Design Django ORM models for Sentry following architectural conventions for silos, replication, relocation, and foreign keys. Use when adding a new Django model, designing a model for a feature, deciding where data should live, picking a foreign key type, or refactoring an existing model's silo placement. Trigger on "add a Django model", "create a model", "design a model for X", "new database table", "store this data in the DB", "I need to track Y", "model for [feature]". Not for Pydantic models, dataclasses, ML models, or Protobuf — this is specifically for Django ORM models in the Sentry codebase.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive natural trigger terms, explicit 'Use when' and 'Not for' clauses, and clear scoping to avoid conflicts with other skills. The explicit exclusion list is a particularly strong touch that reduces ambiguity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: designing Django ORM models, handling silos, replication, relocation, foreign key type selection, and refactoring silo placement. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (design Django ORM models following Sentry architectural conventions for silos, replication, relocation, and foreign keys) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios, plus explicit exclusions for what it's NOT for). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'add a Django model', 'create a model', 'new database table', 'store this data in the DB', 'I need to track Y', and 'model for [feature]'. These are phrases users would naturally say, covering both technical and casual variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to Django ORM models in the Sentry codebase, with explicit exclusions for Pydantic models, dataclasses, ML models, and Protobuf. This makes it very unlikely to conflict with other model-related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that captures genuinely non-obvious Sentry-specific architectural decisions. It provides excellent actionability with a complete code skeleton and clear decision framework, and delegates appropriately to companion skills. Minor verbosity in some explanatory sections (soft delete, constraints, field-type intent) could be trimmed without losing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and covers genuinely non-obvious Sentry-specific conventions, but some sections are slightly verbose — e.g., the soft delete and constraints sections explain Django concepts Claude likely knows, and phrases like 'The wrong way to think about it' add editorial weight without actionable value. Overall it respects Claude's intelligence but could be tightened by ~20%. | 2 / 3 |
Actionability | The skill provides a complete, executable model skeleton with correct imports, concrete field examples (FlexibleForeignKey vs HybridCloudForeignKey with exact syntax), a decision table for relocation scopes, and specific file path conventions. The guidance is copy-paste ready and leaves no ambiguity about what to write. | 3 / 3 |
Workflow Clarity | The skill clearly sequences the four design decisions that must be made before writing fields, explains their coupling, and provides an explicit post-design checklist (generate migration, wire outboxes, update exports). The 'After the model is designed' section acts as a validation checkpoint ensuring downstream steps aren't skipped. | 3 / 3 |
Progressive Disclosure | The skill cleanly delegates to three other skills (generate-migration, hybrid-cloud-outboxes, hybrid-cloud-rpc) at the top and bottom, keeping the body focused on model design decisions. References are one level deep, clearly signaled, and contextually placed. For a standalone skill with no bundle files, the structure is well-organized with logical sections. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
552fb5c
Table of Contents
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.