agent-tui

Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection. Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior. Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.

Quality

78%

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 ./.gemini/skills/agent-tui/SKILL.md

Quality

Content

73%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 and a well-sequenced, validated workflow including error-recovery feedback loops. Its main weakness is verbosity: the same observe/act/wait/verify guidance is repeated across multiple sections alongside conceptual padding that could be trimmed or split into reference files.

Suggestions

Consolidate the observe→act→wait→verify guidance into a single section; the Critical Rules, Core Workflow, Anti-Patterns, and Quick Reference all restate the same loop and could be merged to remove redundancy.

Trim or cut the 'Philosophy: Why Terminal Automation Is Different' table and 'Fresh Eyes Principle' section — these explain concepts Claude already grasps and add token cost without new executable guidance.

Move the macOS daemon workaround and the Gemini CLI testing requirements into separate one-level-deep reference files (e.g. references/macos-daemon.md, references/gemini-cli.md) referenced from the main body, keeping SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body restates the observe→act→wait→verify loop across at least four sections (feedback-loop diagram, Critical Rules, Core Workflow, Anti-Patterns, Quick Reference) and includes padded conceptual sections ('Philosophy: Why Terminal Automation Is Different', 'Fresh Eyes Principle') that go beyond what Claude needs; this is noticeable verbosity with several padded/repeated sections. Not a 1 because the code and command examples themselves are tight and useful.	2 / 5
Actionability	Provides fully executable, copy-paste-ready commands throughout (agent-tui run, screenshot --format json, type, press, wait --assert, kill) and the Quick Reference and Core Workflow cover the common automation cases concretely.	5 / 5
Workflow Clarity	The Core Workflow is a clearly sequenced 1–8 process with explicit validation checkpoints ('wait --assert' to prove outcomes), a dedicated Failure Recovery table, and RULE 5 feedback loop (screenshot to diagnose on timeout); this matches the anchor for clear sequence with explicit validation and error-recovery feedback loops.	5 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and no nested/deep references, but it is a long monolithic document with no external reference files; specialized content (macOS daemon workaround, Gemini CLI testing) could be split into one-level-deep reference files for cleaner navigation, so it stops short of a 5.	4 / 5
	Total	16 / 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.

The description is strong: it clearly states the skill's purpose, provides explicit 'Use when' triggers including natural user phrasings, and carves out a distinct niche. Its only weakness is that the listed capabilities (testing, automation, inspection) are somewhat generic rather than concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Drive terminal UI (TUI) applications programmatically') and lists a few actions ('testing, automation, and inspection'), but those actions are high-level and generic rather than concrete like 'extract text, fill forms, merge documents'; not comprehensive enough for a 4.	3 / 5
Completeness	Explicitly answers both 'what' (drive TUI apps programmatically for testing, automation, inspection) and 'when' ('Use when: automating CLI/TUI interactions... Also use when: user asks...') with concrete trigger phrases, matching the anchor for full completeness.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('what is agent-tui', 'demo agent-tui', 'show me agent-tui', 'how does agent-tui work') plus use-case keywords (automating CLI/TUI interactions, regression testing); a few natural variations are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (programmatic TUI/CLI automation) with distinct product-name triggers ('agent-tui') that are unlikely to fire for unrelated skills, giving 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: google-gemini/gemini-cli
Path: .gemini/skills/agent-tui/SKILL.md
Commit: 85aca16

Reviewed: 4 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.