eightctl

Control Eight Sleep pods (status, temperature, alarms, schedules).

2.07x

Quality

69%

Does it follow best practices?

Impact

83%

2.07x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/eightctl/SKILL.md

The canonical home for this skill is eightctl in openclaw/openclaw

Quality

Content

76%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 exemplary lean command reference: no filler, concrete commands with a real example value, and useful operational notes about rate limits and confirmation. Weaknesses are the absence of validation steps for state-changing operations and section headers that are not markdown headings, plus missing argument details for the create/update subcommands.

Suggestions

Add a verification step after state changes, e.g. run `eightctl status` to confirm the new temperature or alarm took effect.

Format section titles as markdown headings (## Auth, ## Quick start) so the structure is machine-parseable and easier to navigate.

Show required arguments for `alarm create` and `schedule update` (e.g. `eightctl alarm create <time>`), since those commands cannot be run as written.

Dimension	Reasoning	Score
Conciseness	The body is ~25 lines of pure commands and facts with zero padding or explanation of concepts Claude already knows — "Use `eightctl` for Eight Sleep pod control. Requires auth." followed immediately by config paths and commands. Every token earns its place, matching 'Lean and efficient; assumes Claude's competence'.	5 / 5
Actionability	Commands are concrete and mostly copy-paste ready ("eightctl temp 20", "eightctl alarm list\|create\|dismiss", "eightctl base info\|angle"), matching 'Mostly executable guidance; concrete code or commands with minor gaps'. Not a 5 because subcommand alternatives like `list\|create\|update` are not literal invocations and required arguments for `alarm create` / `schedule update` are not shown.	4 / 5
Workflow Clarity	The skill is presented as a flat command catalog with no sequencing, and operations that change device state ("eightctl temp 20", alarm create, "Confirm before changing temperature or alarms") lack verification steps. Per the guideline that destructive/impactful operations without validation cap workflow clarity at 3, this matches 'Steps listed but validation gaps; checkpoints missing or implicit' — the confirm-before note is a partial checkpoint but there is no verify-after step.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no external bundle files, organized into Auth / Quick start / Common tasks / Notes sections, so the simple-skill exception applies. However the section headers are plain text lines rather than markdown headings, a minor organization gap that keeps it at 'Good structure; most content is appropriately placed' rather than a 5.	4 / 5
	Total	16 / 20 Passed

Description

62%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 concise, specific, and highly distinctive thanks to the explicit Eight Sleep product name, and it clearly states what the skill does. Its main weakness is the complete absence of any 'when to use' trigger guidance and limited synonym coverage (no 'bed', 'mattress', or 'smart mattress' phrasing).

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions Eight Sleep, their Pod, bed temperature, or sleep settings.'

Include natural synonyms such as 'bed', 'mattress', or 'smart mattress' so the description matches how users actually refer to the device.

Consider mentioning additional capabilities (audio, base) if those are common requests, to round out coverage.

Dimension	Reasoning	Score
Specificity	"Control Eight Sleep pods (status, temperature, alarms, schedules)" names the domain and lists four concrete capability areas, matching the anchor 'Lists several specific actions; minor gaps in coverage'. It is not a 5 because coverage is incomplete relative to the tool itself (audio, base controls from the body are absent), and not a 3 because it lists several specific actions rather than just 1-2.	4 / 5
Completeness	The 'what' is clearly answered ("Control Eight Sleep pods (status, temperature, alarms, schedules)") but there is no 'when' — no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3 ('Has a clear what but when is missing or only weakly implied').	3 / 5
Trigger Term Quality	Relevant keywords are present ("Eight Sleep", "pods", "status", "temperature", "alarms", "schedules"), but common variations users would naturally say — "bed", "mattress", "smart mattress", "sleep tracker" — are missing, matching 'Some relevant keywords but missing common variations or synonyms'. It exceeds 2 because the core product terms are included, but falls short of 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	"Eight Sleep pods" is a clear niche with distinct product-specific triggers; virtually no other skill would match this description, matching the anchor 'Clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	15 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 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	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/eightctl/SKILL.md
Commit: 9bb1c42

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.