imsg
iMessage/SMS CLI for listing chats, history, and sending messages via Messages.app.
86
Quality
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.
This description effectively communicates specific capabilities (listing chats, viewing history, sending messages) and clearly identifies the platform (iMessage/SMS via Messages.app). However, it lacks explicit trigger guidance ('Use when...') and could benefit from additional natural language terms users might say when needing this functionality.
Suggestions
Add a 'Use when...' clause with trigger scenarios like 'Use when the user wants to send texts, read message history, or interact with their iMessage/SMS conversations'
Include additional natural trigger terms users might say: 'text', 'texting', 'send a text', 'conversations', 'message someone'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'listing chats', 'history', and 'sending messages'. Also specifies the platform (Messages.app) and interface type (CLI). | 3 / 3 |
Completeness | Clearly answers 'what' (CLI for listing chats, history, sending messages) 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', but missing common variations users might say like 'text', 'texting', 'send a text', 'message history', or 'conversations'. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche - specifically targets iMessage/SMS via Messages.app CLI. Unlikely to conflict with other skills due to the specific platform and application mentioned. | 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 providing concrete, executable commands while maintaining clear safety boundaries with explicit confirmation requirements. The 'When NOT to Use' section is particularly valuable for routing to appropriate tools.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient. No unnecessary explanations of what iMessage is or how messaging works. Every section serves a clear purpose with minimal padding. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready commands with real examples including flags, JSON output, and jq filtering. Service options and send commands are concrete and complete. | 3 / 3 |
Workflow Clarity | The example workflow shows a clear 3-step sequence (find → confirm → send) with an explicit confirmation checkpoint before sending. Safety rules reinforce validation requirements for destructive operations (sending messages). | 3 / 3 |
Progressive Disclosure | For a skill under 100 lines with no need for external references, the content is well-organized with clear sections (When to Use, Requirements, Commands, Safety, Workflow). No unnecessary nesting or monolithic walls of text. | 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 | |
- Repository
- trpc-group/trpc-agent-go
- Commit
50ef2f3
- 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.