agent-terminal
Terminal and TUI automation CLI for AI agents. Use when the user needs to create a terminal session, run a command in a terminal, automate an interactive CLI or TUI, wait for terminal output, capture a TUI screenshot, export a terminal recording, or test a CLI workflow with reviewable artifacts.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly defines its niche in terminal and TUI automation. It provides specific concrete actions, comprehensive trigger terms covering terminal/CLI/TUI variations, and an explicit 'Use when...' clause with multiple scenarios. The description is concise, uses third person voice, and is highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create a terminal session, run a command, automate an interactive CLI/TUI, wait for terminal output, capture a TUI screenshot, export a terminal recording, and test a CLI workflow with reviewable artifacts. | 3 / 3 |
Completeness | Clearly answers both 'what' (terminal and TUI automation CLI for AI agents) and 'when' with an explicit 'Use when...' clause listing seven distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'terminal session', 'run a command', 'interactive CLI', 'TUI', 'terminal output', 'TUI screenshot', 'terminal recording', 'CLI workflow'. Good coverage of variations across terminal/CLI/TUI terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around terminal/TUI automation specifically for AI agents. The combination of TUI screenshots, terminal recordings, and interactive CLI automation is highly distinctive and unlikely to conflict with general shell or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides clear, executable guidance for terminal automation with agent-terminal. Its main strengths are the fully runnable bash examples, clear workflow sequencing with validation steps, and useful anti-patterns. The primary weakness is redundancy between the Core Workflow and Common Patterns sections, which inflates token usage without adding proportional value.
Suggestions
Reduce redundancy by making Common Patterns show only the delta from the Core Workflow (e.g., just the --no-wait and send-keys lines for TUI driving, rather than repeating session creation boilerplate)
Consider extracting the Essential Commands reference into a separate REFERENCE.md file to keep the main skill leaner and improve progressive disclosure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy. The 'Common Patterns' section repeats much of what's already shown in the 'Core Workflow' section with minor variations. The anti-patterns section, while useful, could be tightened. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | Every command is fully executable and copy-paste ready with concrete bash examples. The essential commands reference is comprehensive, and the common patterns provide complete, runnable workflows for different use cases. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced with 8 numbered steps, includes validation checkpoints (doctor --json for prerequisites, wait for observable state instead of blind sleeps), and the anti-patterns section explicitly addresses error-prone approaches. The destroy step ensures cleanup. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (Core Workflow, Essential Commands, Common Patterns, Anti-Patterns), but it's somewhat monolithic. The common patterns section repeats boilerplate from the core workflow and could potentially be split into separate files. No external references are provided, though for a standalone skill of this size it's borderline acceptable. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- coder/agent-tty
- Commit
a05d4e5
- 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.