iMessage/SMS CLI for listing chats, history, and sending messages via Messages.app.
86
83%
Does it follow best practices?
Impact
96%
1.81xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is concise and specific about its capabilities, clearly identifying the domain (iMessage/SMS) and concrete actions (listing chats, viewing history, sending messages). Its main weaknesses are the lack of an explicit 'Use when...' clause and missing common user trigger terms like 'text message' or 'texting'. Adding these would make it significantly more effective for skill selection.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user wants to send or read text messages, check iMessage conversations, or interact with Messages.app.'
Include additional natural trigger terms users would say, such as 'text message', 'texting', 'send a text', 'conversation history', 'read messages'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'listing chats', 'history', and 'sending messages'. Also specifies the tool ('Messages.app') and interface type ('CLI'). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (listing chats, history, sending messages via CLI), but lacks an explicit 'Use when...' clause or trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'iMessage', 'SMS', 'chats', 'messages', and 'Messages.app', but misses common user variations like 'text message', 'texting', 'send a text', or 'conversation history'. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — iMessage/SMS via Messages.app CLI is highly specific and unlikely to conflict with other skills. The combination of messaging platform and CLI interface creates a clear identity. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%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 that efficiently teaches Claude how to use the imsg CLI. It excels at disambiguation (when to use vs. not), provides fully executable commands, and includes a safety-conscious workflow with user confirmation before sending. The content is concise without sacrificing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what iMessage is or how Messages.app works. Every section earns its place — routing guidance, concrete commands, safety rules. The 'When NOT to Use' section is valuable disambiguation, not filler. | 3 / 3 |
Actionability | All commands are copy-paste ready with real flags and arguments. The example workflow shows a complete end-to-end process with concrete bash commands and jq filtering. Service options are specific and complete. | 3 / 3 |
Workflow Clarity | The example workflow clearly sequences find → confirm → send with an explicit user confirmation checkpoint before the destructive action (sending a message). Safety rules reinforce validation steps. This is appropriate for a messaging skill. | 3 / 3 |
Progressive Disclosure | For a CLI tool skill with no bundle files, the content is well-organized into logical sections (when to use, commands, safety, workflow) without being monolithic. The skill is appropriately self-contained at under 80 lines with no need for external references. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 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 |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
a5bf5e0
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.