tmux-processes

Patterns for running long-lived processes in tmux. Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation.

1.52x

Quality

82%

Does it follow best practices?

Impact

90%

1.52x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

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.

A tight, highly actionable tmux recipe reference with executable code and sensible validation guards on destructive operations. Main improvement opportunity is reducing the repeated SESSION-derivation boilerplate across snippets.

Suggestions

Define the SESSION derivation once near the top and reference it in subsequent snippets, or note that it is assumed already set, to cut repeated boilerplate and improve conciseness.

Consider splitting the longer reference sections (Monitoring Output, Lifecycle Management) into a bundled reference file and signaling it from SKILL.md to strengthen progressive disclosure now that the file exceeds 200 lines.

Add an explicit error-recovery note for the 'Wait for server ready' polling loop (what to do after the 30 iterations elapse without a ready signal) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Prose is lean and assumes Claude's competence, but the SESSION derivation line ('SESSION=$(basename $(git rev-parse --show-toplevel ...) \|\| basename $PWD)') is repeated in roughly ten snippets and could be factored out once.	4 / 5
Actionability	Fully executable, copy-paste-ready bash covering the common cases (start, idempotent start, add windows, monitor, restart, status, kill) with concrete commands throughout.	5 / 5
Workflow Clarity	Sequences are clear with validation checkpoints (has-session guards, list-windows grep checks, ready-polling feedback loop) and isolation rules guarding destructive kill operations; not a single end-to-end workflow with explicit recovery loops, so short of 5.	4 / 5
Progressive Disclosure	A single self-contained file organized into clearly headed sections (Interactive Shell, Session Naming, Starting Processes, Monitoring, Lifecycle, Isolation, When to Use); the cohesive recipe set is appropriately inline, with only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

82%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.

A well-formed description that clearly states both purpose and usage triggers in concise third-person voice. The only soft spot is specificity, which lists trigger scenarios rather than a comprehensive set of distinct skill capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain (tmux, long-lived processes) and the concrete action of running them, but does not list multiple distinct capabilities — the trailing items ('dev servers, watchers, tilt') are trigger scenarios rather than a comprehensive action list.	3 / 5
Completeness	Explicitly answers both 'what' ('Patterns for running long-lived processes in tmux') and 'when' (concrete 'Use when...' clause) in third-person voice with concrete triggers.	5 / 5
Trigger Term Quality	Natural trigger phrases users would actually say ('starting dev servers, watchers, tilt, or any process expected to outlive the conversation') provide good keyword coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	A clear tmux-specific niche anchored by a concrete tool trigger (tilt) makes this distinct from other skills with minimal conflict risk.	5 / 5
	Total	17 / 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: NeverSight/skills_feed
Path: data/skills-md/0xbigboss/claude-code/tmux-processes/SKILL.md
Commit: 2f57aec

Reviewed: about 23 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.