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 exemplar of skill writing: two runnable examples, exact commands, a validated workflow with a feedback loop and publish-safety check, dense version-pinned facts with zero padding, and clean offloading of exhaustive syntax and CI detail to two well-signaled reference files. The 'Mistakes that cost time' and 'Older versions' sections preempt real failure modes without verbosity.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it carries only version-specific facts (the 0.12.1 baseline, the '.tape' suffix rule, 'VHS_PUBLISH' semantics, ffmpeg exit-code behavior) and non-obvious pitfalls, with no explanation of concepts Claude already knows. Time-sensitive version information is properly quarantined in a dedicated 'Older versions' section, and the longest prose passage (the build-sentinel rationale) devotes each sentence to a distinct failure mode, so it fits the 'every token earns its place' anchor rather than the level below.

5 / 5

Actionability

It provides two complete, executable tapes — a self-contained demo.tape that 'needs no project binary or fixture' and a full TUI recording tape — plus exact commands with flags ('vhs validate ./*.tape', 'env -u VHS_PUBLISH vhs demo.tape'). The examples are copy-paste ready and cover the common cases (bash demo and alt-screen TUI), matching the fully-executable top anchor.

5 / 5

Workflow Clarity

The 4-step workflow sequences writing, validation ('run vhs validate demo.tape'), a publish-safety check ('Check that VHS_PUBLISH is unset, then render'), and output inspection, with an explicit error-recovery feedback loop ('If a command fails or a wait times out, fix the command or expected text and rerun validation and rendering'). This matches the anchor requiring explicit validation steps and feedback loops; the destructive/batch cap does not apply since rendering is non-destructive and the one risky side effect (accidental public upload) has its own checkpoint.

5 / 5

Progressive Disclosure

The body is a clear overview with two well-signaled, one-level-deep references that both exist and deliver exactly what is promised: 'Read references/tape-syntax.md for every Set option … and the full action list' and 'Read references/ci.md before adding vhs to a pipeline: it covers guarding vhs validate …, the pinned charmbracelet/vhs-action step, and what to pin for golden-file and screenshot fixtures'. Exhaustive Set/action tables and CI details are correctly kept out of the main file, and neither reference nests further references, matching the top anchor for clean structure and easy navigation.

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: concrete actions with comprehensive feature coverage, abundant natural trigger terms with synonyms and extensions, an explicit 'Use when' clause with concrete triggers, and a clear negative boundary. It is written in third person and concise despite its density.

DimensionReasoningScore

Specificity

The description states concrete actions ('Record terminal demos as a terminal GIF, MP4, or WebM demo video from a .tape text file', 'asserting its output in tests with golden files', 'CI usage') and enumerates the tool's full feature surface ('tape syntax, Output, Require, Set options (size, font, theme, typing speed, window bar, margin), typing and key commands, Sleep and Wait, Hide and Show, Screenshot, Source'). It matches the anchor for multiple specific concrete actions with comprehensive coverage; it is not the level below, which requires minor gaps in coverage, and no feature area of vhs is omitted.

5 / 5

Completeness

It explicitly answers 'what' ('Record terminal demos as a terminal GIF, MP4, or WebM demo video from a .tape text file with vhs') and 'when' with a concrete 'Use when' clause ('documenting a CLI or TUI with an animated demo, screencast, terminal recording, or screen recording for a README, or asserting its output in tests with golden files'), plus a negative boundary ('Not for writing the program itself'). This clearly matches the top anchor, not the level below where the 'when' could be more explicit.

5 / 5

Trigger Term Quality

Natural user phrases are comprehensively covered with synonyms and extensions: 'terminal demo', 'GIF', 'MP4', 'WebM', 'demo video', 'animated demo', 'screencast', 'terminal recording', 'screen recording', 'README', 'golden files', and '.tape'. This fits the anchor for comprehensive coverage including synonyms and file extensions rather than the level below ('a few natural terms missing').

5 / 5

Distinctiveness Conflict Risk

It names the specific tool (vhs, charmbracelet), occupies a clear niche (terminal demo recording and golden-file assertions), and includes an exclusion clause ('Not for writing the program itself'), so it is unlikely to trigger for the wrong skill. Minimal conflict risk matches the top anchor rather than the level below ('minor overlap risk with closely related skills').

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