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.

5.55x

Quality

87%

Does it follow best practices?

Impact

100%

5.55x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Quality

Content

92%Weight 40%Scale 1-3

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

A highly actionable, concise operations runbook with clear sequenced workflows and explicit validation/recovery loops; its only weakness is the monolithic single-file structure with no progressive disclosure into reference files.

Suggestions

Move the JSON-RPC Protocol Reference and/or the Files table into a references/ file (e.g. PROTOCOL.md) and link to it one level deep to improve progressive disclosure.

Consider extracting the FDA Setup new-machine procedure into a separate setup reference so the main SKILL.md stays a lean overview for status/restart/troubleshooting.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — commands, paths, and terse guidance with no concept tutorials (no 'what is launchd/FDA' preamble); every token earns its place, matching the lean anchor.	3 / 3
Actionability	Every section provides copy-paste-ready, fully executable bash with specific flags and paths (launchctl print, openssl req, security import, launchctl kickstart), matching the executable-code anchor.	3 / 3
Workflow Clarity	FDA Setup is a clear numbered 1-4 sequence with explicit verification ('security find-identity should show', 'verify: tail -f ... watch.subscribe OK') and the Troubleshooting section gives validate-check-fix recovery loops (TCC auth_value inspection, terminal test -> wrong path/signature diagnosis).	3 / 3
Progressive Disclosure	No bundle files exist and the ~200-line body is monolithic with inline content (JSON-RPC protocol reference, Files table) that could live in separate reference files; sections are well-organized but no one-level-deep references exist, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	11 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 specific, well-targeted description that names concrete actions and a distinct niche, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit 'Use when ...' clause naming trigger phrases (e.g., 'Use when setting up or debugging iMessage gateway access, launchd FDA/signing issues, or the com.joel.imsg-rpc service').

Include common user phrasings of the problem (e.g., 'iMessage not sending', 'socket ENOENT', 'FDA denied') so the trigger fires on natural-language requests.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("Set up, maintain, and debug") and multiple specific sub-areas ("FDA setup, code signing, launchd service, and the imsg source repo"), matching the multiple-specific-actions anchor rather than the domain-only level 2.	3 / 3
Completeness	It clearly states what the skill does but lacks any "Use when..." or equivalent explicit trigger clause; per the judging guidelines a missing explicit-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Covers the natural terms the target operator would say — imsg-rpc, iMessage, gateway, JSON-RPC, launchd, FDA, code signing — giving good keyword coverage rather than a single bare term.	3 / 3
Distinctiveness Conflict Risk	The imsg-rpc Unix socket daemon niche with FDA/signing/launchd triggers is highly specific and unlikely to conflict with other skills, matching the clear-niche anchor.	3 / 3
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/imsg-rpc/SKILL.md
Commit: 979b138

Reviewed: 10 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.