mcpField
K
korean-bond-search

korean-bond-search

github.com/nomadamasOther8.2k1.7k installsUpdated 2d ago
Repository

About korean-bond-search

A skill for searching Korean bond-related sources, with runtime-specific instructions provided through its CLI. It emphasizes approval before consequential actions and prohibits credential exposure or bypassing legal and identity checks.

Key features

  1. 01Runtime-specific instructions via CLI
  2. 02Approval required for consequential actions
  3. 03Credential handling safeguards
  4. 04Legal and identity-check boundaries

Use cases

  1. 01Guide an agent through Korean bond research
  2. 02Prevent unapproved payments or submissions
  3. 03Avoid exposing credentials during tasks

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nomadamas/k-skill --skill korean-bond-search

After installing, type/korean-bond-searchin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

instruction.md
skill.json
references/
fields.md
source-notes.md
scripts/
bond_search.py
tests/
test_bond_search.py
tests/fixtures/
bonds.json

Details

From the project README

korean-bond-search

Get the full instructions (required first step)

Run this and follow its output as the primary instructions for this skill:

npx -y @nomadamas/k-skill@0 instruct korean-bond-search

The CLI detects the current runtime (Dolshoi vault/CloakBrowser vs generic) and prints only the applicable instructions, always up to date. Helper files bundled with the CLI are listed by:

npx -y @nomadamas/k-skill@0 files korean-bond-search

Keep the CLI and every coding-agent skill install current (including Vercel Agent Skills) with:

npx -y @nomadamas/k-skill@0 update

If npx is unavailable, install Node.js 18+ or follow https://github.com/NomaDamas/k-skill#readme, or read the source instructions at https://github.com/NomaDamas/k-skill/blob/main/korean-bond-search/instruction.md.

Hard rules even without the CLI

  • Never execute payment, message/email delivery, final submission, cancellation, or public posting without the user's explicit approval immediately beforehand.
  • Never ask for, print, or store plaintext credentials in chat, files, or shell arguments.
  • Never bypass legal, physical-presence, CAPTCHA, identity-proofing, or electronic-signature boundaries.

Comments

Markdown supported