dsh-nail-shape
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-nail-shape
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-nail-shape in DeepSeek Harness to install this plugin; the source is available at https://github.com/uckkk/dsh-nail-shape .
About this plugin
dsh-nail-shape is a workflow plugin that adds structured nail-shape selection to agent conversations. In real-world beauty or wellness flows, a user often needs to pick a nail shape and receive a matching care plan. Instead of letting the model re-reason through that logic every turn, this plugin collapses the step into a single, well-defined tool call: pass in parameters, get back a plan.
The core is a tool called nail_shape, which returns a manicure care plan based on the parameters you supply. The whole implementation is pure Node with no network dependencies at all — no external APIs, no key management, no third-party services. That keeps it fast to respond, trivially deployable, and free of any network-related failure modes.
It is aimed at developers building agent workflows that touch nail or fingertip care scenarios. If you want to turn a fairly vertical decision — choosing a shape and pairing the right aftercare — into one clean, deterministic tool call rather than a free-form model answer, this plugin gives you a lightweight way to do exactly that.
Use Cases
- Recommend a nail shape and matching care plan within an agent conversation
- Automate fingertip-care step matching in salon or studio workflows
- Prove structured, deterministic outputs for offline nail-consultation flows
Best For
- Developers building agent workflows in the nail-care industry
- Workflow orchestrators who want to reduce nail-shape selection to a single tool call
- Integrators who prefer offline, zero-network, easy-deploy tooling
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.