Skills for Real Engineers. Straight from my .agents directory.
kanchi-dividend-review-monitor
Agent skill fromtradermonty/claude-trading-skills
Monitor dividend portfolios with Kanchi-style forced-review triggers (T1-T5) and convert anomalies into OK/WARN/REVIEW states without auto-selling. Use when users ask for 減配検知, 8-Kガバナンス監視, 配当安全性モニタリング, REVIEWキュー自動化, or periodic dividend risk checks.
How to install kanchi-dividend-review-monitor
npx skills add tradermonty/claude-trading-skills# or add only this skill to Claude Code: copy the folder
skills/kanchi-dividend-review-monitor/
# into
~/.claude/skills/kanchi-dividend-review-monitor/ (all projects)
.claude/skills/kanchi-dividend-review-monitor/ (one project)
1# Kanchi Dividend Review Monitor23## Overview45Detect abnormal dividend-risk signals and route them into a human review queue.6Treat automation as anomaly detection, not automated trade execution.78## When to Use910Use this skill when the user needs:11- Daily/weekly/quarterly anomaly detection for dividend holdings.12- Forced review queueing for T1-T5 risk triggers.13- 8-K/governance keyword scans tied to portfolio tickers.14- Deterministic `OK/WARN/REVIEW` output before manual decision making.1516## Prerequisites1718Provide normalized input JSON that follows:19- `references/input-schema.md`2021If upstream data is unavailable, provide at least:22- `ticker`23- `instrument_type`24- `dividend.latest_regular`25- `dividend.prior_regular`2627## Non-Negotiable Rule2829Never auto-sell based only on machine triggers.30Always create `WARN` or `REVIEW` evidence for human confirmation first.3132## State Machine3334- `OK`: no action.35- `WARN`: add to next check cycle and pause optional adds.36- `REVIEW`: immediate human review ticket + pause adds.3738Use `references/trigger-matrix.md` for trigger thresholds and actions.3940### Flat-dividend cadence caveat41…
Excerpt shown under the repository's MIT license.
More skills in claude-trading-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
