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

77%

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

This is a well-structured, highly actionable skill that provides concrete API endpoints, clear workflows with decision points, and practical troubleshooting guidance. Its main weaknesses are moderate redundancy (inbox placement described three times) and some unnecessary explanatory text that Claude doesn't need. The referenced bundle files (dmarc.md, google-postmaster.md) are not provided, making progressive disclosure harder to fully evaluate.

Suggestions

Remove duplicate descriptions of inbox placement testing — define it once in Common Workflows and reference it from Agent Instructions and Key Concepts rather than repeating the full flow.

Cut the Overview paragraph and credential handling advice ('never hardcode API keys') — Claude already knows these concepts and they consume tokens without adding value.

DimensionReasoningScore

Conciseness

Generally efficient but has some redundancy — the inbox placement workflow is described in both Agent Instructions (#4), Key Concepts, and Common Workflows. Some explanatory text like 'Mailgun Optimize (by Sinch), formerly InboxReady, is a deliverability suite' is unnecessary context for Claude. The credential handling section tells Claude to 'never hardcode API keys' which it already knows.

2 / 3

Actionability

Provides concrete API endpoints with HTTP methods, specific curl examples, exact query parameter syntax (e.g., `?domain=example.com`), and clear endpoint paths for every operation. The deliverability audit workflow gives specific thresholds (spam rate > 0.3%) and actionable remediation steps for each finding.

3 / 3

Workflow Clarity

Multi-step workflows are clearly sequenced with numbered steps. The Deliverability Audit workflow includes decision points and remediation guidance at each step (e.g., 'If blocklisted → prioritize delisting'). The inbox placement test includes the polling pattern. The New Domain Onboarding workflow provides a complete sequential setup process with verification steps.

3 / 3

Progressive Disclosure

References to external files like `references/dmarc.md`, `references/google-postmaster.md`, and `../sinch-authentication/SKILL.md` are present but no bundle files were provided, so these references are unverifiable. The skill itself is fairly long with inline Key Concepts that could potentially be split out, though the content is reasonably organized with clear section headers.

2 / 3

Total

10

/

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 thoroughly covers specific capabilities, includes a comprehensive set of natural trigger terms spanning both proactive and reactive use cases, and clearly delineates both what the skill does and when to use it. The description is well-structured with the 'Use when' clause covering both feature-based triggers and problem-based triggers, making it highly effective for skill selection.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: test inbox placement with seed lists, monitor IP/domain blocklists, track spam traps, check email health scores, review DMARC reports, pull Google Postmaster/Microsoft SNDS data, domain warmup monitoring, IP blocklist removal.

3 / 3

Completeness

Clearly answers both 'what' (monitors email deliverability via Mailgun Optimize API with specific capabilities listed) and 'when' (explicit 'Use when' clause covering both proactive monitoring scenarios and reactive troubleshooting scenarios like emails going to spam or reputation dropping).

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'emails going to spam', 'sender reputation', 'inbox rate', 'blocklist', 'DMARC', 'spam traps', 'domain warmup', 'Google Postmaster', 'Microsoft SNDS', 'email deliverability'. These are terms users would naturally use when facing deliverability issues.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: email deliverability monitoring via a specific API (Mailgun Optimize/InboxReady). The domain-specific triggers like 'seed lists', 'DMARC reports', 'spam traps', 'blocklist removal', and 'SNDS data' are unlikely to conflict with other 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