Plugin

Pet da desktop per la Web UI di DSH con 25 animazioni trasparenti, vagabondaggio sullo schermo, reazioni al clic e trascinamento, più una pipeline riproducibile per la generazione degli asset.

Toolkit di R&S quantitativa per DeepSeek Harness — 46 strumenti in sei aree che coprono dati di mercato, indicatori, valutazione dei fattori, validazione ML walk-forward, rischio, opzioni, obbligazioni e simulazione di fondi, con una pipeline di ricerca end-to-end.

Failover ad alta disponibilità dei modelli (quarantena, circuit breaking, ripristino tramite probe) e orchestrazione di subagent (fanout/pipeline/supervisor) con interfaccia impostazioni bilingue.

Porta tutti i 34 temi ufficiali di opencode (33 JSON statici + 1 di sistema) in DeepSeek Harness: pipeline basata sui dati (JSON → risoluzione colore → override DSH), persistenza per browser, scelta tra monospazio/proporzionale, cinque font per il codice e un fallback di sistema che mantiene solo la tipografia.

Aggancia DeepSeek Harness a una pipeline Hermes: template di specifica di dispatch, instradamento per livello di modello, gate di qualità per l'esecuzione dell'orchestratore, regola del singolo scrittore Git, come pacchetto SKILL.md (installabile come bundle).

Preset dell'agente per team di prodotto virtuale: conversazione guidata dall'utente che ti accompagna attraverso l'intera pipeline di 12 fasi dall'idea al prodotto spedito, promosso e operato, con gate per fasi e competenze per fase.

Plugin trust pipeline for DeepSeek Harness: deterministic static scan with verdicts, opt-in runtime guard with honeypot lures, agent audit-protocol skill, and a browser shield status light. Alarm-only, never an enforcer.

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.

WeChat Official Account content studio: anti-homogenization rotation writing, low-creativity remediation playbook, blessing-image visual baseline, gpt-image pipeline with OCR acceptance, and the measured xiaolvshu draft web API.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

Cross-session reference (mention) for DeepSeek Harness: paste @[label](dsh-session:…) into any session — including one in another workspace — and the host resolves and injects the referenced session snapshot via the native session-reference pipeline. Incl

Multi-agent deep long-form article pipeline skill for DeepSeek Harness, running 8 roles across 5 phases with parallel literature/data/case retrieval, a critical-companion review, M-Gate mechanical final check, independent G0-G13 audit and human verification gates.

Rigorous open mathematics research suite: four agent skills (rigorous-open-math-research, manage-math-research-program, math-research-workflow, lean-verify) for theorem solving with adversarial audit, research program management, pipeline orchestration, and Lean 4 formalization audit; CI-verified tests and mechanical upstream sync.