Design, review, and diagnose DeepSeek Harness tests and fixtures that can fail nondeterministically under CI concurrency, shared host resources, clocks, process-global state, subprocesses, network listeners, or asynchronous teardown. Use when adding or changing tests with those risks, investigating flaky CI, or reviewing test isolation; use dsh-pre-push-checks separately to select outgoing commands.
WHAT YOU GET
Files, tags and the three-step install
Tip: Read the documentation and the code before first use, so you know what it does and which permissions it needs.
NEXT SCRIPTS
Recommended based on tags and category
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. Use when designing or reviewing REST endpoints, resource names, status codes, pagination, or versioning.
A built-in API automation authoring skill for the test-automation project, located at `.claude/skills/api-test-E10/`. It is used to add, maintain, backfill, and migrate API test methods and pytest cases under `\test-automation\E10自动化\接口自动化测试`, covering scenarios such as adding new methods or cases, backfilling uncovered APIs based on Java Controller source or Jacoco reports, maintaining existing methods and cases, completing parameterization, fixing assertions, inserting code at specified locations, finding duplicate implementations by URL, handling UTF-8 Chinese encoding, and running pytest with iterative real-error fixing until pass. Runtime artifacts are placed in the project root under `api_test_dwp_temp/`.
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.