Control Eight Sleep pods (status, temperature, alarms, schedules).
69
61%
Does it follow best practices?
Impact
83%
2.07xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/eightctl/SKILL.mdQuality
Discovery
50%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 concise and names a clear product niche (Eight Sleep pods) with specific actions, making it distinctive. However, it critically lacks a 'Use when...' clause, which hurts completeness and could make it harder for Claude to know when to select this skill. Adding natural user trigger terms like 'smart bed', 'bed temperature', or 'sleep schedule' would also improve discoverability.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks about their Eight Sleep pod, bed temperature, sleep schedule, or smart mattress settings.'
Include common user-facing synonyms and variations such as 'smart bed', 'bed cooling', 'bed heating', 'mattress temperature', or 'sleep tracking' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: status, temperature, alarms, and schedules. These are clear, distinct capabilities related to Eight Sleep pod control. | 3 / 3 |
Completeness | Describes what the skill does (control Eight Sleep pods) but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Eight Sleep pods', 'temperature', 'alarms', 'schedules', and 'status' which are relevant keywords. However, it misses common user variations like 'bed', 'mattress', 'sleep tracking', 'bed cooling/heating', or 'smart bed'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Eight Sleep pods' is a very specific product/brand niche. This is unlikely to conflict with other skills since the trigger is tied to a distinct smart home device. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured skill that efficiently covers the basics of the eightctl CLI tool. Its main weakness is incomplete actionability—while simple commands are clear, more complex operations (alarm creation, schedule management) lack argument formats or examples. The safety notes are present but could be better integrated into a workflow.
Suggestions
Add example arguments for complex commands like `eightctl alarm create` and `eightctl schedule create` (e.g., expected time formats, required parameters).
Document valid temperature range and what happens on auth failure or rate limiting (error recovery guidance).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Every line provides actionable information with zero unnecessary explanation. No padding or concept explanations Claude already knows. | 3 / 3 |
Actionability | Provides concrete CLI commands which are copy-paste ready, but lacks details on command arguments (e.g., what format does `alarm create` expect? What are valid temp ranges? What does `schedule create` need?). Key details for non-trivial commands are missing. | 2 / 3 |
Workflow Clarity | For a simple CLI tool this is mostly adequate, but the note about confirming before changing temperature/alarms is a safety constraint without a clear workflow around it. There's no validation or feedback loop for operations that could fail (e.g., auth failure, rate limiting recovery). | 2 / 3 |
Progressive Disclosure | For a simple, short skill under 50 lines with a single CLI tool, the content is well-organized into logical sections (auth, quick start, common tasks, notes) with clear navigation. No need for external references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
09cce3e
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.