kr-research-kit
AGENTS.md2 starsChanged 8 days agoMITView on GitHub
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository42 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- kr-analyst-report-discoverSkill
- kr-analyst-report-fetchSkill
- kr-analyst-report-insightSkill
- kr-analyst-report-watchSkill
- kr-article-readabilitySkill
- kr-chatgpt-reviewSkill
- kr-daily-market-newsSkill
- kr-earnings-reviewSkill
- kr-finance-slide-claritySkill
- kr-foreign-analystSkill
- kr-market-leadersSkill
- kr-market-sentimentSkill
- kr-naver-bloggerSkill
- kr-naver-blog-publishSkill
- kr-naver-browseSkill
- kr-naver-insightSkill
- kr-order-backlog-analysisSkill
- kr-portfolio-guardSkill
- kr-portfolio-monitorSkill
- kr-research-siteSkill
- kr-sector-analysisSkill
- kr-sector-auditSkill
- kr-sector-compareSkill
- kr-sector-data-packSkill
- kr-sector-planSkill
- kr-sector-updateSkill
- kr-stock-analysisSkill
- kr-stock-chartSkill
- kr-stock-dart-analysisSkill
- kr-stock-data-packSkill
- kr-stock-planSkill
- kr-stock-updateSkill
- kr-strategy-backtestSkill
- kr-trade-flow-analysisSkill
- kr-web-browseSkill
- telegram-report-senderSkill
- us-daily-market-newsSkill
- us-earnings-reviewSkill
- us-sec-analysisSkill
- us-stock-analysisSkill
- us-strategy-backtestSkill
The file
We split this AGENTS.md into the rules it gives an agent
12 rules. About 0 are common, 6 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
When you add or update a stock analysis example, keep it under analysis-example/<market>/<company>/.
- Very specific: line 11
When a stock-analysis skill is invoked in this repo and the workspace is writable, create or update the matching report file under …
- Distinctive: line 13
When a commit changes a skill's required output shape, refresh any affected example documents so they still match the current skill …
- Distinctive: line 14
When an example document embeds a chart image, refresh the linked PNG asset together with the markdown file so the visual stays in sync …
- Very specific: line 15
When you update an existing Korean memo with follow-up analysis, preserve the original 기준일, refresh 최근 업데이트일, and append or replace a dated …
- Distinctive: line 17
Treat example analysis documents as time-sensitive.
- Distinctive: line 18
If the example must mix metrics from sources with different refresh cadences, keep the document honest by stating the exact date for each …
- Distinctive: line 19
Do not invent revenue mix, customer concentration, governance facts, or valuation metrics that are not disclosed in the current source set.
- Very specific: line 20
Do not invent foreign-IB views.
- Distinctive: line 23
Prefer primary sources first for Korean stocks: DART, KRX disclosures, company IR pages, governance pages, and official financial …
- Very specific: line 28
Before publishing a new or edited article, use skills/kr-article-readability/SKILL.md to review emphasis, tone colors, paragraph length, …
- Very specific: line 29
Run npm run check:readability before site or preview deployment.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.
Files
AGENTS
External Agent Targets
- A request referring to the Hermes agent means the remote Hermes runtime (SSH address in
~/stock-analysis-private/HERMES.md, not in this public repo) unless the user explicitly names another target. - Inspect the remote runtime and its active configuration before changing Hermes behavior. Keep source and the installed
~/.hermesruntime copy aligned when a scheduled Hermes script is changed.
Repository Rules
- When you add or update a stock analysis example, keep it under
analysis-example/<market>/<company>/. - When a stock-analysis skill is invoked in this repo and the workspace is writable, create or update the matching report file under
analysis-example/<market>/<company>/memo.mdinstead of leaving the analysis only in chat. - When you add a new example file, do NOT append a link to
README.md. Stage the example first (git add), then runnode scripts/build-artifact-index.jsto regeneratedocs/ARTIFACTS.md, and commit the index together with the example. The index deliberately covers only git-tracked files so its links never 404 on a fresh clone. The README carries only a handful of curated representative links; replace one only when the new artifact is a better canonical demonstration, never by appending. - When a commit changes a skill's required output shape, refresh any affected example documents so they still match the current skill behavior.
- When an example document embeds a chart image, refresh the linked PNG asset together with the markdown file so the visual stays in sync with the text.
- When you update an existing Korean memo with follow-up analysis, preserve the original
기준일, refresh최근 업데이트일, and append or replace a dated block under## Update Loginstead of rewriting the whole memo by default. - For dated follow-up updates, search only for company-specific disclosures, IR materials, and news published after the memo's
기준일, then deduplicate against existing update dates and source URLs when possible. - Treat example analysis documents as time-sensitive. Before committing changes to an example document, refresh prices, valuation metrics, disclosures, and source dates with current sources.
- If the example must mix metrics from sources with different refresh cadences, keep the document honest by stating the exact date for each metric block or row.
- Do not invent revenue mix, customer concentration, governance facts, or valuation metrics that are not disclosed in the current source set. State what is not separately disclosed.
- Do not invent foreign-IB views. Every
## Street / Alternative Viewsbullet that names a foreign broker, rating, or target price must trace back to a dated Korean news article that quoted that broker; preferkr-foreign-analystoutput over paraphrasing from memory. - When the user asks for a Korean post-earnings review (실적 리뷰, 실적발표 자료), read and follow
skills/kr-earnings-review/SKILL.mdend to end: runcollect-earnings-inputs.js, pass its readiness gate, and if any required input is missing stop in 검토 대기 with.tmp/earnings/<ticker>-<period>/REVIEW-NEEDED.mdfor the user's review instead of publishing. At the start of a session, check.tmp/earnings/*/REVIEW-NEEDED.mdfor reviews left on hold. - For a U.S.-listed company's post-earnings review, follow
skills/us-earnings-review/SKILL.mdthe same way (collect-us-earnings-inputs.js, the same R1–R6 gate,.tmp/earnings/us-<TICKER>-<period>/REVIEW-NEEDED.mdwhen on hold). - Prefer primary sources first for Korean stocks: DART, KRX disclosures, company IR pages, governance pages, and official financial statements.
- When the memo needs sell-side consensus (target price, rating distribution, broker coverage), use the analyst-report chain (
kr-analyst-report-discover→kr-analyst-report-fetch→kr-analyst-report-insight). It pulls reports fromconsensus.hankyung.com(primary) withfinance.naver.com/researchas fallback, defaults to a 365-day lookback, and skips login-gated reports. Treat the resultinganalyst-report-insight.mddigest as sell-side inference, not a primary filing fact — it lands inanalysis-example/kr/<company>/and is ingested intokr-stock-data-pack'sExternal ViewswithSource role: sell-side consensus.
Article readability before site deployment
- Before publishing a new or edited article, use
skills/kr-article-readability/SKILL.mdto review emphasis, tone colors, paragraph length, section rhythm, tables and source labels. Preserve facts, source dates and judgment in layout-only edits. - Run
npm run check:readabilitybefore site or preview deployment. Official npm deployment commands also run this gate automatically. A new/changed article needs a matching review insite/readability-reviews.json; do not generate review records without doing the editorial review. - Legacy article snapshots are explicitly unreviewed debt, not passes. Do not bulk-refresh those hashes to bypass the review. If browser checks are unavailable, record source/renderer checks honestly and retain the visual limitation.
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
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.

