Name: textanywhere
Rating: 58.4 (1 reviews)
Author: membranedev

textanywhere

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

Quality

67%

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/textanywhere/SKILL.md

Quality

Content

72%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 copy-paste Membrane CLI commands and a solid connection-state feedback loop, but its workflow step numbering is broken, batch action runs lack validation checkpoints, and all detail is inlined with no progressive disclosure to reference files.

Suggestions

Fix the broken step numbering: label 'Step 1' (connect) and 'Step 2' (search/run actions) explicitly so the 'skip to Step 2' references resolve.

Add a validation checkpoint before batch/destructive action runs, e.g. dry-run or confirm recipient count before sending SMS/MMS campaigns.

Move the proxy-flags table and the connection state-machine detail into reference files (e.g. references/proxy.md, references/connection-states.md) and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, executable commands with little concept-padding (the brief product overview is acceptable for an obscure tool), but has minor redundancy such as the action-list command repeated at lines 101 and 110 and 'Discover before you build' restating earlier guidance.	4 / 5
Actionability	Copy-paste-ready commands cover the common cases end to end — install, login (including headless completion), connection ensure, state polling, action list/run with --input JSON, and a full proxy-flags table.	5 / 5
Workflow Clarity	The connection-state machine provides a real feedback loop, but step references are broken ('skip to Step 2' with no labeled Step 1/Step 2), and running actions or sending SMS campaigns is a batch operation with no validation checkpoint, which caps the score per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist and there are zero external references; ~140 lines are inlined including the proxy-flags table and full state-machine detail that could live in separate reference files, though section headers provide reasonable structure.	3 / 5
	Total	15 / 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 correctly pairs a what and a when around a specific product, but its action verbs are generic and its trigger terms miss the natural messaging/campaign vocabulary users would actually say.

Suggestions

Replace generic verbs with concrete TextAnywhere actions, e.g. 'Send SMS/MMS campaigns, manage contacts and templates, and review delivery analytics'.

Expand the trigger clause to include natural terms users say: 'Use when the user wants to send SMS/MMS or email campaigns, manage contacts or templates, or work with TextAnywhere messaging data'.

Mention conversation/message entities in the description so the skill is distinguishable from generic CRM or data-management skills.

Dimension	Reasoning	Score
Specificity	Names the TextAnywhere domain with several action verbs ('Manage data, records, and automate workflows'), but the verbs are generic rather than concrete, so it sits above the minimal-action anchor yet below comprehensive specific actions.	3 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with TextAnywhere data') are present, with the when being product-scoped, though the what is somewhat generic.	4 / 5
Trigger Term Quality	The trigger 'Use when the user wants to interact with TextAnywhere data' includes the product keyword but misses natural variations users would actually say (SMS, MMS, campaigns, messaging, contacts, templates).	3 / 5
Distinctiveness Conflict Risk	Naming a specific product (TextAnywhere) gives a clear niche with low conflict risk, but the generic action language leaves minor overlap risk with other integration 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/textanywhere/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.