Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".
86
Quality
81%
Does it follow best practices?
Impact
100%
1.96xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
75%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 description has good completeness with explicit 'Use when' guidance and clear distinctiveness through platform-specific terminology. However, it could benefit from more specific action verbs beyond 'send or manage' and additional natural trigger terms that users commonly use when referring to messaging.
Suggestions
Expand specific actions beyond 'send or manage' to include concrete capabilities like 'read conversations', 'search messages', 'send attachments', or 'check delivery status'
Add natural trigger term variations users might say such as 'text', 'texting', 'Apple messages', 'iMessage chat', or 'message someone'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (iMessages via BlueBubbles) and mentions two actions ('send or manage'), but lacks comprehensive specific actions like 'read messages', 'search conversations', 'send attachments', etc. | 2 / 3 |
Completeness | Explicitly answers both what ('send or manage iMessages via BlueBubbles') and when ('Use when you need to send or manage iMessages') with clear trigger guidance and implementation detail about the channel parameter. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'iMessages', 'BlueBubbles', and 'message tool', but misses common variations users might say like 'text', 'SMS', 'Apple messages', 'chat', or 'texting'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishes itself with specific platform references (BlueBubbles, iMessage) and technical implementation detail (channel='bluebubbles'), making it unlikely to conflict with other messaging skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%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-crafted skill with excellent actionability and conciseness. The JSON examples are complete and immediately usable, and the content respects Claude's intelligence by avoiding unnecessary explanations. The main weakness is the lack of validation/error handling guidance, particularly for operations that may fail or have platform-dependent behavior.
Suggestions
Add a brief error handling section explaining how to verify message delivery or handle failures, especially for edit/unsend operations that may be macOS-version dependent
Include guidance on what to do if an action fails (e.g., 'If edit fails, inform user and offer to send a new message instead')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary information. No unnecessary explanations of what iMessage or BlueBubbles is - it jumps straight to actionable content. | 3 / 3 |
Actionability | Every action has a complete, copy-paste ready JSON example with all required fields. The inputs section clearly specifies formats (E.164, chat_guid) and the examples cover all common use cases. | 3 / 3 |
Workflow Clarity | Individual actions are clear, but there's no validation or error handling guidance. For operations like edit/unsend that could fail (noted as potentially broken on macOS 26), there's no feedback loop or verification step. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Overview, Inputs, Actions, Notes, Ideas). References developer docs appropriately without deep nesting. Content is appropriately scoped for a skill file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
50ef2f3
Table of Contents
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.