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 content is a model library skill: lean and dense with library-specific gotchas, executable code with justified excerpts and links to complete programs, a sequenced workflow with explicit terminal verification and a test-fix-rerun loop, and a clean two-file reference structure that keeps the main body focused. No dimension falls below the top anchor.

DimensionReasoningScore

Conciseness

The body teaches only non-obvious, library-specific facts ("Glamour v2 has no auto style and does not detect the terminal's background", "Only the lipgloss.Print family downsamples colors") and never explains concepts Claude already knows; version references (v2.0.1, Go 1.26) are purposeful API pinning rather than time-conditional instructions, and legacy v1 material is segregated into a migration section. Every token earns its place, matching the level-5 anchor.

5 / 5

Actionability

The Go blocks are executable with error handling and are trimmed from linked complete programs ("Go blocks headed // examples/... are trimmed from complete programs that build against the pinned modules"), plus a concrete run command ("go run ./charmed-glamour/viewer ../README.md"); the single excerpt block is explicitly justified as an API sketch with the full program linked, so the pseudocode penalty does not apply.

5 / 5

Workflow Clarity

The five-step workflow is clearly sequenced with a concrete validation step ("Check in a real terminal: light and dark styles, narrow widths, tables, code blocks, and links") and an explicit feedback loop after migration ("run your application's tests, fix failures, and rerun"). This is not a destructive or batch operation, so the level-3 cap does not apply; it matches the level-5 anchor with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

The body keeps the core workflow and key examples inline while deferring detail with clear signposts ("Read [references/options.md](references/options.md) for the other built in style names, every renderer option…"); both referenced files exist, are exactly one level deep, and link back to the skill, matching the level-5 anchor.

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.

This is an exemplary skill description: it states a precise capability inventory in third person, gives explicit and natural Use-when triggers with synonyms and file extensions, and closes with disambiguating negative boundaries against a sibling skill. No dimension shows a weakness against the highest anchors.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete capabilities — "one shot Render, reusable TermRenderer with word wrap and emoji, built in styles (dark, light, dracula, tokyo-night, pink, ascii), custom StyleConfig in Go or JSON, color downsampling through Lip Gloss, and a scrolling viewer inside Bubble Tea" — giving comprehensive coverage of the library's surface, matching the level-5 anchor rather than level 4 (which implies coverage gaps).

5 / 5

Completeness

It explicitly answers both what ("Render Markdown to styled terminal text in Go with Glamour v2…") and when ("Use when showing a README, .md file, help text, changelog…"), with concrete trigger phrases — exactly the level-5 pattern; a 4 would require a less explicit when-clause.

5 / 5

Trigger Term Quality

Natural user phrasing is comprehensive: "showing a README, .md file, help text, changelog, or any Markdown in a CLI or TUI, or when asked to pretty-print Markdown in the terminal" covers synonyms (README, Markdown, pretty-print, terminal/CLI/TUI) and the file extension (.md), matching the level-5 anchor; level 4 ("a few natural terms missing") does not fit.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (Glamour v2 Markdown terminal rendering in Go) and it states explicit negative boundaries — "Not for editing Markdown or for general styling (charmed-lipgloss)" — minimizing conflict risk, matching the level-5 anchor.

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