imsg-rpc
Set up, maintain, and debug the imsg-rpc Unix socket daemon that gives the gateway iMessage access via JSON-RPC. Covers FDA setup, code signing, launchd service, and the imsg source repo.
91
87%
Does it follow best practices?
Impact
100%
5.55xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
82%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, specific description that clearly identifies a narrow technical domain (imsg-rpc daemon for iMessage access) with concrete actions and relevant subtopics. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical trigger terms are excellent and highly distinctive.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about imsg-rpc, iMessage daemon setup, launchd configuration for iMessage, or troubleshooting the Unix socket connection.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Set up, maintain, and debug' the daemon, and covers specific subtopics: 'FDA setup, code signing, launchd service, and the imsg source repo.' | 3 / 3 |
Completeness | Clearly answers 'what does this do' (set up, maintain, debug the imsg-rpc daemon with specific subtopics), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'imsg-rpc', 'Unix socket', 'daemon', 'iMessage', 'JSON-RPC', 'FDA', 'code signing', 'launchd', 'imsg'. These are highly specific technical terms a user working with this system would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very clear niche: 'imsg-rpc Unix socket daemon' for iMessage access is extremely specific and unlikely to conflict with any other skill. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, operationally focused skill that provides excellent actionable guidance for managing the imsg-rpc daemon. It excels at conciseness (no wasted explanation of concepts Claude knows), actionability (every command is copy-paste ready), and workflow clarity (clear sequences with verification steps). The only minor weakness is that the content is moderately long and could benefit from splitting some detailed sections (like FDA cert creation or protocol reference) into separate referenced files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. No unnecessary explanations of what launchd, FDA, or Unix sockets are. Every section delivers specific paths, commands, or architecture details that Claude wouldn't already know. The architecture diagram is minimal yet informative. | 3 / 3 |
Actionability | Every section provides fully executable, copy-paste-ready commands. The FDA setup has complete openssl and security commands, the status check has specific bash pipelines, troubleshooting includes exact sqlite3 queries and log commands. Nothing is left as pseudocode or vague direction. | 3 / 3 |
Workflow Clarity | The FDA setup is clearly sequenced (1-4) with verification at each stage. Troubleshooting provides clear diagnostic → fix → verify flows. The rebuild workflow explicitly warns against using the wrong command ('NOT make build'). Status check defines what 'healthy state' looks like. Validation checkpoints are present throughout (e.g., 'should show watch.subscribe OK'). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a summary files table, but it's a fairly long single file (~170 lines of substantive content). The JSON-RPC protocol reference and the full FDA cert creation could potentially be split into referenced files. However, the ADR reference and gateway channel file are clearly signaled. | 2 / 3 |
Total | 11 / 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
825972c
- 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.