Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with copy-paste commands and code, and is reasonably concise and clearly sequenced. Its main weakness is progressive disclosure: several referenced reference files are absent from the bundle, so signaled pointers lead nowhere locally.
Suggestions
Add the referenced `references/` files (python-api.md, configuration.md, advanced-features.md, cli-reference.md) to the bundle, or remove the dangling pointers and inline the essential details.
Tighten the 'Field notes' section by removing fields already documented in the TOML config comments to reduce redundancy.
If references must live in a sibling skill, state that explicitly at each pointer (e.g. 'in the sibling xberg skill') so navigation expectations are clear — currently only some pointers note this.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with concrete commands and no over-explanation of basic concepts, but the 'Field notes' section re-explains fields already commented inline in the TOML block, a minor trimmable redundancy. | 4 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands (extract, embed, cache warm), a complete TOML config block, a provider flag table, and a working Python example covering the common cases. | 5 / 5 |
Workflow Clarity | Sequences are clear (e.g. `xberg extract | xberg embed` for document embeddings) and the 'Common pitfalls' section gives recovery guidance such as pre-warming cold models, though there are no explicit validation checkpoints since the operations are non-destructive. | 4 / 5 |
Progressive Disclosure | Sections are well-organized and references are explicitly signaled, but the referenced `references/*.md` files do not exist in the bundle (some are deferred to a sibling `xberg` skill), leaving navigation gaps for the reader. | 3 / 5 |
Total | 16 / 20 Passed |