CtrlK
BlogDocsLog inGet started
Tessl Logo

jbaruch/govee-h6056

Ground truth for Govee Flow Plus Light Bars (H6056): phantom segments, bar-to-segment mapping, API auth and rate limits. Language-agnostic facts; Kotlin/Ktor reference example.

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

72%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.

A dense, expert-grade skill body that leads with non-obvious device facts and backs them with executable Kotlin and concrete anti-patterns. Its main gap is the absence of a result-verification feedback loop for batch segment commands, which the rubric caps at workflow_clarity 3.

Suggestions

Add an explicit validation step after batch segment commands (e.g., re-read device state or compare expected vs reported segments) so the verify->fix->retry loop exists for batch operations.

Replace the TODO discovery stub with a minimal executable JSON parse (kotlinx.serialization or Jackson) so the discovery example is copy-paste ready like the control example.

Trim the second code block's main() demo or fold it into the class example to tighten token use toward the score-5 conciseness anchor.

DimensionReasoningScore

Conciseness

Dense with device-specific facts Claude does not already know (phantom segments, segment[0]=TOP, rgb=(1,1,1) off-semantics, silent 429s, no mDNS) and assumes competence, but two full Kotlin classes (client + main) push slightly past 'every token earns its place'.

4 / 5

Actionability

Executable Kotlin with exact endpoints, auth header, payload shape, packed-rgb formula, bar constants, worked bottom-up examples, and env vars, but the discovery block ends in a TODO stub and uses a hand-built JSON string rather than a serializer — minor gaps below fully copy-paste-ready.

4 / 5

Workflow Clarity

Sequence (discover -> set segments -> off-semantics -> shutdown clear) and guardrails (rate-limit, anti-patterns) are clear, but batch segment commands lack an explicit verify-the-light-actually-changed feedback loop, which the rubric caps at 3 for batch operations.

3 / 5

Progressive Disclosure

Well-sectioned, self-contained body with clearly signaled one-level-deep cross-skill references (iot-actuator-patterns-kotlin, render-progress-bar-kotlin), no nested or buried references, and no bundle files to mismanage.

5 / 5

Total

16

/

20

Passed

Description

92%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.

A highly specific, device-expert description that surfaces non-obvious API quirks concisely while clearly stating both capabilities and trigger conditions in correct third-person voice. Its only soft spot is trigger phrasing that leans slightly technical in places.

DimensionReasoningScore

Specificity

Names concrete actions (control via cloud REST API, segment-to-bar mapping Yankee=0-5/Golf=6-11, phantom-segment awareness, rgb=(1,1,1) off-semantics, rate-limit guidance) with comprehensive, esoteric detail beyond the score-4 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (the detailed capabilities clause) and 'when' ('Use when the user wants to control Govee H6056 light bars, change LED light colors or brightness, set bar segment colors, or automate Govee smart lighting scenes') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural phrases ('change LED light colors or brightness', 'automate Govee smart lighting scenes') with synonyms (light bars/LED lights/smart lighting), but 'set bar segment colors' is jargon and common phrasings like 'turn off the lights' are absent, keeping it just below a clean 5.

4 / 5

Distinctiveness Conflict Risk

Tied to a single specific SKU (Govee H6056) with distinct, product-level triggers and minimal conflict risk; the cross-reference to iot-actuator-patterns-kotlin targets a different concern (debounce), not an overlap.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents