dsh-academy
A DeepSeek Harness academic behavior plugin that adds a research persona, citation/data anti-fabrication rules, and bilingual academic-writing conventions.
Install
$ dsh plugin --profile web add dsh-academyPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Adds a research-oriented persona for scholarly tasks.
- Instructs the agent not to invent papers, authors, publication metadata, DOIs, citation counts, or data.
- Encourages separation of literature-derived claims from inference and requires checkable citations.
- Answers in the user's language while preserving original titles, journal names, and terminology.
- Supports configurable persona, integrity, language, field, and prompt ordering settings.
Useful For
- Academic writing and literature-based drafting.
- Research assistance where citation and data fabrication must be avoided.
- Chinese or bilingual scholarly communication.
- Pairing with literature-search or research-skill plugins.
Who It Fits
- Researchers
- Students
- Academic writers
- Teams building DeepSeek Harness research workflows
Documented Limitations
- Registers no tools or skills; external plugins provide literature lookup and research capabilities.
- Integrity rules are described as enforceable only when the agent can actually look papers up.
- Requires Node.js >=22.19.0 according to package metadata.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 6 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- literaf/dsh-academy
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 0c6da51 · 2026-09-17
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-17
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
A standalone, local persistent-memory system for AI agents, with DeepSeek Harness support provided through the separate dsh-mnemon plugin.
View plugin →Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
View plugin →Long-term spatiotemporal memory, zero-LLM whitebox reasoning, and knowledge flywheel integration for DeepSeek Harness via AEIS.
View plugin →Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →