Content
88%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 content is a strong, highly actionable skill with clear sequencing, validation checkpoints, and good reference split. Its only notable gap is conciseness/structure: version-migration detail and some dense reference tables are inlined rather than pushed to a reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense with executable code and avoids explaining concepts Claude already knows (no 'what is a graph algorithm' padding), but inline version pins (1.22, <2) and a large in-body 2.0-alpha rename map add tokens that read more like reference material than overview. | 4 / 5 |
Actionability | It provides copy-paste-ready executable code across auth, memory estimation, three session modes, four projection modes, mutate/stream/write algorithms, async polling, results retrieval, write-back, and cleanup — covering the common cases fully. | 5 / 5 |
Workflow Clarity | Steps 1–8 are clearly sequenced with explicit validation checkpoints (verify_session_connectivity, verify_db_connectivity, poll job until RUNNING_DONE, 'Write before delete'), plus a Common Errors fix table and a Checklist — appropriate feedback loops for this billed/destructive-context skill. | 5 / 5 |
Progressive Disclosure | It is a well-organized overview with two clearly signaled one-level-deep references (references/workflows.md, references/limitations.md) that both exist, but the sizable in-body 2.0 rename table and Cypher API blocks are reference-grade material that could be split out. | 4 / 5 |
Total | 18 / 20 Passed |