agentleFS
ray5273ray5273/kr-research-kit/skills/kr-analyst-report-watch/SKILL.md

kr-analyst-report-watch

Skill2 starsChanged 9 days agoMITView on GitHub

Monitor newly published Korean sell-side analyst reports in daily or weekly mode, summarize the Top N public brokerage reports, compare topic narratives against prior report-watch outputs, and write Markdown/JSON artifacts under analysis-example/kr-reports/.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants a daily or weekly watch of Korean securities analyst reports across companies, sectors, or themes, …

    line 8
  2. Distinctive:

    Read references/workflow.md for collection, comparison, and copyright rules.

    line 12
  3. Distinctive:

    Read references/output-format.md before writing or reviewing final artifacts.

    line 13
  4. Distinctive:

    Run the collector in the requested cadence:

    line 14
  5. Distinctive:

    Run before considering changes complete:

    line 51

≈ “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 Analyst Report Watch

Use this skill when the user wants a daily or weekly watch of Korean securities analyst reports across companies, sectors, or themes, without starting from a single ticker.

Workflow

  1. Read references/workflow.md for collection, comparison, and copyright rules.
  2. Read references/output-format.md before writing or reviewing final artifacts.
  3. Run the collector in the requested cadence:

    node skills/kr-analyst-report-watch/scripts/discover-watch-reports.js \
      --mode daily \
      --date YYYY-MM-DD \
      --max-reports 10 \
      --output .tmp/kr-analyst-report-watch/raw-daily-YYYY-MM-DD.json

    Weekly mode defaults to Top 30:

    node skills/kr-analyst-report-watch/scripts/discover-watch-reports.js \
      --mode weekly \
      --date YYYY-MM-DD \
      --max-reports 30 \
      --output .tmp/kr-analyst-report-watch/raw-weekly-YYYY-MM-DD.json
  4. The script writes final artifacts unless --no-artifacts is passed:
    • analysis-example/kr-reports/report-watch-daily-YYYY-MM-DD.md
    • analysis-example/kr-reports/report-watch-daily-YYYY-MM-DD.json
    • analysis-example/kr-reports/report-watch-weekly-YYYY-MM-DD.md
    • analysis-example/kr-reports/report-watch-weekly-YYYY-MM-DD.json
  5. In chat, provide only a short summary: mode/date, number of reports, top narrative changes, and any source gaps. Do not paste long report excerpts.

Defaults

  • Source scope: Korean securities reports only.
  • Cadence: daily or weekly; default is daily.
  • Depth: daily Top 10, weekly Top 30 unless overridden by --max-reports.
  • Source order: Hankyung Consensus first, Naver Research fallback/secondary.
  • Priority: narrative changes in industry trend, demand/supply, policy, competition, risk framing, and catalysts.

Validation

Run before considering changes complete:

node --check skills/kr-analyst-report-watch/scripts/discover-watch-reports.js
node skills/kr-analyst-report-watch/scripts/test-report-watch.js

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.