow Clarity	A connection sequence with state-based polling checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) exists, but the flow references a 'Step 2' that has no header, the '1b' subsection has no '1a', and the 'Searching' and 'Popular actions' sections are redundant, fitting 'sequence present but checkpoints missing or implicit' below the clean level 4.	3 / 5
Progressive Disclosure	Content is organized into clear labeled sections with no nested external references (appropriate for a single CLI skill over 50 lines), but some inlined material (the proxy flags table, detailed connection-state handling) and redundant sections leave minor organization gaps, fitting 'good structure; most content appropriately placed' below the cleanly-split level 5.	4 / 5
	Total	14 / 20 Passed

Description

66%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 pairs an explicit 'Use when' trigger with the distinctive Onna brand, but its capability language ('manage data, records, automate workflows') is generic and lacks concrete actions or synonym coverage. It is clearly distinct but only moderately specific.

Suggestions

Replace generic verbs with concrete actions, e.g. 'Search Onna sources, run saved searches, fetch source content, and proxy custom API requests.'

Broaden trigger terms with natural synonyms users say, such as 'search Onna', 'query Onna records', or 'eDiscovery across Onna data'.

Tighten the 'when' clause with specific trigger phrases (e.g. 'Use when the user wants to search, query, or pull records from Onna').

Dimension	Reasoning	Score
Specificity	Names the Onna domain and a few action areas ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor and falling below the 'several specific actions' level 4.	3 / 5
Completeness	It has both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Onna data'), but the 'when' could be more specific with concrete triggers, matching level 4 and below the explicit-trigger-phrase level 5.	4 / 5
Trigger Term Quality	The 'Onna' / 'Onna data' keywords are relevant natural terms a user would say, but common variations and synonyms (search, query, eDiscovery, records) are missing, fitting the 'some relevant keywords but missing common variations' anchor rather than the comprehensive level 5.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to the named 'Onna' product creates a clear niche with a highly distinctive trigger and minimal overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	15 / 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/onna/SKILL.md
Commit: f484c82

Reviewed: 5 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.