engram-tui-quality

Bubbletea/Lipgloss quality rules for Engram TUI. Trigger: Changes in model, update, view, navigation, or rendering.

Quality

56%

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 ./skills/tui-quality/SKILL.md

Quality

Content

62%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 admirably concise and well-structured for a simple rules skill, scoring top marks on conciseness and progressive disclosure. Its weakness is actionability: rules are stated as principles without concrete code, commands, or verification steps that tell Claude exactly how to check or enforce them.

Suggestions

Add concrete, executable guidance for each UX rule (e.g., example test snippets for key-transition and rendering-branch tests, or a command to run the TUI test suite).

Include an explicit validation checkpoint before shipping (e.g., 'Run `go test ./...` and confirm all update/view/model tests pass before committing a TUI change').

For each rule, give a one-line concrete check (e.g., 'Empty/loading/error states: assert each screen renders a non-blank placeholder for these states') so the guidance is verifiable rather than aspirational.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's knowledge of TUI concepts, listing only the rules and test expectations without padding or explaining what Bubbletea/Lipgloss are; every token earns its place.	5 / 5
Actionability	Guidance is high-level and rule-based ('Keyboard behavior must be consistent', 'Add update tests for new key transitions') without concrete commands, code, or specific executable steps, leaving Claude to infer how to verify or enforce each rule.	2 / 5
Workflow Clarity	The 'When to Use' list gives a rough sequence of when rules apply and 'No TUI behavior change ships without deterministic tests' acts as a checkpoint, but there are no explicit validation steps or feedback loops for confirming rules are satisfied before shipping.	3 / 5
Progressive Disclosure	The skill is well under 50 lines with no external references needed, organized into clearly labeled sections (When to Use, UX Rules, Test Rules); per the simple-skill guidance this merits a top score with just well-organized sections.	5 / 5
	Total	15 / 20 Passed

Description

51%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 clearly scopes a niche (Engram TUI, Bubbletea/Lipgloss) and provides a trigger, but the trigger relies on internal architecture terms rather than natural user language, weakening trigger term quality. It is concise and reasonably complete but could use more natural phrasing.

Suggestions

Reword the trigger using natural user phrases (e.g., 'Use when modifying Engram screens, key bindings, list rendering, or navigation flows') rather than internal architecture terms like 'update'/'view'.

Expand specificity by naming concrete actions (e.g., 'enforces keyboard consistency, empty/loading/error state handling, and deterministic TUI tests').

Add synonyms/file cues users actually say (e.g., 'Engram TUI', 'Bubbletea commands', 'Lipgloss styles') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Bubbletea/Lipgloss quality rules for Engram TUI') and lists concrete actions like model, update, view, navigation, and rendering, but these are generic TUI areas rather than a comprehensive set of distinct actions.	3 / 5
Completeness	States both what it does (Bubbletea/Lipgloss quality rules for Engram TUI) and when to trigger ('Trigger: Changes in model, update, view, navigation, or rendering'), though the 'when' is terse and could be more explicit.	4 / 5
Trigger Term Quality	'Changes in model, update, view, navigation, or rendering' are internal architecture terms rather than natural phrases a user would say; lacks natural synonyms or file/extension cues a user would actually voice.	2 / 5
Distinctiveness Conflict Risk	The Engram TUI + Bubbletea/Lipgloss framing carves a clear niche with minimal overlap against generic Go or TUI skills, though it could still overlap with a broader Go quality skill.	4 / 5
	Total	13 / 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: Gentleman-Programming/engram
Path: skills/tui-quality/SKILL.md
Commit: 47f281c

Reviewed: 6 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.