dsh-prompt-optimizer
Pre-execution intent interpreter and arbiter plugin that injects evidence-backed context into DSH models.
Install
$ dsh plugin --profile po061 add "$d\dsh-external-dsh-arbiter-wf-$v.tgz" # 装Plugin 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
- Intercepts prompts before dispatch to parse concrete requirements without altering verbatim input text
- Generates evidence-backed requirement bundles strictly tied to source context or verbatim quotations
- Provides a customizable control panel with sensitivity tiers (off, light, standard, heavy) and approval modes
- Features an interception overlay displaying a thought layer and an editable output bundle
- Integrates independent task review (consult_task) and managed workspace tool execution safeguards
Useful For
- Stabilizing performance and requirement adherence for models like DeepSeek-V4.1-Flash on complex tasks
- Clarifying implicit constraints and ambiguities in software generation prompts before AI execution
- Inspecting and editing AI prompt context bundles prior to dispatch
Who It Fits
- DeepSeek Harness users seeking structured, evidence-backed prompt disambiguation
- Developers working with iterative single-file or multi-step generation tasks in DSH Web
Documented Limitations
- Requires 20-60 seconds for interpretation depending on context size and selected model tier
- Does not maintain persistent long-term cross-turn constraints automatically without context window awareness
- Distributed via GitHub Releases as a private package; not published to npm registry
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, 0 development, 1 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as BSD-3-Clause.
A root package.json was captured and can be inspected by the registry.
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
- WestFox-AwA/dsh-prompt-optimizer
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 832e330 · 2026-10-14
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
- 115GitHub stars
- Forks
- 11
- Open issues
- 4
- Last commit
- 2026-10-11
- Last release
- 2026-10-09
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →An ontology-first agent preset and epistemic loop platform for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed fallback and session audit logging.
View plugin →