tmux

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Quality

85%

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

Quality

Content

87%

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

A concise, highly actionable skill body with clean progressive disclosure and real helper scripts, weakened only by destructive cleanup operations that proceed without an explicit verification checkpoint.

Suggestions

Add a validation checkpoint before destructive cleanup, e.g. run `./scripts/find-sessions.sh -S "$SOCKET"` to list targets and confirm intent before `kill-session`/`kill-server`.

Tighten the repeated monitor-command emphasis (the 'ALWAYS... must ALWAYS... once again... the earlier you send it the happier' passage) into a single concise instruction to reduce editorial padding.

Dimension	Reasoning	Score
Conciseness	The body is lean — short sections, executable snippets, and no explanation of concepts Claude already knows; it assumes tmux/bash competence and almost every token earns its place, with only minor editorial emphasis on the monitor-command reminder that is justified behavioral guidance rather than concept padding.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout — `tmux -S "$SOCKET" new -d -s ...`, `send-keys ... -l --`, `capture-pane -p -J -t ... -S -200`, and helper-script calls with all flags — rather than vague direction.	3 / 3
Workflow Clarity	The interactive loop has good polling-based validation (wait-for-text.sh with explicit success/timeout feedback), but the destructive cleanup path (kill-session, `xargs ... kill-session`, kill-server) lacks a verify-before-destroy checkpoint, capping this at 2 per the destructive-operation guideline.	2 / 3
Progressive Disclosure	Well-organized into clear sections with one-level-deep references to real bundle files (`./scripts/find-sessions.sh`, `./scripts/wait-for-text.sh`) that are clearly signaled and whose short usage is documented inline; no nested references.	3 / 3
	Total	11 / 12 Passed

Description

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.

A specific, distinctive description that names concrete actions and natural trigger terms, but it omits an explicit 'Use when...' trigger clause, leaving the activation guidance implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when you need to drive an interactive CLI (python REPL, gdb, psql, node) inside a persistent tmux session, send keystrokes to it, or read its output.'

Surface a couple more natural variations a user might say (e.g. 'terminal', 'REPL', 'send commands to a running process') to widen trigger coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Remote control tmux sessions', 'sending keystrokes and scraping pane output' — tied to a concrete interactive-CLI domain, matching the anchor listing several specific actions rather than only naming a domain.	3 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is only implied; the missing-trigger cap holds this at 2.	2 / 3
Trigger Term Quality	Includes natural terms a user would actually say — 'tmux sessions', 'interactive CLIs (python, gdb, etc.)' — giving good coverage of the realistic trigger vocabulary for this niche.	3 / 3
Distinctiveness Conflict Risk	The combination of 'tmux sessions' and 'interactive CLIs' carves a clear, narrow niche that is unlikely to collide with unrelated skills.	3 / 3
	Total	11 / 12 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: mitsuhiko/agent-stuff
Path: skills/tmux/SKILL.md
Commit: d265b8e

Reviewed: 5 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.