Content
46%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 has a sound file structure (real script, real one-level reference) but is dominated by generic templated filler that says nothing specific about bioDBnet. It also contains a broken cross-reference and a fabricated 'expected output' block, and lacks any fully worked API-call example. It needs substantial trimming plus one concrete end-to-end example to reach good quality.
Suggestions
Remove the generic template sections (When to Use, Key Features, Implementation Details, Output Contract, Failure Handling, Validation and Safety Rules) or collapse them into a few lines; roughly two-thirds of the body teaches nothing about bioDBnet specifically.
Add one complete, copy-paste-ready example with real values, e.g. `python scripts/biodbnet_client.py --method db2db --params '{"input": "genesymbol", "outputs": "affy", "values": "TP53"}'` plus its expected response format.
Fix the incorrect navigation and fabricated expectations: 'See ## Usage above' points to a section that appears below, and the 'Expected output format' block describes result-file output that `--help` would never produce — replace it with the actual argparse help text.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Large portions are generic template boilerplate that Claude already knows — 'Use this skill when the request matches its documented task boundary', 'Scope-focused workflow aligned to: ...', 'Output discipline: keep results reproducible', and the redundant When to Use / Required Inputs / Recommended Workflow / Validation and Safety Rules / Output Contract / Failure Handling sections, none of which teaches anything specific to bioDBnet. This matches anchor 2 ('noticeably verbose; several unnecessary explanations or padded sections') rather than 3, where padding would be limited to 'some' unnecessary explanation. | 2 / 5 |
Actionability | There are real commands ('python scripts/biodbnet_client.py --method <method_name> --params <json_params>' and '--help') and a valid pointer to references/api_methods.md, but the method and params remain placeholders — no worked example with actual values (e.g., a concrete db2db call converting a gene symbol), no sample params JSON, and no sample response. This matches anchor 3 ('some concrete guidance but incomplete ... missing key details') rather than 4, which requires mostly executable, copy-paste-ready guidance. | 3 / 5 |
Workflow Clarity | Sequences exist (Recommended Workflow steps 1-4, the example run plan, Quick Validation), but they are triplicated and generic, the 'Example Usage' section says 'See ## Usage above' while the Usage section actually appears below it, and the 'Expected output format' block fabricates output ('Result file: biodbnet_api_result.md ... Validation summary: PASS/FAIL') that running the script with --help would not produce. This fits anchor 3 (steps listed but incoherent checkpoints/navigation gaps) rather than 4, where the sequence and checkpoints would be coherent. | 3 / 5 |
Progressive Disclosure | The body appropriately delegates the API method catalog to a real one-level-deep reference ('See references/api_methods.md for a complete list of supported methods and their parameters') and the executable surface to scripts/biodbnet_client.py, both of which exist in the bundle. It matches anchor 4 (good structure, references mostly clear, minor organization gaps) rather than 5 because navigation is weakened by the incorrect 'above' cross-reference and boilerplate sections that bury the genuinely useful Usage/Commands content. | 4 / 5 |
Total | 12 / 20 Passed |