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.
93
92%
Does it follow best practices?
Impact
100%
3.84xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 excellent skill description that is highly specific, technically detailed, and well-structured. It clearly identifies the exact hardware target, lists concrete implementation details that would help Claude use the skill correctly, and includes a comprehensive 'Use when' clause with natural trigger terms. The only minor concern is that the description is quite dense with technical details that serve more as implementation guidance than selection criteria, but this doesn't detract from its effectiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and technical details: segment-to-bar mapping with exact ranges (Yankee=0-5, Golf=6-11), phantom-segment awareness (12-14), correct 'off' semantics (rgb=(1,1,1)), rate-limit guidance (~7 req/min), and references a specific companion skill for debounce. | 3 / 3 |
Completeness | Clearly answers both 'what' (controls Govee H6056 via cloud REST API with specific technical behaviors) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios including controlling light bars, changing colors/brightness, setting segment colors, and automating scenes. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Govee H6056', 'light bars', 'LED lights', 'change LED light colors or brightness', 'bar segment colors', 'smart lighting scenes', 'Govee smart lighting'. Good coverage of both product-specific and general smart lighting terms. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely specific niche targeting a single hardware product (Govee H6056 Flow Plus light bars) with device-specific implementation details. Very unlikely to conflict with any other skill given the precise product model and protocol details. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, information-dense skill that captures critical tribal knowledge about the Govee H6056 (phantom segments, off semantics, rate limits, bar mapping) that Claude could not infer from general knowledge. The executable Kotlin examples are excellent. The main weaknesses are the lack of explicit validation/retry workflows given the described silent failure modes, and the monolithic structure that could benefit from splitting into bundle files for the code examples and anti-patterns.
Suggestions
Add an explicit validation/retry workflow after sending segment commands — e.g., 'If status != 200 or device doesn't update within 2s, retry with backoff' — to address the silent 429 and no-op failure modes you document.
Provide explicit file paths or links for the referenced skills (iot-actuator-patterns-kotlin, render-progress-bar-kotlin) so Claude can navigate to them directly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section delivers non-obvious, hard-won knowledge (phantom segments, off semantics, bar mapping, rate-limit quirks). There is no explanation of what Govee is, what REST APIs are, or how Kotlin works. Every token earns its place. | 3 / 3 |
Actionability | Provides fully executable Kotlin code for the core client, discovery, bottom-up fill, and shutdown hook. Includes exact API endpoint, header format, payload JSON structure, packed RGB formula, and companion object constants — all copy-paste ready. | 3 / 3 |
Workflow Clarity | The skill covers discovery, control, and shutdown as distinct operations with clear code, but lacks an explicit sequenced workflow with validation checkpoints. There's no 'verify the device responded' step after sending commands, and given the silent 429 / silent no-op failure modes described, a validate-and-retry feedback loop would be important. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and references two external skills (iot-actuator-patterns-kotlin, render-progress-bar-kotlin). However, the file is fairly long (~120 lines of substantive content) and has no bundle files to offload detail into. The discovery code and anti-patterns could be separate references, and the cross-skill references lack explicit paths or links. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents