dsh-ask-leader
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-ask-leader
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-ask-leader in DeepSeek Harness to install this plugin; the open-source repository is at https://github.com/uckkk/dsh-ask-leader .
About this plugin
Upward communication — reporting progress, requesting decisions, or pitching ideas — often falls flat due to scattered structure, unclear priorities, and missed key points. dsh-ask-leader turns this process into a structured tool so that every interaction with a manager or stakeholder is grounded in a clear framework rather than improvised speech.
The core capability is the ask_leader tool: given a set of parameters at call time, it returns a structured method for upward communication, giving the caller a ready-made skeleton for reports, decision requests, or proposals. The plugin is implemented in pure Node with zero network dependencies, keeping it lightweight and instantly responsive within any existing agent workflow.
It is well suited for individuals or teams who need a standardized approach to upward communication in their sessions, especially those who want to embed reporting, decision requests, or proposal submissions as fixed steps in an automated workflow and cut down on the overhead of reorganizing language from scratch every single time.
Use Cases
- Generating a structured draft for upward reporting or decision requests within an agent session
- Embedding reporting and decision steps as fixed parts of an automated workflow
- Instantly retrieving a communication framework in an offline environment
Best For
- Individuals who need standardized upward-communication steps in their agent workflows
- Mid-level managers who want to cut the overhead of reorganizing report language each time
- Tool developers who prefer lightweight, dependency-free, pure-Node implementations
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.