Name: ez-texting
Rating: 52.8 (1 reviews)
Author: membranedev

ez-texting

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

Quality

59%

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/ez-texting/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 action-oriented with solid copy-paste CLI commands and a well-structured connection workflow, but it pads explanations Claude doesn't need and—critically—offers no validation checkpoints before destructive action runs or proxy requests, capping workflow clarity. Tightening prose and adding pre-execution verification would notably improve it.

Suggestions

Add an explicit validation/verification checkpoint before destructive or batch operations: e.g. before `membrane action run` or `membrane request` with POST/PUT/PATCH/DELETE, confirm the target and parameters, then verify the result in the `output` field before proceeding.

Trim unnecessary context Claude already knows—remove the opening paragraph describing what EZ Texting is and lines like 'Use action names and parameters as needed' and 'so you can focus on the integration logic rather than auth plumbing'.

Fix the step numbering inconsistency (the 'skip to Step 2' reference with no labeled Step 1 / '1b' heading) so the connection workflow sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but includes unnecessary explanation Claude doesn't need (the opening paragraph on what EZ Texting is, 'so you can focus on the integration logic rather than auth plumbing', and filler like 'Use action names and parameters as needed'), matching score 3; not a 4 because several sections could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste-ready commands for install, auth, connecting, searching, running actions, and proxying with a flags table, covering common cases with minor gaps (e.g. capturing CONNECTION_ID into a variable); not a 5 because some end-to-end composition details are left implicit.	4 / 5
Workflow Clarity	The connection flow has a clear sequence with a polling feedback loop (BUILDING -> poll -> READY/CLIENT_ACTION_REQUIRED), but `membrane action run` and `membrane request` support destructive/batch operations (POST/PUT/PATCH/DELETE on EZ Texting data) with no validation or verification checkpoint before executing, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained with well-organized sections (Overview, Install, Authentication, Connecting, Searching, Running actions, Proxy, Best practices); structure is good with minor organization gaps (the detailed clientAction handling and proxy flags table are somewhat dense inline); not a 5 because a couple of sections could be tightened or split.	4 / 5
	Total	14 / 20 Passed

Description

57%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 correctly uses third-person voice and includes an explicit 'Use when' trigger with a clear domain niche, but its action language is generic and it misses natural SMS/texting synonyms that users would actually say. It is functional but could be sharper and more concrete.

Suggestions

Replace generic actions with concrete ones, e.g. 'Send SMS campaigns, manage contacts and contact lists, handle keywords and phone numbers' instead of 'Manage data, records, and automate workflows'.

Add natural trigger terms users would say: 'Use when the user wants to send SMS/text messages, manage contacts, or run text-marketing campaigns via EZ Texting'.

Keep the explicit 'Use when' clause but tie it to specific EZ Texting use cases (SMS marketing, alerts, reminders) to reduce overlap with generic data-management skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('EZ Texting integration') but the actions 'Manage data, records, and automate workflows' are minimal and generic rather than concrete, matching the score-2 anchor of naming the domain with minimal/generic actions; not a 3 because no concrete actions (e.g., send SMS, manage contact lists) are enumerated.	2 / 5
Completeness	Both 'what' (manage data, records, automate workflows) and 'when' ('Use when the user wants to interact with EZ Texting data') are present, but the trigger could be more explicit/specific, matching score 4; not a 5 because the trigger phrases are not concrete (no SMS/texting scenarios).	4 / 5
Trigger Term Quality	It includes 'EZ Texting' and 'interact with EZ Texting data' but omits natural synonyms a user would say ('SMS', 'text messages', 'texts', 'campaigns'), so it has some relevant keywords missing common variations; not a 4 because keyword coverage is thin rather than merely missing a few.	3 / 5
Distinctiveness Conflict Risk	'EZ Texting' is a specific platform niche with a distinct trigger, giving mostly distinct coverage with minor overlap risk from the generic 'manage data, records' phrasing; not a 5 because the generic action language weakens the distinct trigger.	4 / 5
	Total	13 / 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/ez-texting/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.