imsg
iMessage/SMS CLI for listing chats, reading message history, watching for new messages, and sending messages. Triggers on: check messages, read imessage, send text, imsg, message history, sms, who texted me.
92
89%
Does it follow best practices?
Impact
100%
2.63xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong skill description that clearly communicates what the skill does (iMessage/SMS CLI operations) and when to use it (with an explicit list of trigger terms). The trigger terms are natural, varied, and cover common user phrasings including abbreviations like 'imsg'. The description is concise, specific, and distinctly scoped to messaging.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'listing chats, reading message history, watching for new messages, and sending messages.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (iMessage/SMS CLI for listing chats, reading history, watching, sending) and 'when' (explicit 'Triggers on:' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'check messages', 'read imessage', 'send text', 'imsg', 'message history', 'sms', 'who texted me' — these cover common phrasings and abbreviations. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — iMessage/SMS messaging is a specific domain unlikely to conflict with other skills. The trigger terms like 'imessage', 'sms', 'who texted me' are highly distinctive. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%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, concise skill that provides fully actionable CLI commands with good coverage of edge cases (permissions, delivery semantics). Its main weakness is the lack of an explicit send workflow with validation checkpoints — given that sending messages is an irreversible action, a sequenced workflow (list chats → verify recipient → confirm → send) would strengthen safety. The progressive disclosure is reasonable for the skill's scope but could benefit from slightly better organization.
Suggestions
Add an explicit numbered workflow for sending messages: 1. Look up recipient in USER.md, 2. Verify chat-id with `imsg chats`, 3. Confirm recipient/text, 4. Send — this would improve workflow clarity for a destructive operation.
Consider adding a brief error-handling section or feedback loop: what to do if `permissionDenied` is returned, or how to verify delivery after sending.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what iMessage is or how CLIs work. The delivery notes section adds genuinely non-obvious information (optimistic sending, permission nuances). Every token earns its place. | 3 / 3 |
Actionability | All commands are fully executable with concrete flags and examples. Multiple send variants (email, phone, attachment) are shown with copy-paste ready commands. The setup section clearly states prerequisites and permissions needed. | 3 / 3 |
Workflow Clarity | The Safety section mentions 'Read-only by default — use chats and history before sending' and 'Always confirm recipient and message text before imsg send', but there's no explicit sequenced workflow with validation checkpoints. For a send operation that is destructive (messages can't be unsent), a clearer step-by-step workflow with verification (e.g., confirm chat-id via history before sending) would be warranted. | 2 / 3 |
Progressive Disclosure | References to USER.md for configuration details are well-signaled and appropriate. However, there are no bundle files, and the content is somewhat monolithic — the delivery notes, safety, and setup sections could potentially be better organized or split. For a skill of this size (~60 lines of content), the structure is adequate but the repeated references to USER.md without a clear navigation section slightly reduce clarity. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- joelhooks/joelclaw
- Commit
03f0a59
- 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.