Tessl • The management layer for AI agent skills

SkillPublic

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.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

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

The content is a strong, highly actionable command reference with genuine safety and error-recovery guidance for an outward-facing messaging skill. Its main weaknesses are mild redundancy, time-sensitive references placed inline, and the Flagg/Executor operational detail that could be split into a reference file.

Suggestions

State the '"sent" is optimistic, not delivery-confirmed' caveat once (keep it in Delivery Notes and drop the duplicate bullet in Setup) to tighten conciseness.

Move the Flagg/Executor operational details (LaunchAgent, bearer token, health/restart commands, receipts path) into a references/flagg.md file, keeping a one-line pointer in SKILL.md to improve progressive disclosure.

Add an explicit post-send verification step for terminal-mode sends (e.g., check Messages.app for the delivery indicator before reporting success), mirroring the retry guidance already present for Flagg.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with every command example earning its place, but the 'sent optimistically' caveat is stated twice (Setup and Delivery Notes) and dated/time-sensitive material (ADR-0067, the 2026-09 receipts path) sits inline rather than in a deprecation-style section.	4 / 5
Actionability	Every operation has a copy-paste-ready command — 'imsg chats --limit 10 --json', 'imsg history --chat-id <id> --limit 20 --attachments --json', three send variants, the brew install line, and concrete health-check commands — covering the common cases fully.	5 / 5
Workflow Clarity	A safe sequence is present (read-only first, 'Always confirm recipient and message text before imsg send', 'Call imsg_status first', 'check Messages.app before retrying'), but the terminal-mode send path lacks an explicit post-send delivery-verification loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Sections are clear and well-organized with no bundle files to reference, but the dense Flagg/Executor operational block (LaunchAgent details, bearer token, health/restart commands) is inlined where it would fit naturally in a separate reference file.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 an exemplary skill description: it states the domain, enumerates all four concrete capabilities, and closes with an explicit trigger clause containing natural user phrasings. It is concise, in third person, and highly distinct from other skills.

Dimension	Reasoning	Score
Specificity	The description lists four concrete actions — 'listing chats, reading message history, watching for new messages, and sending messages' — which comprehensively covers the CLI's command surface with no gaps, matching the top anchor.	5 / 5
Completeness	It explicitly answers 'what' (the four concrete actions) and 'when' via an explicit 'Triggers on:' clause with concrete trigger phrases, satisfying the top anchor's requirement for both.	5 / 5
Trigger Term Quality	'Triggers on: check messages, read imessage, send text, imsg, message history, sms, who texted me' covers natural conversational phrases users would actually say, including synonyms (sms, text, imessage) and the CLI name itself.	5 / 5
Distinctiveness Conflict Risk	The iMessage/SMS messaging niche is clear and triggers like 'imsg' and 'who texted me' are highly unlikely to fire for any other skill, giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/imsg/SKILL.md
Revision: 4639c31

Reviewed: 1 month ago

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.

imsg

Table of Contents

Is this your skill?