Content
17%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 skill reads as a persona/competency catalog rather than actionable guidance: it enumerates Django topics Claude already knows without executable examples, concrete workflows, or working references. Its only external reference points to a nonexistent file.
Suggestions
Replace the capability/topic catalog with concrete, copy-paste-ready guidance: example model/query code, async view snippets, and a real DRF/Celery/Channels setup pattern.
Make the single reference real by creating `resources/implementation-playbook.md`, or remove the dangling reference; split the bulky capability list into that reference file.
Add an explicit workflow with validation checkpoints (e.g., run migrations -> run `pytest` -> verify) instead of the abstract Response Approach steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a ~170-line catalog of capabilities, behavioral traits, and a knowledge base that largely restates Django domain knowledge Claude already has, and the persona ("Django expert") is restated across the Purpose section. | 2 / 5 |
Actionability | There is no executable code, no concrete commands, and no specific examples; guidance like "Apply relevant best practices and validate outcomes" only describes rather than instructs, and the lone reference target does not exist. | 1 / 5 |
Workflow Clarity | The 8-step "Response Approach" gives a rough abstract sequence but defines steps poorly and includes no validation checkpoints or feedback loops for risky operations like migrations or batch tasks. | 2 / 5 |
Progressive Disclosure | A large capability catalog is inlined monolithically rather than split into reference files, and the single referenced file (`resources/implementation-playbook.md`) does not exist, leaving a broken, dangling reference. | 2 / 5 |
Total | 7 / 20 Passed |