bluebubbles
Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".
88
83%
Does it follow best practices?
Impact
100%
1.96xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 a reasonably strong description with clear 'when' guidance and distinctive trigger terms that make it easy to select from a pool of skills. Its main weakness is the lack of specific concrete actions beyond 'send or manage' — listing capabilities like reading conversations, sending attachments, or searching message history would improve specificity. The description also uses second person ('you need to') which is noted but not penalized under the specificity dimension since the rubric penalizes first/second person there.
Suggestions
Expand the 'what' portion with more specific actions, e.g., 'Sends, receives, reads, and searches iMessages via BlueBubbles' to improve specificity.
Rephrase to third person voice: 'Sends and manages iMessages via BlueBubbles' instead of 'Use when you need to send or manage'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (iMessages via BlueBubbles) and mentions two actions ('send or manage'), but doesn't list specific concrete actions like reading conversations, sending attachments, searching messages, etc. | 2 / 3 |
Completeness | Explicitly answers both 'what' (send or manage iMessages via BlueBubbles using the generic message tool with channel='bluebubbles') and 'when' ('Use when you need to send or manage iMessages via BlueBubbles'). The 'Use when' clause is present and clear. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'iMessages', 'BlueBubbles', 'send', 'manage', 'message tool', and 'channel="bluebubbles"'. Users asking about iMessage or BlueBubbles would naturally use these terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific triggers: 'BlueBubbles', 'iMessages', and the technical detail 'channel="bluebubbles"' make it very unlikely to conflict with other messaging or communication skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
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 solid, actionable skill with clear JSON examples for every supported action. Its main weakness is moderate verbosity—the 'Ideas to try' section and some introductory text add little value for Claude. The progressive disclosure could be improved by splitting advanced/rare actions into a referenced file, but the current inline structure is acceptable for the number of actions covered.
Suggestions
Remove the 'Ideas to try' section—Claude can infer appropriate usage from the action examples.
Consider trimming the overview paragraph since the actions section already demonstrates all capabilities with concrete examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with concrete JSON examples, but includes some unnecessary sections like 'Ideas to try' and 'Inputs to collect' explanations that Claude could infer. The overview paragraph also restates what the actions section already demonstrates. | 2 / 3 |
Actionability | Every action is illustrated with a complete, copy-paste-ready JSON payload showing exact field names and values. The inputs section specifies formats (E.164, chat_guid prefix), and the skill clearly instructs Claude to ask for missing information. | 3 / 3 |
Workflow Clarity | This is essentially a single-action-per-invocation skill (each action is independent), and each action is unambiguous with clear JSON structure. The guidance on when to ask for clarification ('If the user is vague...') serves as a lightweight validation checkpoint appropriate for this type of skill. | 3 / 3 |
Progressive Disclosure | The skill references `extensions/bluebubbles/README.md` for developer details, which is good, but no bundle files are provided to verify this. The content is somewhat long with all actions inline; grouping less common actions (edit, unsend, effects) into a separate reference file could improve organization. | 2 / 3 |
Total | 10 / 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 | |
- Repository
- qsimeon/openclaw-engaging
- Commit
4467e04
- Reviewed
Table of Contents
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.