Name: datumbox
Rating: 59.2 (1 reviews)
Author: membranedev

datumbox

Datumbox integration. Manage Organizations, Users, Goals, Filters. Use when the user wants to interact with Datumbox data.

Quality

68%

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/datumbox/SKILL.md

Quality

Content

75%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, copy-paste CLI commands and a well-sequenced connection workflow with genuine state feedback loops. Its main weaknesses are verbose inline reference enumerations and a couple of dangling internal step labels ('Step 2', '1b').

Suggestions

Move the 16-model Train/Predict enumeration and the Popular actions table into a separate references file, keeping only a concise summary inline in SKILL.md.

Fix the dangling 'Step 2' reference and relabel '1b' with a matching '1a' so the connection sequence is internally consistent.

Remove filler lines like 'Use action names and parameters as needed.' that assume no new information.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient structured reference, but the ~50-line Train/Predict enumeration for 16 models and the 14-row Popular actions table are repetitive inline content that could be tightened, and "Use action names and parameters as needed." is filler.	3 / 5
Actionability	It provides copy-paste ready, fully specified commands with flags throughout (npm install, membrane login, connection ensure, action list/run, request), covering the common install-auth-connect-search-run cases with concrete placeholders.	5 / 5
Workflow Clarity	The connection workflow has a clear sequence with explicit state feedback loops (poll until READY, handle CLIENT_ACTION_REQUIRED then re-poll, check error states), but the referenced 'Step 2' and '1b' labels are not cleanly defined, leaving minor navigation gaps.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers and no nested external references, but no bundle files exist and large inline enumerations (model list, actions table) that could live in a separate reference file are kept in SKILL.md, a minor organization gap for a 200+ line skill.	4 / 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 includes a 'Use when' trigger and brand-specific distinctiveness, but its actions are generic ('Manage') and it omits the natural ML task phrases users would say. It also lists entities (Organizations, Users, Goals, Filters) that do not reflect Datumbox's actual ML capabilities.

Suggestions

Replace the generic 'Manage Organizations, Users, Goals, Filters' with concrete Datumbox ML actions such as 'Run sentiment analysis, text classification, language detection, and keyword extraction'.

Expand the trigger clause to name natural user phrases, e.g. 'Use when the user wants sentiment analysis, text classification, topic modeling, or other Datumbox ML predictions'.

Align the description with the body so the stated capabilities match the actual Datumbox ML model suite.

Dimension	Reasoning	Score
Specificity	It names the domain (Datumbox) and enumerates entity targets ("Manage Organizations, Users, Goals, Filters"), but the only action verb is the generic "Manage" with no concrete create/list/delete operations, so it lands between generic and comprehensive.	3 / 5
Completeness	It states both a what ("Manage Organizations, Users, Goals, Filters") and a when ("Use when the user wants to interact with Datumbox data"), but the when clause is generic rather than tied to concrete trigger phrases, so it falls just below a 5.	4 / 5
Trigger Term Quality	"Datumbox" and "Datumbox data" are relevant brand keywords, but the natural phrases a user would actually say (e.g. sentiment analysis, text classification, language detection) are absent, missing common variations.	3 / 5
Distinctiveness Conflict Risk	The repeated "Datumbox" brand anchors a clear niche with minimal conflict risk, though the generic "Manage Organizations, Users, Goals, Filters" CRUD framing creates minor overlap with other management skills.	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/datumbox/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.