dsh-eval-harness
DSH 插件回归评测门禁:yaml 用例 + headless 驱动 + trace 断言 + baseline 门禁(eval_run / eval_gate)
19 results
DSH 插件回归评测门禁:yaml 用例 + headless 驱动 + trace 断言 + baseline 门禁(eval_run / eval_gate)
ECC (227k-star operator system) skills for DeepSeek Harness — progressive port of 274 curated single-file skills (agentic engineering, evaluation, testing, patterns, vertical domains, docs). Adapted from affaan-m/ECC (MIT)
Automated unit-test generation for DeepSeek Harness: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass.
Read-only recovery drill evidence for DeepSeek Harness
接口测试生成:解析 OpenAPI 3.x,为每个接口生成覆盖成功/缺参/非法枚举的测试用例,输出 Python(pytest) 或 TypeScript(vitest) 测试骨架
测试驱动开发:先写失败测试再写实现,Prove-It 模式,测试即证明。受 addyosmani/agent-skills(88k★ MIT)启发。
Grafana k6 load-testing integration for DeepSeek Harness: write, run and analyze performance test scripts.
DeepSeek Harness 叶子工具正文边界的确定性录制、完整性校验与离线回放插件
DeepSeek Harness skill bundle: function-testing (loads SKILL.md).
Content-addressed conformance proof across recorded DSH ToolRuntime, MCP JSON-RPC and CLI JSON surfaces
DSH plugin: structured test runner tool (test_run) — auto-detect vitest/jest/pytest/node:test, run tests, parse failure summaries for the model.
DSH 测试稳定性插件:flaky_detect/history/quarantine/clear/report 五工具,支持 vitest/jest/pytest/node:test,重复运行测试并识别不稳定用例,JUnit/TAP 完整解析,JSON 历史与隔离清单,零运行时依赖。
Deterministic, CI-safe golden-output evaluation for DeepSeek Harness
Electron 应用端到端测试:通过 Chrome DevTools Protocol(CDP)连接真实 Electron 渲染器——DOM 检查/JS 求值/点击/截图、DPR 乘数、右键事件真实触发、xterm 布局延迟等坑。受 bholmesdev/hubble.md(test-desktop-app)启发。
DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.
Paired experiments and promotion gates for DSH plugins.
Deterministic evidence for DSH schema migration fixtures
Run one command N rounds and judge by median/distribution instead of a single run
Record MCP once. Replay it safely inside DeepSeek Harness.