CtrlK
BlogDocsLog inGet started
Tessl Logo

sinch-partnerships-ecosystems/sinch-skills

Official Sinch API skills for AI coding agents — SMS, Voice, Verification, Numbers, Mailgun email, and more.

71

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

This plugin was archived by the owner on Jun 4, 2026

Reason: we moved this to another workspace

Overview
Quality
Evals
Security
Files

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a solid foundation for 10DLC registration with good credential handling, a complete brand registration example, and useful troubleshooting tips. However, it defers too much core workflow content to a references/workflow.md file that isn't provided in the bundle, leaving the main skill without executable examples for most of the multi-step process. The Key Concepts section is verbose for Claude's knowledge level, and the Common Patterns section is mostly external links rather than actionable inline guidance.

Suggestions

Include the key workflow steps (qualify, create campaign, poll status) with inline curl examples rather than deferring entirely to references/workflow.md, or ensure that file is provided in the bundle.

Trim the Key Concepts section significantly — Claude doesn't need definitions of Brand, Campaign, CSP, or TCR. Keep only non-obvious details like the trust score caveat and use case categories.

Add explicit validation checkpoints in the workflow (e.g., 'Verify brand status is APPROVED before proceeding to campaign creation') with the specific API call to check status.

Convert the Common Patterns link list into brief actionable snippets (method + path + key parameter) so Claude can act without following external links.

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary explanations (e.g., explaining what 10DLC is, what a brand/campaign/TCR/CSP is — Claude knows these). The Key Concepts section could be trimmed significantly. The overview paragraph restates what the description already covers. However, the code examples and workflow references are lean.

2 / 3

Actionability

The first API call (brand registration) is fully executable with a complete curl example, which is good. However, the workflow section says 'see references/workflow.md' for the actual step-by-step curl examples, response schemas, and polling strategies — meaning the core actionable content is deferred. The Common Patterns section is mostly links rather than executable guidance. Campaign registration, qualification, and status checking lack inline examples.

2 / 3

Workflow Clarity

The skill references a clear multi-step workflow ('Follow these steps in order. Each step depends on the previous one succeeding') but defers the actual steps to references/workflow.md, which is not provided in the bundle. The troubleshooting section mentions checking feedback and re-registering but lacks explicit validation checkpoints and feedback loops inline. Polling guidance ('poll hourly') is mentioned but not structured as a validation step within the workflow.

2 / 3

Progressive Disclosure

The skill references references/workflow.md for detailed workflow steps and links to external API docs, which is good structure in principle. However, the bundle has no files provided, so we cannot verify that references/workflow.md exists or is well-structured. The Common Patterns section is essentially a link dump to external documentation rather than providing concise inline summaries with targeted references. The main SKILL.md itself is somewhat long with the Key Concepts section that could be trimmed or moved.

2 / 3

Total

8

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that hits all the marks. It provides specific concrete actions, includes abundant natural trigger terms, explicitly states both what it does and when to use it (including negative boundaries), and occupies a clearly distinct niche that would be very unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: register a brand, create a 10DLC campaign, check registration status, troubleshoot a rejection, fix an EIN mismatch, upgrade from simplified to full registration, and qualify a campaign. These are highly specific and actionable.

3 / 3

Completeness

Clearly answers both 'what' (registers brands and campaigns with Sinch for A2P SMS) and 'when' (explicit 'Use when...' clause listing seven specific trigger scenarios). Also includes a 'Do NOT use' exclusion clause, which further clarifies boundaries.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: '10DLC', 'brand', 'campaign', 'A2P SMS', 'EIN mismatch', 'rejection', 'registration status', 'Sinch', '10-digit long codes', 'US SMS'. These are the exact terms a user working in this domain would naturally use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a very clear niche: US 10DLC registration via Sinch. The explicit exclusion of non-US messaging and toll-free/short code registration further reduces conflict risk with adjacent SMS-related skills.

3 / 3

Total

12

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents