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 a dense, high-signal reference: pinned-version API facts, disclosed excerpt conventions with linked complete programs, a sequenced workflow with an explicit test-and-fix loop, and well-signaled one-level-deep references that were all verified to exist. The 'Mistakes that cost time' list adds concrete failure modes with exact fixes.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows; every sentence carries huh-v2-specific API facts ("Passwords use NewInput().EchoMode(huh.EchoModePassword)", "Validation runs when the field loses focus"). The "Pinned and verified against v2.0.3" statement is load-bearing accuracy info paired with pre-v2 drift handling rather than stale date-conditional advice, so it does not warrant the version-number penalty.

5 / 5

Actionability

Guidance is executable end to end: a runnable command ("cd examples && go run ./charmed-huh/standalone"), complete worked examples for standalone, dynamic, embedded, and spinner cases with the trimming convention disclosed up front ("Go blocks headed // examples/... are trimmed from complete programs"), and exact error contracts ("errors.Is(err, huh.ErrUserAborted) ... os.Exit(130)"). The common cases are each covered by specific code, fitting the copy-paste-ready anchor.

5 / 5

Workflow Clarity

The 6-step workflow is clearly sequenced and ends with an explicit validation checkpoint and feedback loop: "Try it in a terminal: required fields, back navigation, ctrl+c, dynamic options, and once in accessible mode (TERM=dumb). Fix what fails and rerun." Additional checkpoints appear inline ("Check the bound values after Run"), and the 'Mistakes that cost time' section acts as an error-recovery checklist. Building forms is neither destructive nor batch, so the workflow-clarity cap does not apply.

5 / 5

Progressive Disclosure

Verified against the actual bundle: all five referenced files exist in references/ and are one level deep with no nested references, and each pointer states exactly what the file contains ("Read [references/fields.md] for the per field setter table, default key bindings and KeyMap, group layouts, and every form level option"). The body stays an overview with representative examples while bulk detail (setter tables, theme lists, v1-to-v2 mapping) lives in the reference files.

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 a model example: it states concrete capabilities exhaustively for the library's scope, gives explicit 'Use when' triggers in natural user language, and closes with explicit negative scoping against the two most confusable sibling skills. Voice and register are correct throughout.

DimensionReasoningScore

Specificity

"input, text, password, select, multiselect, confirm, note, and file picker fields grouped into pages, with validation, dynamic fields, themes, accessible mode, and a spinner" enumerates every field type the skill supports plus cross-cutting features and both execution modes ("standalone with Run or embedded in a Bubble Tea v2 program"), matching the comprehensive-coverage anchor rather than anchor 4's 'minor gaps'. Voice is third person, so no voice penalty applies.

5 / 5

Completeness

The 'what' is explicit and concrete ("Build terminal forms and interactive prompts in Go with Huh v2..." with the full field list) and the 'when' is an explicit "Use when" clause with concrete trigger scenarios and run modes. This clearly matches the anchor where both what and when are answered with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Use when asking a user questions from a CLI, building a wizard, survey, or yes or no question" plus "terminal forms and interactive prompts" and "Bubble Tea v2 program" covers the natural synonyms users would say, and the library identity ("charm.land/huh/v2, charmbracelet") serves the same role a file extension does for document skills. No meaningful natural trigger phrasing is missing, so it sits above anchor 4.

5 / 5

Distinctiveness Conflict Risk

The description pins the exact library, language, and version, and adds explicit negative scoping — "Not for shell scripts (charmed-gum) or free form TUIs (charmed-bubbletea)" — which disambiguates it from the closest sibling skills. Clear niche with distinct triggers and 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