agentleFS
ray5273ray5273/kr-research-kit/skills/kr-market-leaders/SKILL.md

kr-market-leaders

Skill2 starsChanged 11 days agoMITView on GitHub

Screen the integrated KOSPI + KOSDAQ universe for Korean market leadership across short-term, intermediate, and structural technical lenses. Use when the user asks for KRX market leaders, market-wide relative strength, Korean leading stocks, short-term movers, 30/60-day leaders, 52-week-high leadership, or Minervini-style market leadership screening.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for market-wide KRX leadership screens.

    line 8
  2. Distinctive:

    Read references/workflow.md for the run checklist.

    line 12
  3. Very specific:

    Run scripts/screen-kr-market-leaders.js with node.

    line 13
  4. Distinctive:

    Write both standard artifacts when the workspace is writable:

    line 14
  5. Distinctive:

    Always show all three lenses: short-term, intermediate, and structural.

    line 40
  6. Distinctive:

    Use exact 기준일 and generated timestamp.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Korean Market Leaders

Use this skill for market-wide KRX leadership screens. It is price/volume-derived only and must not imply fundamental leadership, broker support, or buy recommendations.

Workflow

  1. Read references/workflow.md for the run checklist.
  2. Run scripts/screen-kr-market-leaders.js with node.
  3. Write both standard artifacts when the workspace is writable:
    • analysis-example/kr-market/leaders-<YYYY-MM-DD>.md
    • analysis-example/kr-market/leaders-<YYYY-MM-DD>.json
  4. Return a compact summary with the output paths, universe counts, failed fetch count, and the highest-ranked names by lens.

Default Universe

  • Integrated KOSPI + KOSDAQ ordinary common stocks.
  • Exclude ETFs, ETNs, SPACs, REITs, preferred shares, and obvious non-common listings through the shared kr-stock-chart KRX listing filter.
  • Reuse the enriched kr-stock-chart/scripts/build-kr-universe-rs-cache.js cache. Existing return63, return126, return252, and rsPercentile fields remain the compatibility contract.

Standard Command

node skills/kr-market-leaders/scripts/screen-kr-market-leaders.js --date YYYY-MM-DD

Useful options:

  • --limit 30 for a small smoke run.
  • --cache-in path/to/cache.json to render from an existing or synthetic cache without live network fetches.
  • --json-out path and --md-out path to override standard output paths.
  • --top 20 to control table size.

Operating Rules

  • Always show all three lenses: short-term, intermediate, and structural.
  • Label weak data rather than filling gaps.
  • Infer themes only from KRX industry labels or company names.
  • Include the warning that this is a technical/market-leadership screen, not a buy recommendation.
  • Use exact 기준일 and generated timestamp.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.