tui

Use when you need to operate a full-screen terminal application (TUI) via wsh. Examples: "navigate vim to edit a file", "use lazygit to stage and commit changes", "interact with htop or k9s".

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/tui/SKILL.md

Quality

Discovery

89%

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 solid description with a clear 'Use when' clause and good trigger term coverage through concrete examples. Its main weakness is that it describes the domain and gives examples rather than listing the specific concrete actions/capabilities the skill provides (e.g., sending keystrokes, reading screen output, navigating menus). The example-driven approach is effective for trigger matching but slightly less specific about the skill's actual mechanics.

Suggestions

Add explicit concrete actions the skill performs, e.g., 'Sends keystrokes, reads screen output, and navigates menus in full-screen terminal applications (TUI) via wsh.'

Dimension	Reasoning	Score
Specificity	The description names the domain (full-screen terminal applications/TUI via wsh) and gives examples of specific tools (vim, lazygit, htop, k9s), but doesn't list concrete actions the skill performs beyond the examples. It describes what the user might ask rather than what the skill does.	2 / 3
Completeness	Explicitly answers both 'what' (operate full-screen terminal applications via wsh) and 'when' (starts with 'Use when' and provides concrete trigger examples). The 'Use when...' clause is present and clear.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would actually say: 'vim', 'lazygit', 'htop', 'k9s', 'TUI', 'terminal application', 'stage and commit changes', 'navigate', 'edit a file'. These cover common user phrasings well.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly defined: full-screen TUI applications operated via wsh. This is distinct from general terminal/shell skills, file editing skills, or git skills because it specifically targets interactive TUI operation through wsh.	3 / 3
	Total	11 / 12 Passed

Implementation

62%

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 instructional skill that covers TUI interaction comprehensively with good workflow patterns (read-act-verify loops) and practical exit strategies. However, it's somewhat verbose for Claude's knowledge level — sections explaining what TUIs are, what vim modes are, and ASCII layout diagrams add tokens without proportional value. The actionability suffers from pseudocode-style examples rather than concrete tool invocations.

Suggestions

Trim explanatory content Claude already knows (what alternate screen buffers are, what vim/nano/htop do) and focus on the novel interaction patterns specific to wsh tooling.

Replace pseudocode navigation sequences ('send: j / wait / read screen') with actual tool call examples using wsh_send_input and wsh_get_screen to make guidance copy-paste actionable.

Extract the 'Common Applications' keybinding reference into a separate file (e.g., TUI_KEYBINDINGS.md) and reference it from the main skill to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-written but includes some unnecessary explanations that Claude would already know (e.g., what alternate screen buffers are, what vim modes are, basic descriptions of htop/k9s). The ASCII diagrams and common application sections add bulk that could be trimmed. The execution context preamble is also somewhat verbose.	2 / 3
Actionability	The skill provides concrete keybindings and navigation patterns, but lacks executable code/commands — the 'send: j / wait / read screen' sequences are pseudocode rather than actual tool invocations. The guidance is specific enough to be useful but not copy-paste ready for any particular tool interface.	2 / 3
Workflow Clarity	The workflow is clearly sequenced: detect alternate screen → read the grid → navigate one keystroke at a time with screen reads between → verify exit via alternate_active flag. The 'read between keystrokes' pattern is an explicit validation checkpoint, and the exit strategies section provides a clear escalation sequence with confirmation steps.	3 / 3
Progressive Disclosure	The content is a single monolithic file with no references to supporting documents. The common applications section (vim, nano, lazygit, htop, k9s) could be split into separate reference files. The execution context preamble references 'skills/core/SKILL.md' for HTTP fallback, which is appropriate, but the main body would benefit from better content splitting.	2 / 3
	Total	9 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: deepgram/wsh
Commit: 4863aaf

Reviewed: 10 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.