dsh-kpi-reach
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-kpi-reach
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-kpi-reach in the DeepSeek Harness terminal to install this plugin; the source repository is available at https://github.com/uckkk/dsh-kpi-reach.
About this plugin
When building agent workflows, turning the question 'how much is left to hit this KPI and which dimensions are dragging' into concrete, reproducible steps is often the most tedious part. dsh-kpi-reach condenses that into a single tool called kpi_reach: the caller passes in the relevant parameters, the plugin performs a precise calculation, and returns a structured breakdown of the gap — no need to hand-craft formulas or intermediate variables inside a prompt.
The plugin is implemented in pure Node.js with zero network calls and no third-party service dependencies. It can therefore run inside offline sandboxes, air-gapped CI pipelines, or any restricted runtime where behavior must be fully predictable and free from external API instability.
If you are assembling dsh workflows around goal tracking, performance review, or business metric analysis and want a deterministic code step for gap breakdown rather than leaving it to the model to improvise, kpi_reach offers a lightweight and controllable option. Register it in the session and the agent can invoke it at any point in the planning chain to obtain calculation results ready for downstream reasoning.
Use Cases
- Precisely computing quarterly KPI gaps and returning structured breakdowns inside an agent workflow
- Running metric-baselined gap analysis in offline sandboxes or air-gapped CI without external API calls
- Offloading the 'how much is left and where' step from prompts to deterministic code
Best For
- Engineers building goal-tracking or performance-review workflows with dsh
- Agent architects who require offline, network-free deterministic computation steps
- Developers who prefer extracting metric breakdown logic from prompts into code
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.