dsh-roleplay-preset
DeepSeek 深度调校的沉浸式角色扮演 Agent 预设(dsh)——零工具纯对话、酒馆式演出格式、文件记忆库
16 results
DeepSeek 深度调校的沉浸式角色扮演 Agent 预设(dsh)——零工具纯对话、酒馆式演出格式、文件记忆库
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)
Skill-trigger evaluation: an LLM judge recreates the DSH skill catalog and measures how reliably a skill description routes matching queries.
Deterministic, CI-safe golden-output evaluation for DeepSeek Harness
Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run
A local DeepSeek Harness north-star guard with explicit AI indicator evaluation and task alignment context.
Installable bundle contributing the DaoZang offline retrieval & original-text extraction skill to DeepSeek Harness (v2.0: launcher + self-check + workspace setup)
An elevated Plugin list for DeepSeek Harness Web Settings — trust tiers, collapsible groups, and complete per-plugin detail
把技能当可训练参数:像训练神经网络一样训练 agent 技能(epochs/batchsize/learning rate/验证门禁,但不碰模型权重)——rollout→reflect→aggregate→select→update→evaluate 循环、候选编辑仅在严格改善 held-out 验证分时接受、文本学习率预算、零推理时模型调用、部署紧凑 best_skill.md。受 microsoft/SkillOpt(MIT)启发。
LLM 评估:输出质量评估、幻觉检测、基准测试、回归守护。受 wshobson/agents(38k★ MIT)启发。
Fill dead waiting time: while a long task runs, surface one small, true, topic-relevant fun fact — never touching the agent's context or result.
Local-first, source-linked Markdown wiki storage and retrieval plugin for DeepSeek Harness
Paired experiments and promotion gates for DSH plugins.
Creator-native candidate capture, isolated evaluation, promotion, rollback, and visual lineage for DeepSeek Harness
Evidence-backed business strategy, pricing, profitability, elevator pitches and business plans.
Community plugin for event-grounded, privacy-first agent reliability analysis in DeepSeek Harness.