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".

1.96x

Quality

—

Does it follow best practices?

Impact

100%

1.96x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

87%

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

A tight, action-oriented reference with copy-paste JSON examples and no wasted tokens, well-organized for a self-contained single-purpose skill. Its main weakness is the absence of explicit confirmation/validation checkpoints for destructive actions such as unsend and edit.

Suggestions

Add an explicit confirmation step before destructive actions (unsend, edit), e.g. 'Confirm the messageId with the user before calling unsend, since it is irreversible.'

Clarify how to obtain a valid messageId/chat_guid (e.g., from a prior send response or incoming webhook), since several actions depend on it but the source is only implied.

Note which actions are macOS-version dependent inline with the relevant example rather than only in the Notes section, so the constraint is visible at the point of use.

Dimension	Reasoning	Score
Conciseness	The body is lean: a short overview, an inputs list, compact per-action JSON blocks, and brief notes with no padding or explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	Each action ships a concrete, copy-paste-ready JSON example with real field values (send, react, edit, unsend, reply, sendAttachment, sendWithEffect), matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The disambiguation guardrail ('If the user is vague... ask for...') adds some sequence, but destructive actions like unsend and edit lack any explicit confirmation or validation checkpoint, capping the score at 2 per the rubric's destructive-operation guidance.	2 / 3
Progressive Disclosure	No bundle files exist, and the body is self-contained and well-organized into clear sections with a single clearly signaled one-level reference (extensions/bluebubbles/README.md), avoiding nested references.	3 / 3
	Total	11 / 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.

A concise, well-constructed description that clearly states capabilities, includes natural trigger terms, and provides an explicit 'Use when...' clause covering both what and when. It occupies a distinct niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('send or manage iMessages via BlueBubbles') and ties them to a specific integration, matching the 'lists multiple specific concrete actions' anchor rather than the vaguer level 2.	3 / 3
Completeness	Explicitly states both what it does ('send or manage iMessages via BlueBubbles') and when to use it via an explicit 'Use when...' clause, satisfying the level 3 anchor for answering what AND when.	3 / 3
Trigger Term Quality	Includes natural user terms like 'iMessages', 'send or manage iMessages', and 'BlueBubbles' that a user would plausibly say, giving good coverage rather than just some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	It targets a distinct niche (BlueBubbles iMessage integration through a specific channel) with triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: c4d1b89

Reviewed: 3 days 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.