gentleman-bubbletea

Bubbletea TUI patterns for Gentleman.Dots installer. Trigger: When editing Go files in installer/internal/tui/, working on TUI screens, or adding new UI features.

Quality

73%

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/gentleman-bubbletea/SKILL.md

Quality

Content

72%

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 real Go code and commands and a clear decision-tree checklist, supported by clean single-file organization. Its main weaknesses are redundancy between the Patterns and Examples sections and the lack of explicit validation checkpoints in the workflow.

Suggestions

Merge or deduplicate the key/scroll-handling code that appears in both 'Pattern 4' and 'Example 3' to reduce redundancy and tighten the token budget.

Turn the build/test commands into explicit validation checkpoints in the decision tree (e.g. after adding a screen: run 'go build ./cmd/gentleman-installer' and only proceed once it compiles).

Expand trigger-term coverage in the description with natural variations users would say (e.g. 'Lipgloss', 'terminal UI', 'navigation', 'menus').

Dimension	Reasoning	Score
Conciseness	The body is code-dense and assumes Claude's competence without explaining what a TUI or Go is, but it carries notable redundancy — the scroll/key-handling logic appears in both 'Pattern 4' and 'Example 3', and 'Example 1' is a trivial two-case snippet. It is mostly efficient but could be tightened, matching the score-2 anchor.	2 / 3
Actionability	It provides real, executable Go code (not pseudocode), concrete build/test commands ('go build ./cmd/gentleman-installer', 'go test ./internal/tui/...'), and a concrete decision-tree checklist. The placeholder types (SomeType, ScreenNewFeature) are justified as illustrative templates for adding new features, keeping it copy-paste-ready in form.	3 / 3
Workflow Clarity	The decision tree gives a clear sequenced checklist (define constant -> add state -> add handler -> create keys function -> add view case -> add title), but validation is only implicit: build/test commands are listed in a separate section rather than wired in as explicit 'validate then proceed' checkpoints, so it does not reach the score-3 feedback-loop anchor.	2 / 3
Progressive Disclosure	With no bundle files present, the single SKILL.md is organized into clear sections (When to Use, Critical Patterns, Decision Tree, Code Examples, Commands, Resources) and points to one-level-deep project files that are clearly signaled ('See installer/internal/tui/model.go for state management'). Navigation is easy and references are not deeply nested.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 distinctive and explicitly covers both what it does and when to use it, with an explicit trigger clause. It is slightly held back by a noun-phrase 'what' and moderate rather than broad trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The 'what' is a single domain noun phrase ('Bubbletea TUI patterns for Gentleman.Dots installer') and the triggers name a few actions ('editing Go files', 'working on TUI screens', 'adding new UI features'), but it does not enumerate multiple concrete capabilities the way a score-3 anchor does. It clears score 2 by naming the domain and some actions, but is not comprehensive.	2 / 3
Completeness	It explicitly answers both what ('Bubbletea TUI patterns for Gentleman.Dots installer') and when, via an explicit 'Trigger: When editing Go files..., working on TUI screens, or adding new UI features' clause — an explicit trigger guidance equivalent to 'Use when...'. It is not score 2 because the 'when' is explicit, not missing or implied.	3 / 3
Trigger Term Quality	It includes relevant natural terms a developer would say ('TUI screens', 'Go files', 'UI features', 'Bubbletea') but misses common variations ('Lipgloss', 'terminal UI', 'navigation', 'menus') and relies on a file path ('installer/internal/tui/') that is not a natural utterance. Coverage is partial rather than broad, matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	It carves a clear, narrow niche tied to a named project (Gentleman.Dots installer), a named library (Bubbletea) and a concrete path, making accidental triggering for an unrelated skill very unlikely. It is more specific than the score-2 'could still overlap' anchor.	3 / 3
	Total	10 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Gentleman-Programming/engram
Path: skills/gentleman-bubbletea/SKILL.md
Commit: 763a6ba

Reviewed: 3 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.