jig

When the user wants to codify a repeatable code generation pattern into a jig recipe — design variables, choose operations (create/inject/patch/replace), write Jinja templates, and validate the result. Use when someone says "I keep writing this same boilerplate", "make a recipe for X", or wants to turn a manual edit into an automated pattern.

When the user needs to chain multiple jig recipes into a multi-step workflow with conditional execution and shared variables. Use when a pattern spans multiple files that need coordinated creation and modification, like scaffolding an entire endpoint or a full feature slice.

Scaffold queryset/manager/selector layers and wire view reads through selector entrypoints with jig.

Generate two-step rollout-safe Django migrations plus model-field patching using jig.

Insert consistent method/step structured logging lines into target functions using jig.

Write deterministic service tests with stable fixtures and boundary mocks without using jig.

Keep reads in selectors/querysets and keep write logic in services without using jig.

Plan and apply backwards-compatible two-step schema changes for Django migrations without using jig.

Apply a stable method/step structured logging contract without using jig.

Enforce request-validation, permission, service-handoff, and response-contract boundaries in views without using jig.

Generate deterministic pytest service tests with stable inputs and autospec-boundary mocks using jig.

Scaffold request/response contracts, view function wiring, URL route, and test updates with jig.

Create a test file for a service or class. Use when scaffolding tests, adding test coverage, or creating test files.

Systematic DX improvement hunt — find friction, inconsistency, and missing abstractions across PRs, code, or tickets, then feed findings into /improve. Use when looking for ways to accelerate development or compound Claude Code's utility.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Find the right jig recipe before writing code. Use whenever you need to create a file, add a field, scaffold a test, add an endpoint, or generate any boilerplate. Always run this before hand-writing code.

A test skill for the eval harness test fixtures.

Add a new REST API endpoint with view, URL route, schema, and test. Use when adding endpoints, routes, or API paths.

Add a new field to a Django model and propagate to admin, serializer, and factory. Use when adding model fields or database columns.

Add a new API view function or endpoint to a Django views.py file. Use when adding views, endpoints, or API routes.

Create a new Django model in a module. Use when adding models, database tables, or data classes.

Add a new serializer class to serializers.py. Use when adding serializers or API data schemas.

Add a new API view function to a Django views.py file. Use when adding views or API handlers.

Audit installed skills and agents against best practices. Use when reviewing skill quality, checking for common problems, or before upgrading existing skills. Read-only — produces a report, changes nothing.

Recreate the current branch with a clean, narrative commit history. Use before creating a PR from a messy development branch, after exploratory coding with WIP commits, or when commit history is hard to review.

Deliberately improve Claude Code by creating or updating skills, agents, hooks, rules, or MCP servers. Use when Claude keeps making the same mistake, a workflow is tedious, a new pattern needs enforcement, or you want to compound Claude's utility.

Upgrade an existing skill or agent by auditing it, gathering user references, and rewriting it with real content. Use when a skill is thin, sloppy, missing gotchas, or needs improvement. Different from /improve which creates new extensions.