Bundle
superpowers-dsh
Superpowers for the DeepSeek Harness: TDD, debugging, planning, and collaboration skills adapted from obra/superpowers
LayneChai105
Browse
12 results
Bundle
dsh-zh-thinking
DSH host plugin: force the agent's chain-of-thought / reasoning / planning / tool-invocation deliberation to stay in Simplified Chinese — 让 Agent 的内部思考（思维链）始终使用简体中文。
yingjian66611
Bundle
dsh-grayprint
GrayPrint — live reasoning-style fingerprints for the DeepSeek Harness web chat. Compares grayscale-vs-current writing style by internal reasoning paragraphs and independently tracks Let me exploratory openers versus We need planning openers.
HongzhongL3
Bundle
think-like-codex
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
zhangnan2
Bundle
dsh-goal-scaffold
Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts
zriyox2
Bundle
dsh-tree-task-flow
树形任务流：把多步任务组织成目标→任务→子任务三级树，节点完成时由 AI 提交结果，插件随即把该节点的执行过程从上下文里折叠掉，只留下结果。
viyiviyi2
Bundle
dsh-growth-workbench
个人成长工作台：90 天计划、每日打卡与证据、加权能力缺口、分级考核复盘，页面与 Agent 读写同一份数据。A personal growth workbench bundle plugin for DeepSeek Harness (dsh).
mingdui1
Bundle
dsh-model-deploy
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
lhwwxy
Bundle
dsh-planning
计划与任务拆解：把目标拆成可验证的小任务、排序依赖、估算工作量、追踪进度。受 addyosmani/agent-skills（88k★ MIT）启发。
satan9394
Bundle
dsh-synomega
Organic reaction prediction for DeepSeek Harness: retrosynthesis, forward prediction, route planning, SynScore, and multi-component evolution, with in-chat molecule/reaction/route visualisation
zbc0315
Bundle
dsh-generative-ideas
Roadmap ideation for DeepSeek Harness: generate and compare distinct roadmap options via headless agent runs, pick the one that fits, export as goal.md, and dispatch it to an agent in the chosen workspace.
svgop
Bundle
backlog-triage
Triage a scattered backlog into a bounded queue of decisions: every item gets a disposition (now / next / scheduled / waiting / reference / drop) with a stated reason, dropped items leave the list instead of haunting it, and anything that changes a commitment goes out as one approval batch.
ChenneyZhuang