KCNyu
UserAI argues. Code settles. The losses stay on the page. A self-grading multi-agent investment desk running a real HK + US portfolio in public.
Categories
Indexed Skills (13)
serenity-skill
Turn an investment agent into a supply-chain bottleneck hunter. Use this skill for source-backed investment research, live market/theme scans, AI/semi/technology value-chain mapping, A-share/HK/US stock screening, thesis stress tests, and Serenity-inspired research conversations. Trigger on requests like "用 Serenity 的方式看", "深度调研", "产业链/供应链/卡点/瓶��", "A股 AI 半导体哪个最值得研究", "find unknown bottlenecks", "rank candidates", or "challenge this thesis". Outputs plain-language reasoning, ranked research priorities, evidence chains, risks, and next verification steps. Research support only; no trade execution.
trading
Trading analysis and education. Technical analysis, chart patterns, risk management, and position sizing for stocks, forex, and crypto.
hk-stock-analysis
Workspace-aware Hong Kong stock analysis for kcn. Routes through scripts/data/analyze_hk_stocks.py (Tencent primary + Eastmoney full-batch independent cross-check/fallback → stooq → yfinance) for price/技术指标/news, layered with HK-specific concepts — 南向资金, HSTECH 方向, 杠杆 ETF 衰减, 老千股警惕, T+0 无涨跌幅. Use when user asks about a HK ticker (e.g. "分析 00100", "07226 怎么样", "恒科今天"), HK book performance, or HK sector view.
us-stock-analysis
Workspace-aware US stock analysis for kcn. Routes through the local fetch pipeline (analyze_us_stocks.py / fetch_us_stocks.py) instead of generic web search, then layers fundamental/technical/news analysis on top. Use when user asks to analyze a US ticker (e.g. "analyze AAPL", "look at RKLB", "compare TSLA vs NVDA"), check earnings, run technicals, or write an investment report on a US name.
tavily
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
daily-deep-brief
kcn 每个工作日 08:00 HKT 跑一次的盘前全 swarm 深度分析。harness 化：`scripts/harness/brief_preflight.py` 计算并编译 typed decision packet，LLM 只做 Tier 1/2/3/Judge 与受限 judgment overlay，`scripts/harness/brief_postflight.py` 验证、生成 Pages projection、commit 并自动投递微信。**输出**：完整 markdown、结构化 plan、受限 judgment JSON 与紧凑微信卡。**只在每日 8 点 cron 触发时使用；手动深度分析仍走 portfolio-swarm-review。**
openclaw-tune
OpenClaw **system-level** maintenance — cleans sessions/.bak rotation, disk bloat under ~/.openclaw/, validates model fallback chain, audits cron health, prunes short-term-recall noise. Run after `openclaw update` or every 1-2 weeks. Different from **workspace document tune-up** (single-responsibility canonical .md files, token waste scan) which is handled by Claude auto-memory `openclaw-workspace-tuneup` — triggered when user says "优化下 openclaw 的文档/skill/canonical". This skill is for `openclaw` daemon/CLI maintenance, NOT for workspace docs.
portfolio-risk-review
Single-pass holdings analysis for kcn using workspace files and the local fetch chain. Use for portfolio review, position risk ranking, US-HK cross-market read, leverage ETF risk assessment, and one-shot actionable reports based on portfolio.json plus fresh quotes from scripts/data/analyze_us_stocks.py / analyze_hk_stocks.py.
portfolio-swarm-review
Multi-agent swarm review of kcn's current holdings. Inspired by TauricResearch/TradingAgents framework already in workspace — three-tier analysis (analysts → bull/bear debate → risk debate + judge) with confidence scoring. Use for post-close reviews, holiday/next-session planning, pre-add sizing decisions, and any moment where a single-pass review is not enough. For lighter single-shot work, use portfolio-risk-review.
earnings-review
Manual, event-driven earnings review for a US or HK holding, backed by first-party filings. Use when a company reports, when a management promise comes due, or when a thesis review needs primary-source numbers. Produces a structured artifact under memory/earnings/<TICKER>/<period>.json whose earnings-quality math, promise ledger, and thesis evidence are computed by scripts/data/earnings_review.py — not by prose. Never places trades and never changes thesis state.
entry-gate
Pre-investment screening gate for a name that is not yet researched or held. Use before spending a deep-research run or opening new exposure, to answer only "is this understandable and researchable enough to proceed?". Grades information richness separately from investment quality, applies deterministic hard vetoes from config/entry-gate-vetoes.json, and returns pass_to_deep_research / reject / gray_needs_evidence via scripts/data/entry_gate.py. Recommends research; never sizes or places a trade.
openclaw-upgrade
Safe OpenClaw version upgrade with regression checklist. Use when kcn says "升级 openclaw" / "openclaw 有没有更新" / "/openclaw-upgrade", or after noticing a newer npm version. Encodes the validated 6.8 flow — checks for in-flight crons before restart, uses the built-in updater, and runs the full regression gate (cron count, embedding, weixin delivery, model chain). Different from `openclaw-tune` (periodic maintenance, no version bump).
github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.