crate-structure

The Xberg workspace layout — the version source of truth (root Cargo.toml [workspace.package] version), the 19 workspace members and 3 excluded crates, the distribution packages under packages/, the tools/ directory, and the ignore-file allowlists a new workspace member must be added to. Load when navigating the repo, deciding where code belongs, or wiring a new crate or binding package.

Quality

92%

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

96%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.

An excellent, dense reference skill: all content is non-inferable repo-specific knowledge, the add-member workflow is fully executable with explicit validation and failure-mode documentation, and it even covers the reverse (deletion) case. The only structural nit is that the detailed per-crate annotations keep it slightly above simple-skill size where a split-out reference file might help.

Dimension	Reasoning	Score
Conciseness	Every line is repo-specific knowledge Claude cannot infer (opaque crate aliasing, 'ffi_style = "panama"', the LOG_TARGET_ROOT constant rule, the .dockerignore/.gitignore allowlist mechanics); no concept Claude already knows is explained and there is no padding. Matches the lean anchor 5; not 4, since nothing is trimmable.	5 / 5
Actionability	Fully concrete, copy-paste-ready guidance: exact directives ('add `!crates/<name>/`', 'add `!crates/<name>/src/vendor/`'), the exact verification command ('Run `task verify:docker-crates`'), the literal failure message ('failed to compute cache key: "/crates/<name>": not found'), and exact config keys. Matches the fully-executable anchor 5.	5 / 5
Workflow Clarity	The 'Adding a workspace member' section is a numbered 4-step sequence with an explicit validation checkpoint that states what it checks 'in both directions' (including stale allowlist entries after deletion) and honestly flags its limitation ('It does not look at `.gitignore`; verify that by hand'). Validation is present, so the destructive/batch cap does not apply; matches anchor 5 with a genuine validate-and-catch-errors loop.	5 / 5
Progressive Disclosure	Well-organized sections with clear headers and a one-level pointer to the sibling 'alef-generated-bindings' skill, but at roughly 65 lines of dense per-crate annotations it exceeds the 'under 50 lines' simple-skill threshold, and the member list is borderline reference material that could live in a separate file. Fits anchor 4 (good structure, minor organization gaps) rather than 5.	4 / 5
	Total	19 / 20 Passed

Description

88%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 description: it comprehensively enumerates the skill's concrete contents and provides an explicit, scenario-based 'Load when' trigger clause. The only weaknesses are a couple of missing natural trigger variants and the slightly broad 'navigating the repo' phrasing that creates minor overlap risk with adjacent repo skills.

Dimension	Reasoning	Score
Specificity	Enumerates concrete, checkable facts — 'the version source of truth (root Cargo.toml [workspace.package] version)', 'the 19 workspace members and 3 excluded crates', 'the distribution packages under packages/', 'the tools/ directory', and 'the ignore-file allowlists a new workspace member must be added to' — with no vague filler; coverage spans every section of the skill body. Anchor 5 rather than 4 because coverage is comprehensive, not 'several items with minor gaps'.	5 / 5
Completeness	Explicitly answers both: what ('The Xberg workspace layout — the version source of truth... the ignore-file allowlists') and when ('Load when navigating the repo, deciding where code belongs, or wiring a new crate or binding package') with three concrete trigger scenarios. Matches the anchor-5 example pattern; not 4, since the 'when' clause is explicit and specific rather than weakly stated.	5 / 5
Trigger Term Quality	'Load when navigating the repo, deciding where code belongs, or wiring a new crate or binding package' plus terms like 'workspace layout' and 'Cargo.toml' are natural phrasings users would say. A few natural variants are missing (e.g., 'where does X live', 'add a workspace member', 'which crate'), so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	A clearly repo-specific niche ('The Xberg workspace layout') with distinctive triggers like 'wiring a new crate or binding package', but 'navigating the repo' is somewhat broad and a sibling skill ('alef-generated-bindings') is explicitly referenced as sharing adjacent territory — minor overlap risk, fitting anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xberg-io/xberg
Path: .ai-rulez/skills/crate-structure/SKILL.md
Commit: fbf07e1

Reviewed: 12 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.