dsh-pua
Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.
提供 /pua，在 Agent 失败后促使其换方法，并在宣称完成前核验收据；含 15 种公司风格、角色模式、全局与会话设置，以及可选验收循环（直到验收命令通过、达到迭代上限或用户取消）。
How to install
dsh plugin add @michengai/dsh-pua About
DSH PUA **Help your agent try another approach and verify its work before calling it done.** 简体中文 · Features · Screenshots · Installation · Usage · Configuration · Commands · Changelog DSH PUA brings PUA to DeepSeek Harness. When an agent repeatedly fails, gives up too early, or claims completion without checking, it encourages a different approach, investigation, and evidence. Community-maintained; not an official DeepSeek AI or PUA product. Features **Try another approach**: prompt the agent to reconsider its reasoning instead of repeating ineffective attempts. **Check before claiming comple…
Recommendation signals
Meta
- License
- Apache-2.0
- Language
- TypeScript
- GitHub stars
- 3
- mo. downloads
- 3.9K
- Last push
- 2026-09-18
- Created
- 2026-09-12
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- ai-agent, deepseek-harness, dsh, dsh-plugin, dsh-plugins, prompt-engineering, pua, typescript
Related plugins
dsh-memory
FuRongJun-1999/dsh-memory
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
dsh-engram
kenz1117/dsh-engram
Cross-session long-term memory under the "memory palace" metaphor: dual-scope SQLite stores (user + per-git-origin project), hybrid FTS5 + local-vector retrieval with RRF fusion and recency/proof ranking boost, automatic capture from the session log (including the final turn), provenance audit chains, consolidation distillation and decay forgetting, and a settings-page Memory Library panel with corridor topology, tour butler, and refurb list.
dsh-answer-reviewer
bycall/dsh-answer-reviewer
Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.
dsh-heartbeat
Kanadego/dsh-heartbeat
Heartbeat loop for DeepSeek Harness: every 20 minutes (by default) the agent wakes on its own to keep a local profile of your interests and preferences, search the web for things you care about, and keep what it finds. When it has something worth sharing, it sends a short package of notes to the sessions you link it to. A set of rules in code - quiet hours, busy windows, a daily limit, a cooldown - decides whether it may speak at all, and the agent in that session decides whether to actually say anything. Windows only.