msg

Inter-agent communication via the msg CLI. Use this when you need to send messages to other agent sessions, read incoming messages, or coordinate with other agents in tmux panes.

Quality

87%

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

87%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 body is a tight, fully executable CLI reference with no wasted tokens and good section organization. Its one real gap is workflow clarity: it sequences the commands well but omits any verification/validation checkpoints for an inter-agent coordination workflow (e.g., confirming registration or diagnosing a failed send).

Suggestions

Add a verification step after registration, e.g. confirm with `msg list` that your name appears before sending, and note that `msg status` diagnoses delivery problems if a send seems to fail.

Clarify the receive/reply loop: mention checking `msg inbox` before relying on `msg reply`, and define what "grouped by thread" means for picking the right thread to reply to.

Add a brief note on message persistence or lifecycle (are messages retained after being read?) so the receiving workflow is unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: short intro lines plus executable command blocks with no padding and no explanation of concepts Claude already knows (e.g., what tmux or agents are); every token earns its place, including genuinely non-obvious guidance about message context cost.	5 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands (msg register, msg send, msg reply, msg inbox, msg list/threads/status) covering the common single-send, multi-send, reply, and inbox cases.	5 / 5
Workflow Clarity	Sections sequence a coherent workflow (register → send/reply → receive → other commands → guidelines), but there are no validation/verification checkpoints — e.g., no instruction to confirm registration with `msg list` before sending, or to consult `msg status` on a send failure — so checkpoints are absent rather than merely minor gaps.	3 / 5
Progressive Disclosure	No bundle files exist and none are referenced; the skill is single-purpose and well-organized into clear sections with no inlined content that belongs in a separate file, so it appropriately self-contained per the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

87%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.

The description is concise, specific, and explicitly pairs a clear statement of what the skill does with concrete "Use this when..." trigger guidance. It occupies a distinct niche with low conflict risk; the only mild weakness is that trigger-term and action coverage could be slightly more exhaustive.

Dimension	Reasoning	Score
Specificity	Names the domain (inter-agent communication via the msg CLI) and three concrete actions — "send messages to other agent sessions", "read incoming messages", "coordinate with other agents in tmux panes" — but does not enumerate the full command surface (reply, threads, list, status), leaving minor gaps that keep it just below comprehensive (5).	4 / 5
Completeness	Explicitly answers both what ("Inter-agent communication via the msg CLI") and when ("Use this when you need to send messages to other agent sessions, read incoming messages, or coordinate with other agents in tmux panes") with concrete trigger phrases, matching the anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ("send messages", "read incoming messages", "coordinate with other agents") but misses common synonyms/variants (chat, notify, ping) and CLI-name variety, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — inter-agent messaging coordinated in tmux panes via a specific CLI — with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pchalasani/claude-code-tools
Path: plugins/msg/skills/msg/SKILL.md
Commit: ee0f309

Reviewed: 3 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.