CtrlK
BlogDocsLog inGet started
Tessl Logo

tmux

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

89

1.14x
Quality

Does it follow best practices?

Impact

100%

1.14x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-guarded tmux reference with executable idempotent patterns and clear validation checkpoints. Its main weaknesses are repeated boilerplate across code blocks and a monolithic single-file structure that does not leverage progressive disclosure.

Suggestions

Define the SESSION derivation once and reference it, or factor it into a small sourced snippet, instead of repeating the full `basename $(git rev-parse ...)` line in every code block.

Consider moving the 'Common Patterns' and 'When to Use tmux' reference material into a separate file (e.g. references/patterns.md) linked from the body to apply progressive disclosure and slim the main SKILL.md.

Consolidate the overlapping 'Session Reuse Rules' and 'Isolation Rules' sections into a single hard-requirements block to remove redundancy.

DimensionReasoningScore

Conciseness

The body is mostly lean code with minimal concept explanation, but the `SESSION=$(basename $(git rev-parse ...))` line is repeated verbatim in nearly every code block and the 'Session Reuse Rules'/'Isolation Rules' sections overlap, so it could be tightened; not the level-3 'every token earns its place' bar.

2 / 3

Actionability

Abundant concrete, executable, copy-paste-ready bash with real tmux commands and idempotent guards, matching the level-3 anchor for fully executable guidance.

3 / 3

Workflow Clarity

Operations are sequenced with explicit validation checkpoints (has-session / list-windows checks before creation, verify-session-name before kill, ready-poll loop), satisfying the level-3 anchor for clear sequences with validation.

3 / 3

Progressive Disclosure

It is a single ~210-line monolithic file with well-organized sections but no file splitting or referenced materials; at this size some content (e.g., the common-patterns library) could be offloaded to a reference, so it sits at level 2 rather than the level-3 split-and-navigate anchor.

2 / 3

Total

10

/

12

Passed

Description

90%

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 strong, well-structured description with explicit what-and-when triggers and natural language a user would say. The only weakness is that the capability verbs are somewhat general ('running') rather than enumerating multiple concrete actions.

DimensionReasoningScore

Specificity

Names the domain ('running long-lived processes in tmux') and concrete trigger scenarios ('dev servers, watchers, tilt'), but the actions themselves are general ('running') rather than multiple distinct concrete operations, so it stops short of the level-3 anchor.

2 / 3

Completeness

It explicitly states what ('Patterns for running long-lived processes in tmux') and when ('Use when starting dev servers, watchers, tilt...'), matching the level-3 anchor with an explicit trigger clause.

3 / 3

Trigger Term Quality

'Use when starting dev servers, watchers, tilt, or any process expected to outlive the conversation' uses natural terms a user would actually say, with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

tmux process management is a clear niche with distinct triggers unlikely to fire for unrelated skills; no overlap risk with general skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
Reviewed

Table of Contents

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.