CtrlK
BlogDocsLog inGet started
Tessl Logo

tpscloud/charmedimsure

Source-verified skills for the Charm terminal stack: Bubble Tea v2, Bubbles v2, Lip Gloss v2, Huh v2, Log v2, Glamour v2, plus the gum and vhs CLIs.

100

1.02x
Quality

100%

Does it follow best practices?

Impact

100%

1.02x

Average score across 9 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

100%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 body is an exemplary skill document: a compact overview that concentrates exclusively on the v2 delta over what Claude already knows, complete executable examples with a documented trimming convention, a numbered workflow with an explicit validate-fix-rerun loop, and six well-signaled one-level-deep reference files covering the long-tail API detail. No dimension shows more than minor room for improvement.

DimensionReasoningScore

Conciseness

Every section teaches the v2-specific delta Claude cannot be assumed to know (View returns tea.View not string, feature toggles become tea.View fields, tea.KeyPressMsg replaces tea.KeyMsg, commands vs command factories), with zero padding or explanation of general TUI/Go concepts. The 'Mistakes that cost time' list is dense, non-obvious guidance where every token earns its place.

5 / 5

Actionability

Fully executable guidance throughout: a complete minimal counter program, a real checkServer command factory with context timeout, concrete built-ins (tea.Batch, tea.Sequence, tea.Quit, tea.Println), and exact validation commands (`go vet ./...`, `go test ./...`). The trimmed-imports convention is explicitly documented with links to complete buildable programs, so nothing is pseudocode.

5 / 5

Workflow Clarity

The 6-step Workflow is clearly sequenced with an explicit validation checkpoint and feedback loop: "run `go vet ./...` and `go test ./...`, fix failures, and rerun until both pass. Then try keys and resizing in a real terminal." Validation is re-invoked after migration ("validate as in workflow step 6, check remaining v1-only calls"), matching the 5 anchor's error-recovery pattern.

5 / 5

Progressive Disclosure

SKILL.md is a lean overview with each of the six references/ files signaled from the exact section that needs it, with a description of what it contains (e.g. "Read references/screen.md for a full screen layout, light or dark background detection, and the remaining fields"). All referenced files and named anchors (api.md#migrating-from-v1, #older-v2-releases) verified to exist; references are one level deep with no nested pointers.

5 / 5

Total

20

/

20

Passed

Description

100%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 exemplary: it names concrete capabilities in third person, provides both spellings of the framework name for triggering, and includes an explicit 'Use when' clause plus 'Not for' exclusions against sibling skills. It answers what, when, and what-not comprehensively with no padding.

DimensionReasoningScore

Specificity

Multiple concrete actions are listed: "Build terminal user interfaces (TUI) in Go", "using the Elm architecture Model, Update, View loop", "commands for I/O", "declarative tea.View fields for alt screen, mouse, cursor, and title", plus writing, migrating, handling key/mouse messages, and testing. Coverage spans the full lifecycle of a Bubble Tea app with no generic filler.

5 / 5

Completeness

The 'what' is explicit (build/migrate Bubble Tea v2 TUIs via the Elm architecture, commands, and tea.View fields) and the 'when' is an explicit clause: "Use when writing or migrating a Bubble Tea or bubbletea app, handling tea.KeyPressMsg or mouse messages, wiring async work into a TUI, or testing one." A 'Not for' exclusion clause further sharpens scope beyond the 5 anchor's requirements.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms: "Bubble Tea", "bubbletea", "charmbracelet", "charm.land/bubbletea/v2", "TUI", "Go", "Elm architecture", "tea.KeyPressMsg", "mouse messages". Both user spellings of the framework name and the import path are present, matching the 5 anchor's synonyms-and-specifics bar.

5 / 5

Distinctiveness Conflict Risk

Pinned to a niche (Bubble Tea v2 in Go) with distinct triggers and explicit negative boundary — "Not for ready made widgets (charmed-bubbles), styling (charmed-lipgloss), or forms (charmed-huh)" — which removes overlap with the closest sibling skills. Minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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.

Reviewed

Table of Contents