CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

90

1.52x
Quality

Does it follow best practices?

Impact

90%

1.52x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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-structured tmux reference with executable patterns and explicit validation checkpoints. Its main weakness is token efficiency: the SESSION derivation and several idempotent-start examples are repeated, creating redundancy that could be consolidated into a shared snippet or DRY helper.

Suggestions

Define the SESSION derivation once at the top and reference it ('using SESSION from above') instead of repeating the basename/git-rev-parse line in every code block.

Consolidate the overlapping idempotent-start examples ('Idempotent Start' and 'Start dev server if not running' Common Pattern) into a single canonical pattern to remove duplication.

Extract the repeated window-existence check (list-windows | grep) into one reusable snippet rather than restating it in both 'Adding Windows' and 'Checking Process Status'.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no irrelevant concept padding, but the SESSION derivation snippet is repeated verbatim ~10 times and several sections (Idempotent Start vs. the duplicated 'Start dev server if not running' Common Pattern) overlap, inflating the token budget without adding information.

2 / 3

Actionability

Fully executable bash with real flags and placeholders throughout — new-session/send-keys, idempotent has-session checks, capture-pane monitoring, and a ready-polling loop — all copy-paste ready.

3 / 3

Workflow Clarity

Clear sequencing with explicit validation checkpoints (has-session before create, list-windows grep before new-window, capture-pane polling for ready) and explicit isolation rules ('Always verify session name before kill operations').

3 / 3

Progressive Disclosure

No bundle files exist and none are referenced; the single file is organized into clearly-headed sections with no nested/deep references and nothing that needs splitting out, so the section-based organization stands.

3 / 3

Total

11

/

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 concise, well-targeted description with an explicit 'Use when' trigger and natural trigger terms covering the dev-server/watcher/tilt niche. The only weakness is that the 'what' is phrased as abstract 'Patterns for running' rather than naming concrete tmux operations.

DimensionReasoningScore

Specificity

Names the domain ('long-lived processes in tmux') and concrete use cases ('dev servers, watchers, tilt') but describes actions abstractly as 'Patterns for running' rather than enumerating multiple specific operations like creating sessions, sending commands, or monitoring output.

2 / 3

Completeness

Clearly answers both what ('Patterns for running long-lived processes in tmux') and when via an explicit 'Use when...' trigger clause listing concrete scenarios.

3 / 3

Trigger Term Quality

'starting dev servers, watchers, tilt, or any process expected to outlive the conversation' gives good coverage of natural terms a user would actually say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

The tmux + long-lived-process niche with specific triggers like 'tilt' and 'outlive the conversation' is sharply defined and unlikely to conflict with other 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.