mcpField
J
jinko

jinko

github.com/novainsilicoAgent workflows4162 installsUpdated 1w ago
Repository

About jinko

jinko is a routing skill for the Jinkō plugin bundle. It identifies the user's immediate intent and directs it to the narrowest published skill owner rather than duplicating task or SDK guidance.

Key features

  1. 01Intent-based skill routing
  2. 02Guidance for Jinkō task and SDK skill owners
  3. 03Handling requests spanning multiple skill areas
  4. 04Instructions for unavailable skills
  5. 05Rules for surfacing resource URLs

Use cases

  1. 01Route a Jinkō request to its relevant skill
  2. 02Handle a request spanning several Jinkō areas
  3. 03Respond when a required skill is unavailable

MCP support

It references the Jinko MCP `get_session_code` tool for connection and credentials routing, and directs resource URLs to be surfaced without constructing them.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/novainsilico/jinko-skills --skill jinko

After installing, type/jinkoin Claude Code to confirm it loaded.

Bundled filesagents/openai.yamlevals/evals.json

Details

From the project README

Jinkō Skill Router

Identify the user's immediate intent and load the narrowest published owner. Do not reproduce its mechanics. Task skills own task-level decisions and orchestration; resource skills own reusable Jinkō SDK/API mechanics.

Routing Map

  • Connection and credentials: jinko-sdk-setup (JINKO_API_KEY, or a single-use JINKO_SESSION_CODE from the Jinko MCP get_session_code tool).
  • Terminology and navigation: jinko-context.
  • Product capabilities and model-library discovery: jinko-solution-and-product-guide.
  • Publication discovery: jinko-task-literature-search.
  • ClinicalTrials.gov discovery: jinko-task-trial-data-scoping.
  • Reference PDFs and source extracts: jinko-reference.
  • Evidence-to-table extraction: jinko-task-extract-data-table.
  • MATLAB/SimBiology export and solver parity: jinko-task-export-to-matlab.
  • NONMEM model and trial conversion: jinko-task-from-nonmem.
  • Data-table mechanics: jinko-data-table.
  • Model mechanics: jinko-model.
  • Calibration-input classification: jinko-task-define-param-to-calibrate.
  • Confirmed CMA-ES execution: jinko-task-cmaes; SDK mechanics: jinko-calibration-cmaes.
  • Protocol mechanics: jinko-protocol.
  • Virtual-population mechanics: jinko-vpop.
  • Trial mechanics: jinko-trial.
  • Trial visualization mechanics: jinko-trial-viz.
  • Document mechanics: jinko-document.

If a request spans several areas, state which owner applies to the immediate request and let that skill determine its own prerequisites or handoffs. Do not invent a project plan, artifact checklist, stage order, or completion gate here.

Missing Capabilities

The public skills are an interdependent plugin bundle. If a named owner is not available, direct the user to install or update the complete Jinkō plugin from novainsilico/jinko-skills, then start a fresh session or reload plugins. Do not recommend installing one skill in isolation.

Resource Links

When an owner returns a resource, surface its SDK-provided .url or returned resource URL. Never construct a link from a SID and a hard-coded hostname; configured JINKO_URL and on-premises application URLs must be preserved.

Comments

Markdown supported