Plugins

Deterministic DeepSeek Harness Web client plugin that explains the Windows-sandbox `spawn EPERM` failure as a distinct Conversation Node.

Rate-limit plugin for DeepSeek Harness: FIFO queue per provider/model bucket with minIntervalMs and maxConcurrent

怀疑驱动开发：每个非平凡决策在落地前接受新鲜上下文的对抗性审查（CLAIM→EXTRACT→DOUBT→RECONCILE→STOP）。受 addyosmani/agent-skills（88k★ MIT）启发。

中文 PPT 生成技能：结构化大纲 → 视觉设计 → HTML/PPTX 出稿，附排版自查清单。原创技能（参考 GordenPPTSkill / ppt-master 思路）。

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

领域建模：主动构建并打磨项目的领域模型（CONTEXT.md 术语表 + ADR 决策记录），挑战模糊术语、推敲边界场景。受 mattpocock/skills（223k★ MIT）启发。

Authenticated remote access for a DeepSeek Harness web profile: TLS, QR/passcode device pairing, password sign-in, and per-device revocation in front of an untouched loopback harness.

Self-evolving memory for DeepSeek Harness (DSH): earned experiences, diary/fact semantic memory, concern tracking, and an append-only audit ledger.

DSH 批量删除工作区插件 — CLI批量清理 + Web批量勾选删除，一键清理 .codex 导入残留空工作区

Portable NoteMD workflow bundle for DeepSeek Harness

Identify whether a DSH UI element belongs to the host interface or an installed plugin, then export or hide it.

DSH plugin: expose Trae Work CN credits as a local OpenAI/Anthropic compatible API for Claude Code, Cursor, Cline and other agents

Host-anchored provider, authentication, catalog, policy, and model-selection extension for DeepSeek Harness.

Search arXiv for ML/DL/RL papers and check claims against real abstracts.

Clustr Trading Console for DeepSeek Harness: secure, multi-exchange tools and an AI trader cockpit.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

上下文工程：按层级（规则文件→规格→源码→错误输出→对话历史）主动策划 agent 看到的信息，提升输出质量。受 addyosmani/agent-skills（88k★ MIT）启发。

Bindet jedes DeepSeek-Harness-Plugin sauber ein oder aus – listet jede eingebundene Ebene auf (Bundles + Patch-Zeilen), entfernt mit vollständiger Bereinigung, deaktiviert/aktiviert ohne Löschen und prüft auf verwaiste/hängende Zustände. CLI- und agentenaufrufbares unplug-Tool. Standardmäßig schreibgeschützt; destruktive Vorgänge erfordern eine ausdrückliche Bestätigung.

Structured syntax highlighting service for DeepSeek Harness Web plugins

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

DeepSeek Harness bundle: vendored anti-slop Oxlint rules, the anti_slop_lint tool, the install-anti-slop skill, a standing prompt section, and the /anti-slop command.

Checks whether a similar dsh plugin already exists before you build one, searching the awesome-dsh-plugin registry and the dsh-plugin GitHub topic and returning ranked matches with evidence.

Erzeugt llms.txt für dsh-Plugin-Repositories aus package.json + README — KI-lesbare Discovery-Dateien, keine Laufzeit-Abhängigkeiten, standardmäßig schreibgeschützt. CLI plus ein vom Agent aufrufbares llms_forge-Tool.

First-run health check for DeepSeek Harness: verifies Node/pnpm/dsh toolchain, home, profile, API key (names only, never values), workspace writability and npm registry, then prints actionable next steps — CLI plus an agent-callable quickstart tool, dsh-firstrun/v1 reports, zero runtime deps.