Name: datagma
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

datagma

Datagma integration. Manage Organizations. Use when the user wants to interact with Datagma data.

Quality

60%

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/datagma/SKILL.md

Quality

Content

71%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-ready Membrane commands and a clear connection workflow including validation checkpoints, though step numbering is slightly inconsistent. It is somewhat verbose in its intro/marketing prose and does not use progressive disclosure: all reference material lives inline in a single file.

Suggestions

Move the popular-actions catalog and proxy-options table into a references/ file (e.g. ACTIONS.md) and link to it from SKILL.md to apply progressive disclosure.

Trim marketing prose such as "helps sales and marketing teams identify and qualify leads", "so you can focus on the integration logic rather than auth plumbing", and "This is the fastest way to get a connection".

Fix the step numbering in the connection section so "skip to Step 2" and "1b" map to explicit "Step 1"/"Step 2" headers.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but retains marketing/explanatory prose ("helps sales and marketing teams identify and qualify leads", "so you can focus on the integration logic rather than auth plumbing", "This is the fastest way to get a connection") that could be trimmed.	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands for install, login, connection ensure, action list/run, and request proxying, plus a concrete popular-actions table and a proxy-options table covering the common cases.	5 / 5
Workflow Clarity	The connection workflow has explicit state-validation checkpoints and a feedback loop (poll until READY, handle CLIENT_ACTION_REQUIRED, re-poll), but step numbering is inconsistent ("skip to Step 2" and "1b" with no matching "Step 2"/"1a" headers).	4 / 5
Progressive Disclosure	The skill is well-sectioned but has no bundle files and no one-level-deep references; reference-like content (the 11-row popular-actions catalog and the proxy-flags table) is inlined in SKILL.md rather than split into a separate file.	3 / 5
	Total	15 / 20 Passed

Description

50%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 third-person and includes an explicit use-when trigger, but it is thin and partly inaccurate: "Manage Organizations" undersells the actual person/company enrichment and email/phone lookup capabilities and omits the natural keywords users would invoke. It is distinct thanks to the brand name yet weak on specificity and trigger terms.

Suggestions

Replace "Manage Organizations" with the actual concrete actions, e.g. "Enrich companies and contacts, find verified work emails, reverse email/phone lookup, and detect job changes from Datagma data."

Add natural trigger keywords users would say, such as "lead enrichment", "email lookup", "phone lookup", or "find a person's email".

Tighten the "when" clause to reference concrete scenarios (e.g. qualifying leads, enriching a contact, finding a verified work email) rather than the generic "interact with Datagma data".

Dimension	Reasoning	Score
Specificity	The description names the Datagma domain but its only action, "Manage Organizations", is generic and does not match the skill's actual enrichment capabilities (person/company lookups, email/phone finding).	2 / 5
Completeness	Both a "what" ("Datagma integration. Manage Organizations.") and an explicit "Use when the user wants to interact with Datagma data" clause are present, though the "what" is thin and could be more specific.	4 / 5
Trigger Term Quality	It relies on the brand name plus "Organizations" and "Datagma data"; the natural phrases users would say (enrich, lead lookup, find email/phone) are missing.	2 / 5
Distinctiveness Conflict Risk	The specific brand name "Datagma" carves a clear niche with distinct triggers, leaving only minor overlap risk with adjacent data/CRM skills.	4 / 5
	Total	12 / 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/datagma/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.