Name: sendsms
Rating: 64 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

sendsms

SendSMS integration. Manage SMSes, Contacts, Groups. Use when the user wants to interact with SendSMS data.

Quality

76%

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/sendsms/SKILL.md

Quality

Content

82%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 a well-structured, highly actionable integration guide with copy-paste commands and a clear connection-state workflow including polling feedback loops. Its main weaknesses are minor over-explanation in the intro and an ambiguous 'Step 2' reference in the workflow.

Suggestions

Resolve the 'skip to Step 2' reference by labeling the searching/running-actions section as 'Step 2' or removing the cross-reference.

Trim the introductory paragraph about what SendSMS is used for, since the description already conveys purpose.

Add a brief validation note for action-run results (e.g. check the 'output' field for errors) to complete the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-driven with minor over-explanation such as the introductory paragraph on what SendSMS is used for and a thin 'SendSMS Overview' tree. Not a 5 because those padded passages could be trimmed; not a 3 because the bulk is efficient executable guidance.	4 / 5
Actionability	It provides copy-paste-ready commands for every common case (install, login, connection ensure, action list/run, request proxy) with a full flags table, all concrete and executable. Not a 4 because examples are complete and cover the common cases rather than having notable gaps.	5 / 5
Workflow Clarity	A clear sequence (install → auth → connect → poll until ready → search → run/proxy) with a genuine feedback loop via the connection-state machine and polling. Not a 5 because the 'skip to Step 2' reference points to an unlabeled step and action-run results are not validated; not a 3 because checkpoints and error-recovery polling are present.	4 / 5
Progressive Disclosure	No bundle files exist, so the single SKILL.md is scored on its own structure: clear section headers and easy navigation with all content appropriately inline for a CLI integration skill. Not a 5 because denser material (the proxy flags table and detailed clientAction sub-fields) could arguably live in a reference file; not a 3 because organization is solid.	4 / 5
	Total	17 / 20 Passed

Description

70%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 answers both 'what' and 'when' with a clear, concise named-app niche and good natural keyword coverage. Its main weakness is reliance on the generic verb 'Manage' and a somewhat vague 'when' trigger rather than concrete action/trigger phrases.

Suggestions

Replace the generic 'Manage' with specific verbs, e.g. 'Send SMSes, manage Contacts and Groups'.

Tighten the 'when' clause with concrete triggers: 'Use when the user wants to send SMS messages or manage SendSMS contacts and groups.'

Add common user phrasings or synonyms (e.g. 'text messages', 'contact lists') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('SendSMS integration') and three concrete objects ('SMSes, Contacts, Groups'), but relies on a single generic verb ('Manage') rather than listing several distinct actions, matching the 'names domain and 1-2 concrete actions' anchor. Not a 4 because no specific actions like 'send', 'create', or 'list' are enumerated.	3 / 5
Completeness	Both 'what' ('Manage SMSes, Contacts, Groups') and 'when' ('Use when the user wants to interact with SendSMS data') are present, but the 'when' clause is generic rather than a concrete trigger phrase. Not a 5 because the trigger lacks concrete phrases; not a 3 because both halves are explicitly stated.	4 / 5
Trigger Term Quality	Natural entity keywords users would say ('SMSes', 'Contacts', 'Groups', 'SendSMS') plus an explicit 'Use when' trigger give good coverage, though a few common phrasings like 'send an SMS' are absent. Not a 5 because synonyms and variations are incomplete; not a 3 because more than generic keywords are present.	4 / 5
Distinctiveness Conflict Risk	The named app 'SendSMS' carves a clear niche with minimal conflict risk, but the generic 'interact with SendSMS data' trigger leaves minor overlap risk with generic messaging or CRM skills. Not a 5 because the trigger phrasing is not tightly distinct; not a 3 because the app name clearly scopes it.	4 / 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/sendsms/SKILL.md
Commit: f484c82

Reviewed: ~22 hours 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.