crabbox

Detect and use Crabbox for repository tests and validation on remote runners. Use when crabbox.yaml or .crabbox.yaml exists, the crabbox CLI is available, or work needs remote compute, a clean or reusable environment, target-platform coverage, or auditable execution evidence.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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.

Highly actionable, executable CLI guidance with strong sequenced workflows and validation checkpoints. The main weakness is progressive disclosure: a large monolithic file with no bundle references inlining content that belongs in separate files.

Suggestions

Move the 'Useful Commands' reference and the Desktop/WebVNC/UI-Proof detail into separate reference files (e.g. references/commands.md, references/desktop-ui.md) and link to them from the body to reduce inline bulk.

Split provider-boundary and Hyper-V/Windows detail into a references/providers.md file, keeping only the decision-level guidance inline.

De-duplicate commands that appear in both the topical sections and 'Useful Commands' to tighten the conciseness score.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, assuming Claude's competence without explaining basics, but the 'Useful Commands' section re-lists commands already shown and the overall length could be trimmed in places.	4 / 5
Actionability	It provides abundant copy-paste-ready commands with concrete flags covering common cases across run, warmup, sync, secrets, desktop, and observability, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Workflows like warmup→status→run→stop and auth are clearly sequenced with validation checkpoints (doctor, preflight, sync-plan, require-artifact) plus a Failure Triage feedback loop, though some sections read as command lists rather than explicit checkpointed sequences.	4 / 5
Progressive Disclosure	No bundle files exist and the ~500-line body inlines command-reference, provider-boundary, and desktop/UI content that would benefit from separate reference files; section headers provide structure but there are no one-level-deep references to split the content.	3 / 5
	Total	16 / 20 Passed

Description

83%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 strong, well-structured description that clearly answers both what the skill does and when to invoke it, with concrete file-extension and CLI trigger terms. Minor risk is overlap from generic remote-compute triggers and a few jargon-leaning phrases.

Dimension	Reasoning	Score
Specificity	"Detect and use Crabbox for repository tests and validation on remote runners" names the domain plus several concrete actions (detect, use, run tests, validate), fitting the 'several specific actions; minor gaps' anchor rather than the 1-2 actions of a 3.	4 / 5
Completeness	It explicitly states both what ("Detect and use Crabbox for repository tests and validation on remote runners") and when ("Use when crabbox.yaml or .crabbox.yaml exists, the crabbox CLI is available, or work needs remote compute...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when' clause covers crabbox.yaml/.crabbox.yaml, the crabbox CLI, remote compute, clean/reusable environment, target-platform coverage, and auditable evidence — good keyword coverage including file extensions, though a few terms lean technical rather than natural user speech.	4 / 5
Distinctiveness Conflict Risk	The named tool plus crabbox.yaml/CLI triggers give a clear niche, but the generic remote-compute/clean-environment triggers create minor overlap risk with general remote-runner or CI skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (501 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openclaw/crabbox
Path: skills/crabbox/SKILL.md
Commit: 8166af8

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.