Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

tmux

Use when a CLI task needs an interactive terminal or control of a tmux session.

Quality

74%

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 ./nanobot/skills/tmux/SKILL.md

Quality

Content

80%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 highly actionable with executable commands throughout and a clean, well-structured layout that makes appropriate use of its two helper scripts. Its main weaknesses are duplicated helper/socket documentation and a lack of validation before destructive cleanup operations (kill-session/kill-server), which caps workflow clarity.

Suggestions

Add a validation step before destructive cleanup, e.g. check that each session's prompt has returned (capture-pane + prompt grep) or confirm with the user before running kill-session/kill-server.

Consolidate the wait-for-text.sh documentation into a single section (the "Watching output" mention or the "Helper" section, not both) and merge the socket-convention details into the Quickstart.

Consider moving the multi-agent orchestration example (~25 lines) into a separate reference file to keep SKILL.md focused on core tmux operation.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-first with almost no explanation of concepts Claude already knows, but the socket convention is repeated (Quickstart vs. its own section) and wait-for-text.sh is documented twice ("Watching output" and the "Helper" section). Anchor 4 (efficient, minor instances that could be trimmed); not 5 due to this duplication.	4 / 5
Actionability	Fully executable, copy-paste-ready bash blocks throughout: complete Quickstart with socket setup, send-keys with literal-mode flags, capture-pane with flags, and helper scripts documented with every flag and default. Matches anchor 5.	5 / 5
Workflow Clarity	The Quickstart sequence is clear and wait-for-text.sh provides a validation checkpoint, but the cleanup section performs destructive batch operations ("list-sessions \| xargs kill-session", "kill-server") with no verification that sessions/agents have finished first. Per the rubric guideline, destructive/batch workflows without validation cap workflow clarity at 3.	3 / 5
Progressive Disclosure	Both bundle scripts (scripts/find-sessions.sh, scripts/wait-for-text.sh) exist and are referenced one level deep with clear, well-signaled usage; the ~120-line body is organized into clean sections with a Quickstart up front. Matches anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

60%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 has a strong, explicit trigger clause and occupies a distinct niche, but it is essentially all 'when' and almost no 'what' — no concrete capabilities (create sessions, send input, capture output) are stated. Adding 2-3 specific actions and a few trigger synonyms would raise specificity and completeness substantially.

Suggestions

Add concrete capabilities to the description, e.g. "Create and manage tmux sessions, send keystrokes to panes, and capture terminal output" before the 'Use when' clause.

Include natural trigger synonyms such as "interactive TTY", "terminal session", or "REPL" to broaden keyword coverage.

State what the skill does for orchestration scenarios (e.g. running multiple coding agents in parallel) since that is a major use case in the body.

Dimension	Reasoning	Score
Specificity	"control of a tmux session" names the domain but lists no concrete actions such as creating sessions, sending keystrokes, or capturing output. This matches anchor 2 (domain named, actions minimal/generic), not 3, because no specific capabilities are stated.	2 / 5
Completeness	The 'when' is explicit ("Use when a CLI task needs an interactive terminal") but the 'what' is only vaguely implied by "control of a tmux session" with no statement of concrete capabilities. Falls between anchor 2 (only 'when' present) and anchor 4 (both present, one weak) — the vague 'what' keeps it below 4.	3 / 5
Trigger Term Quality	Natural phrases "CLI task", "interactive terminal", and "tmux session" would be said by users needing this skill. Not 5 because common synonyms like "TTY", "REPL", or "attach" are absent.	4 / 5
Distinctiveness Conflict Risk	tmux session control with an interactive-terminal trigger is a clear niche with distinct triggers and minimal conflict risk with other skills. Matches anchor 5.	5 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HKUDS/nanobot
Path: nanobot/skills/tmux/SKILL.md
Revision: 3c61bcf

Reviewed: 10 days ago

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.

tmux

Table of Contents

Is this your skill?