jbaruch/govee-h6056
Ground truth for Govee Flow Plus Light Bars (H6056): phantom segments, bar-to-segment mapping, API auth and rate limits.
100
100%
Does it follow best practices?
Impact
100%
3.84xAverage score across 6 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 combines highly specific technical details (segment-to-bar mapping, phantom-segment awareness, REST API) with clear trigger guidance via an explicit 'Use when' clause. It covers both product-specific terms and general smart lighting vocabulary, making it easy for Claude to select appropriately. The description is concise yet comprehensive, serving as a strong example of a well-crafted skill description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and technical details: controlling light bars via cloud REST API, segment-to-bar mapping with exact ranges (Yankee=0-5, Golf=6-11), phantom-segment awareness (12-14), color/brightness control, and scene automation. | 3 / 3 |
Completeness | Clearly answers both 'what' (controls Govee H6056 via cloud REST API with correct segment mapping and phantom-segment awareness) and 'when' (explicit 'Use when' clause listing control light bars, change colors/brightness, set segment colors, automate scenes). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Govee', 'H6056', 'light bars', 'LED lights', 'colors', 'brightness', 'bar segment colors', 'smart lighting', 'scenes'. Covers both product-specific and generic lighting control terms. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely distinct — targets a specific hardware device (Govee H6056 Flow Plus) with specific technical details like segment mapping and phantom segments. Very unlikely to conflict with any other skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that efficiently communicates hard-won, non-obvious knowledge about the Govee H6056 API — phantom segments, firmware quirks, and correct segment mapping — that Claude could not derive from public documentation alone. The executable code example is complete and production-ready with retry logic and safety assertions. The structure is clean, progressing from device facts through API contract to actionable guidance and shutdown procedures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section delivers information Claude wouldn't already know — phantom segments, firmware quirks with rgb(0,0,0), packed int format, bar-to-segment mapping. No filler explaining what APIs or LEDs are. Comments in code are terse and purposeful. | 3 / 3 |
Actionability | Provides a fully executable Python example with correct headers, payload structure, retry logic, and an assertion guard against phantom segments. The 'How to act' section gives specific, numbered instructions with concrete segment ranges and exact behaviors. | 3 / 3 |
Workflow Clarity | The 'How to act' section provides a clear sequence with explicit validation (check HTTP 429, back off exponentially, don't trust 200 OK for phantom segments). The session shutdown pattern provides a clear closing step with the (0,0,0) no-op workaround. Error recovery via exponential backoff is built into the code example. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections (device facts, API contract, executable example, behavioral rules, shutdown pattern). References to external files (scripts/govee_control.py, govee-h6056-gotchas rule, iot-actuator-patterns) are one level deep and clearly signaled in the 'Related' section. | 3 / 3 |
Total | 12 / 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