dsh-plugin-conflict-checker
DeepSeek Harness plugin conflict checker: pre-flight duplicate-id detection and optional real startup smoke test.
165 results
DeepSeek Harness plugin conflict checker: pre-flight duplicate-id detection and optional real startup smoke test.
DSH plugin for AST context compression, test log filtering, and token budget guard
Settings-page DSH self-upgrade: check the running host against the npm registry, run `npm install -g @deepseek-ai/dsh@latest` on confirmation, and restart the host instance.
DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.
Checks GitHub for deepseek-harness updates, notifies in the conversation header, and can auto-download the latest source zipball. Adapts to the installed DeepSeek Harness desktop app.
Quant factor research pipeline: probe to panel to IC/5-gate to backtest to regime, with persistent project object + genui dashboards.
DeepSeek Harness plugin: Linux X11 computer-use tools (screenshot, mouse, keyboard) via a Python XTest helper
An API testing sidebar panel (Getman) for dsh-better-sidebar: method/URL, params, headers, raw body, response viewer, shared history — with a host-side proxy that bypasses CORS.
一个用于MBTI人格测试的MCP服务器,支持AI助手引导用户完成人格测试并给出结果分析。
Offline DSSE/in-toto attestation evidence for DeepSeek Harness releases
Model availability tester panel in the Models settings page: one-click real streaming test per added model with TPS / first-token / elapsed metrics
DeepSeek Harness bundle for the BurpSuite MCP Bridge
Zero-dependency static + sandbox smoke detector for DeepSeek Harness (dsh) plugins: package-structure gates (R), cordis contract scans (K), keyless-headless sandbox smoke (D), and ecosystem-listing checks (CC).
DSH plugin: unified MCP, Skills, AGENTS.md presets, archived-session and scene-memory manager — Settings UI + HTTP API + model-facing skill_mcp_manager_* / skill_manager_* / rule_manager_* tools. Install with one command: dsh plugin --profile web add dsh-plugin-tool-management@latest
并行多角色代码评审小队:/review 一条命令派出安全/正确性/测试/风格四名只读评审员子代理(每人可单独指定模型与思考强度),汇总为按严重度分组的结构化报告。Parallel multi-role code review squad: /review dispatches security/correctness/tests/style reviewer subagents (each on its own model) and aggregates one severity-grouped report.
Evidence-backed test plans and reviewable test drafts for DeepSeek Harness.
Browser Ops for DeepSeek Harness: let the agent drive a real browser (managed Chrome or your daily Chrome over CDP), snapshot/read pages, record manual operations into reusable flows with variable slots, and replay flows to create test data on demand.
Live subagent progress dock for DeepSeek Harness: folds each child session's events into a subagentProgress projection (turn/step, last tool, latest assistant preview, notify_user updates) and renders a frosted-glass status dock above the parent conversation composer.
Multi-Agent collaborative skill forging system for DeepSeek Harness — distill conversational experience into verifiable, reusable skills with evolutionary optimization.
DSH++ — a local-first control plane for DeepSeek Harness. Plugin security auditing and workflow regression testing for dsh, in a CLI plus a loopback web console.
DeepSeek Harness (dsh) plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, test engineer, code engineer, QA, code reviewer, security reviewer, doc reviewer) that talk through files on disk, with the PM as the