Khufu

English | 简体中文

A test generation skill framework for AI IDEs, following the test pyramid methodology with Evaluation-Driven Development (EDD) and Specification-Driven Development (SDD).

Khufu provides nine skills — /khufu-doc-prd, /khufu-doc-api, /khufu-doc-adr, /khufu-doc-testcase, /khufu-harness, /khufu-test-unit, /khufu-test-integration, /khufu-test-api, and /khufu-test-e2e — that leverage AI agents to generate MVP PRDs, REST API contracts, architecture decision records, test-case documents, project constraint assets (Harness Engineering), unit tests, integration tests, API tests, and end-to-end tests.

Features

• Test Pyramid: Complete coverage across all four test layers with built-in deduplication — higher layers only test what lower layers structurally cannot
• Evaluation-Driven Development (EDD): Define quantifiable quality criteria (coverage, performance, correctness) BEFORE generating tests. Every test serves a measurable evaluation standard. Built-in Evaluate → Verify → Improve feedback loop
• Specification-Driven Development (SDD): Test cases are explicit, versioned Markdown spec files (specs/<feature>/spec.v<N>.md). Supports forward generation (Spec → Tests) and reverse generation (Tests → Spec). Each test links back to its spec entry
• Generation paths:
  • Spec-based: Generate tests from specification documents (/khufu-test-unit @docs/spec.md)
  • Code-based: Generate tests by reading existing implementations (auto-generates retroactive specs)
  • Both together (API and E2E): when a test case and the implementation are both present, the call target comes from the real route or page, and the assertion comes from the test case
• Language-Aware: Auto-detects your project language and suggests appropriate test frameworks
• Testability Assessment (UT): Grades source files A/B/C — directly testable, needs PowerMock (marked fragile), or requires refactoring (recorded to untestable-report.md)
• H2 Database Support (IT): Lightweight in-memory database option for Java integration tests — zero Docker dependency, <5s startup for fast CI feedback
• Shared Test Data Factories: Define test data once, reuse across IT, API, and E2E layers
• TDD-Aligned: Tests follow Test-Driven Development and Agile best practices
• Requirement to PRD: /khufu-doc-prd grills a requirement description, splits it into MVPs, and writes a PRD set under docs/prd/. Project goals, scope, and the glossary live in prd-catalog.md, which also links every document; Cockburn fully dressed use cases live in prd-mvp1.md, prd-mvp2.md, …; non-functional requirements live in prd-quality.md
• PRD to test cases: /khufu-doc-testcase writes one document per PRD under docs/test-cases/ (test-cases-prd-mvp1.md, …), with one case per main flow, alternate flow, and independently asserted business rule. A script classifies only the words after the command. With no PRD path, the skill asks in the reply and does not scan or write. After you choose to scan, it lists the files and asks again before generating. prd-catalog.md is an index, not an input
• PRD quality attributes to ADRs: /khufu-doc-adr reads prd-quality.md and the ADR template, analyzes each decision against the template's elements (context, drivers, options, pros and cons, consequences, confirmation), asks one decision question at a time as selectable options with a recommended choice plus a user-provided solution (a numbered plain-text fallback is used when the host has no structured question tool), and records each confirmed technology selection or architecture decision as its own ADR. It writes into the khufu-harness ADR directory when constraint assets exist, otherwise into docs/architecture/adr/, and maintains an index that links every ADR
• PRD use cases to API contracts: /khufu-doc-api reads the Cockburn use cases and prd-quality.md, draws the client/backend boundary, and turns every call point into a RESTful contract. It writes docs/design/api-catalog.md and docs/design/api-contracts.md with request/response/error schemas, an embedded OpenAPI 3.0.3 document, a per-API SLA, acceptance criteria, and testability notes. The output is usable both as an implementation contract and as input for API test generation
• Oracle binding (API and E2E): a bound test calls the real entry and asserts the test case, even if that fails against the current implementation. A case with no unique match is not generated; it is listed in docs/khufu/api/oracle-mismatch.md or docs/khufu/e2e/oracle-mismatch.md
• Multi-IDE Support: Installs into Claude Code, Cursor, OpenCode, Codex, Qoder, and Trae — each tool gets its skills placed using that tool's own skill/command directory convention

Quick Start

# Install globally
npm install -g khufu-kit

# Initialize in your project. The tool list has nothing pre-selected.
cd your-project
khufu init

# Check for a newer version on npm and update if available
khufu update

# Use the skills in your IDE (e.g. Claude Code)
/khufu-doc-prd                # Grill a requirement into MVP PRDs
/khufu-doc-api                # Turn PRD use cases into REST API contracts
/khufu-doc-adr                # Turn PRD quality attributes into ADRs
/khufu-doc-testcase @docs/prd/prd-mvp1.md   # Turn that PRD into test cases
/khufu-harness                # Build / update project constraint assets
/khufu-test-unit              # Generate unit tests
/khufu-test-integration       # Generate integration tests
/khufu-test-api               # Generate API tests
/khufu-test-e2e               # Generate E2E tests

Skill names changed

The skills were renamed so the command states what it produces: doc-* writes a document, test-* generates test code. The old names are not kept as aliases. After upgrading, reinstall and let the installer remove the old skill directories:

This is the beginning of the README. Read the rest at the original. Read the full README ↗