AI Agent Workflow Collection

Run SweetClaude's behavioral regression test suite.

Show the full project at a glance — roadmap pipeline with milestones, epics, and issues. Trigger on: 'big picture', 'whole project status', 'full status', 'what's the full state', 'project overview', 'where is everything', 'show me everything'.

Redirects to sweetclaude:doctor. Config compatibility checks are now part of the doctor system.

Internal TDD process skill — invoked by code-feature, code-issue, and code-debt.

Generate and run unit and integration tests using pytest (Python) or Jest (JavaScript) with fixtures, mocks, and async support. Use for test-driven development, code review validation, coverage verification, and regression testing. Target 80%+ code coverage. Supports pytest markers, Jest snapshots, and CI/CD integration. Triggers on "test", "TDD", "unit test", "integration test", "test coverage", "pytest", "jest".

Run verification before claiming work is complete.

Scan source directories, deduplicate files, copy unique files into corpus/raw/inbox/.

Rebuild RAG collections from source files.

Configure and run local semantic search on project documents using mcp-local-rag.

Take staged files and work with the user to produce approved canonical documents in corpus/working/.

Show the current state of the document corpus pipeline — file counts in each stage, last-run timestamps per step, and recommended next action.

Classify files in corpus/raw/inbox/ as keep-as-is, needs-reconciliation, discard, or defer.

Design API endpoints: routes, request/response shapes, authentication, pagination, error responses, and versioning strategy.

Define system architecture — components, boundaries, communication patterns, data flow, and compliance requirements.

Ripple-effect analysis for changes to EXISTING code or specs — trace what is affected across code, tests, docs, APIs, and specs.

Design the data model: entities, relationships, constraints, indexes, and migration strategy.

Record and track design and architecture decisions with context, options considered, decision made, and rationale.

Validate the proposed solution before implementation.

Technical specification — every decision a developer needs before writing the first line of code.

Convert user stories into UX/UI flows — step-by-step paths through the interface.

Manage the full document corpus pipeline — consolidate raw files, triage, reconcile into canonical documents, promote, set up semantic search (RAG), and reindex.

Academic paper development — from first principles through submission.

Build and query a knowledge graph connecting strategic claims, proof points, objectives, and supporting/opposing evidence.

Update documentation when implementation changes behavior.