CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

django-models

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.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Dense, high-signal, project-specific conventions with an executable skeleton and a clear decision-first workflow; almost nothing re-teaches what Claude already knows. Minor room to trim generic Postgres rationale and to split the field-norms detail into a reference file.

DimensionReasoningScore

Conciseness

Largely lean — it defers Django syntax, migrations, and outbox plumbing to other skills and assumes competence — but a few asides could be trimmed, e.g. the generic Postgres varchar/TOAST storage explanation justifying the max_length=256 guidance. Efficient but not quite "every token earns its place".

4 / 5

Actionability

A fully executable, copy-paste-ready skeleton with real imports and concrete conventions throughout: exact decorators and base classes (@cell_silo_model, DefaultFieldsModel, ReplicatedCellModel), a relocation-scope decision table, explicit FK typing rules with on_delete string values, and precise file paths.

5 / 5

Workflow Clarity

A clear ordered sequence — "decide all four" coupled decisions before writing fields, then a skeleton, then numbered post-design steps that route to sibling skills — with the runtime __relocation_scope__ check noted as a guard. It lacks an explicit validate-the-design checkpoint or feedback loop, so it does not reach the 5 anchor.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep pointers to sibling skills (generate-migration, hybrid-cloud-outboxes, hybrid-cloud-rpc). However, the ~124-line body keeps convention detail inline that could be split into a reference file, so content is not "appropriately split" at the 5 anchor.

4 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: concrete capabilities, explicit when-to-use triggers in natural language, and a sharp negative-scope clause that disambiguates it from adjacent skills. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "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" — covering the skill's scope comprehensively with no evident gaps.

5 / 5

Completeness

It explicitly answers both what ("Design Django ORM models for Sentry following architectural conventions for silos, replication, relocation, and foreign keys") and when, via a concrete "Use when..." clause listing five trigger scenarios.

5 / 5

Trigger Term Quality

Trigger phrases are natural user phrasings with good synonym coverage: "add a Django model", "create a model", "new database table", "store this data in the DB", "I need to track Y", "model for [feature]" — the kind of language a user would actually say.

5 / 5

Distinctiveness Conflict Risk

A clear niche (Django ORM models in the Sentry codebase) reinforced by an explicit exclusion clause — "Not for Pydantic models, dataclasses, ML models, or Protobuf" — keeping conflict risk with similar-sounding skills minimal.

5 / 5

Total

20

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

getsentry/sentry

Path

.agents/skills/django-models/SKILL.md

Reviewed

Table of Contents

Is this your skill?

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.