crabbox

Use the Crabbox wrapper for validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/crabbox/SKILL.md

Quality

Content

77%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 content is highly actionable with strong workflow sequencing and validation checkpoints, but it is a long monolith that inlines reference-style material and repeats the provider-selection policy across many sections.

Suggestions

Move the provider-specific command catalogs (Direct Brokered AWS, Blacksmith Testbox, Brokered AWS), the Observability Flags reference, and the Diagnostics command list into one-level-deep reference files (e.g., references/aws.md, references/testbox.md, references/flags.md) and link to them from SKILL.md.

Consolidate the repeated provider-override policy into the 'Provider Selection Contract' section and reference it once from later sections instead of restating it seven times.

Tighten or relocate the duplicated Blacksmith footguns (they appear in both 'If Crabbox Fails' and 'Blacksmith Backend Notes').

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable commands and avoids explaining basics Claude already knows, but the provider-override policy ('omit --provider', 'preserve the resolved provider', 'override only when the user explicitly names a backend') is restated across roughly seven sections, which is unnecessary padding that could be consolidated.	3 / 5
Actionability	Fully executable, copy-paste-ready shell blocks with complete flags cover local-container, AWS, Blacksmith Testbox, SSH, desktop/WebVNC, and diagnostics, with appropriately parameterized placeholders for the common cases.	5 / 5
Workflow Clarity	Multi-step flows are explicitly sequenced (e.g., the 5-step 'Efficient flow', 'If Crabbox Fails' triage) with explicit validation/verify checkpoints, feedback loops (retry once with --debug, rerun only the failing shard), and checklists; batch/destructive lease operations include validation, so no cap applies.	5 / 5
Progressive Disclosure	The file has clear section headers, but it is an 855-line monolith with no bundle files and zero references to separate files; reference-style catalogs (observability flags, diagnostics, provider-specific sections) are inlined rather than split into one-level-deep reference files.	3 / 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 clearly states what the skill does and occupies a distinct, low-conflict niche, but it lacks an explicit 'when to use' trigger clause and leans on specialized jargon over natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when the user asks to run validation/tests in Crabbox or via Blacksmith Testbox').

Soften jargon with common synonyms users actually say (e.g., 'run tests remotely', 'CI proof') alongside the product names.

The missing trigger guidance currently caps completeness at 3; adding it would lift both completeness and trigger_term_quality.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions — 'validation across Linux, macOS, Windows, and WSL2', 'delegated Blacksmith Testbox proof', 'Report the actual provider and id' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	The 'what' is clear ('Use the Crabbox wrapper for validation... Report the actual provider and id') but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist (Crabbox, Blacksmith Testbox, the platform names) but they are specialized product jargon rather than natural user phrases, and common variations/synonyms a user would actually say are missing.	3 / 5
Distinctiveness Conflict Risk	Distinct product-named niche (Crabbox wrapper, Blacksmith Testbox, specific provider/id reporting) gives clear triggers with minimal overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (860 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: openclaw/clawsweeper
Path: .agents/skills/crabbox/SKILL.md
Commit: 02c930c

Reviewed: about 13 hours 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.