oss-prompt-optimizer
A DeepSeek Harness prompt optimization plugin bundle that rewrites raw instructions into structured, high-quality prompts.
Install
$ dsh plugin --profile web add oss-prompt-optimizerPlugin 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
- Rewrites casual instructions into plain text, role-task-goal, or four-section (Role/Task/Context/Format) prompts
- Provides an interactive UI button in the composer toolbar with undo and cancel capabilities
- Exposes the prompt_optimize tool for agent workflows and ctx.promptOptimizer for programmatic invocation
- Includes context-aware and situation-aware parsing to extract role, task, and goal profiles from dialogue history
- Offers fast local templates via /template commands without consuming LLM tokens
- Features a 3-layer self-iteration system that adapts to user preference over time
- Supports auto-optimization hooks for user messages via pre-step agent hooks and /optimize commands
- Provides in-memory caching (LRU + TTL) to avoid redundant LLM invocations
Useful For
- Enhancing vague user input in the chat composer with a single click before submission
- Iteratively refining and aligning prompt goals during agentic task execution
- Instantly generating boilerplate templates for weekly reports, code reviews, and bug fixes without LLM latency
- Auto-optimizing prefixed prompts sent directly to DeepSeek Harness agents
Who It Fits
- DeepSeek Harness web client users seeking higher AI output quality
- Prompt engineers and developers wanting consistent multi-section prompt formats
- Agent builders integrating automatic prompt refinement into workflows
Documented Limitations
- Requires Node.js >= 22 and compatible DeepSeek Harness versions (^0.1.6-alpha.2 or ^0.2.0-rc.2)
- Settings UI registration requires the host dsh-settings service, falling back to cordis.patch.yml if absent
- Self-iteration profile learning requires at least 10 optimization records before activation
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 1 runtime, 8 development, 2 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.
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
- seven282/oss-prompt-optimizer
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 8911de6 · 2026-10-05
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
- 21GitHub stars
- Forks
- 1
- Open issues
- 5
- Last commit
- 2026-10-01
- Last release
- No release detected
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 →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →Multi-model workflow teams and DAG orchestration GUI for DeepSeek Harness Web profile.
View plugin →Industry and company research domain pack for DeepSeek Harness with chain mapping, tracking, company cards, and verifiable reports.
View plugin →