tmux-cli

CLI utility to communicate with other CLI Agents or Scripts in other tmux panes; use it only when user asks you to communicate with other CLI Agents or Scripts in other tmux panes.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tmux-cli/skills/tmux-cli/SKILL.md

Quality

Content

75%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 concise, actionable, and well-organized with a clear validation mechanism for its primary command, consistently landing at anchor 4 across dimensions. The main weakness is incomplete coverage of the agent-to-agent command set, which is named but never exemplified or sequenced.

Suggestions

Add a short "Communicate with another Claude Code instance" subsection with copy-paste examples for `send`, `wait_idle`, and `capture`, since the Note flags this as the correct path for agent-to-agent chat.

Either flesh out the "Key Commands" section with one subsection per command or explicitly state that `tmux-cli --help` is the canonical reference, so the incomplete section header does not imply missing content.

Replace the deflective "Do `tmux-cli --help` to see how to use it!" with the two or three most common invocations inline, keeping the body self-contained.

Dimension	Reasoning	Score
Conciseness	The body is lean — it does not explain what tmux or exit codes are, and code examples are compact — with only minor instances that could be trimmed (the "This is useful for" bullet list and the deflective "Do tmux-cli --help to see how to use it!"), placing it at anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	The `tmux-cli execute` examples are executable and copy-paste ready with concrete flags (--pane, --timeout) and documented JSON/exit-code output, but the agent-to-agent path (send + wait_idle + capture), flagged as important in the Note, lacks any examples, leaving a coverage gap that caps this at anchor 4.	4 / 5
Workflow Clarity	The single execute action is unambiguous and its exit-code detection (0 success, non-zero failure, -1 timeout) serves as an explicit validation checkpoint, but the broader multi-command agent-to-agent workflow is only named, not sequenced, so it sits at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	The short, well-sectioned body (Instructions, Key Commands, Execute with Exit Code Detection) is appropriately organized for a sub-50-line skill, but the "Key Commands" section documents only `execute` while mentioning send/wait_idle/capture in a note without giving them their own sections, a minor organization gap that fits anchor 4 over 5.	4 / 5
	Total	16 / 20 Passed

Description

68%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 clearly defines a distinctive niche and provides explicit trigger guidance, but its specificity is dragged down by second-person phrasing and a "when" clause that merely restates the "what". Trigger-term quality and distinctiveness are strong.

Suggestions

Rewrite in third person to avoid the specificity penalty — e.g., "CLI utility to communicate with other CLI Agents or Scripts in other tmux panes. Use only when the user requests communication with other CLI Agents or Scripts in other tmux panes."

Add one or two more concrete actions (e.g., send messages, capture output, run commands and detect exit codes) to lift specificity from anchor 3 toward 4–5.

Make the "when" clause add distinct trigger scenarios rather than restating the "what" — e.g., name the situations (multi-agent orchestration, delegating a build/test to another pane) instead of repeating the capability.

Dimension	Reasoning	Score
Specificity	"CLI utility to communicate with other CLI Agents or Scripts in other tmux panes" names the domain and one concrete action, matching anchor 3, but the trigger clause uses second person ("use it only when user asks you to communicate"), which per the judging guidelines reduces the specificity score by 1 to 2.	2 / 5
Completeness	Both "what" (CLI utility to communicate with other CLI Agents or Scripts in tmux panes) and "when" ("use it only when user asks you to communicate...") are explicitly present, but the "when" largely restates the "what" rather than adding distinct trigger scenarios, landing at anchor 4 instead of 5.	4 / 5
Trigger Term Quality	Natural terms a user would say are present — "tmux panes", "CLI Agents", "Scripts", "communicate" — giving good keyword coverage with only minor synonyms missing, fitting anchor 4 rather than 3 (which requires missing common variations) or 5 (which requires comprehensive synonyms and file extensions).	4 / 5
Distinctiveness Conflict Risk	The niche — inter-pane communication with other CLI Agents or Scripts in tmux — is highly specific with distinct triggers and minimal overlap risk with other skills, matching anchor 5.	5 / 5
	Total	15 / 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/tmux-cli/skills/tmux-cli/SKILL.md
Commit: c35a135

Reviewed: about 13 hours 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.