KCNyu

19 mods across 1 repository, 21 stars between them.

investment-decision

01

KCNyu/clawock

Skill Claude CodeCodex needs its repo

Run a clawock investment decision — read the prepared request, research with the host's own tools, write decision.json with evidence and an explicit bull/bear debate, and let Python validate and settle. Use when the user asks for an investment decision or a clawock run request is present.

not rated 21 +1 today A SkillSpector: warn 62 tokens original MIT

investment-decision

02

KCNyu/clawock

Skill Claude CodeCodex

Read the clawock request file, write decision.json, let clawock validate. Use when a clawock run request is present in .clawock/work/.

not rated 21 +1 today A SkillSpector: warn 36 tokens original MIT

daily-deep-brief

03

KCNyu/clawock

Skill Claude CodeCodex

A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.

not rated 21 +1 changed today A SkillSpector: pass 163 tokens original MIT

earnings-review

04

KCNyu/clawock

Skill Claude CodeCodex

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/ / .json whose earnings-quality math, promise ledger…

not rated 21 +1 today A SkillSpector: pass 98 tokens original MIT

entry-gate

05

KCNyu/clawock

Skill Claude CodeCodex

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…

not rated 21 +1 changed 12d ago A SkillSpector: pass 109 tokens original MIT

github

06

KCNyu/clawock

Skill Claude CodeCodex

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.

not rated 21 +1 today A 44 tokens copy · 81% MIT

hk-stock-analysis

07

KCNyu/clawock

Skill Claude CodeCodex

A workspace-aware analysis workflow for Hong Kong-listed stocks. It retrieves prices, technical indicators, market comparisons, and news through a local data pipeline, then adds Hong Kong-specific investment context.

not rated 21 +1 changed yesterday A SkillSpector: pass 126 tokens original MIT

openclaw-tune

08

KCNyu/clawock

Skill Claude CodeCodex

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…

not rated 21 +1 changed 19d ago A SkillSpector: warn 135 tokens original MIT

openclaw-upgrade

09

KCNyu/clawock

Skill Claude CodeCodex needs its repo

A cautious procedure for upgrading OpenClaw, an agent system that may run scheduled jobs and other live services. It checks the target version, known issues, active scheduled jobs, local patches, and the system after the update.

not rated 21 +1 changed 3d ago A SkillSpector: warn 110 tokens original MIT

KCNyu/clawock

Skill Claude CodeCodex

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 clawock analyze-us / clawock analyze-hk.

not rated 21 +1 changed 6d ago A SkillSpector: pass 70 tokens original MIT

KCNyu/clawock

Skill Claude CodeCodex

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…

not rated 21 +1 changed 5d ago A SkillSpector: pass 90 tokens original MIT

scrapling

12

KCNyu/clawock

Skill Claude CodeCodex

A Python framework for collecting information from websites, including pages whose content is created by JavaScript. It provides CSS and XPath selectors for extracting text, links, and other page data, and includes browser-based fetching for sites with anti-bot checks.

not rated 21 +1 today A SkillSpector: pass 0 tokens original MIT

serenity-skill

13

KCNyu/clawock

Skill Codex

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…

not rated 21 +1 today A 146 tokens copy · 100% MIT

tavily

14

KCNyu/clawock

Skill Claude CodeCodex

AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.

not rated 21 +1 today A SkillSpector: warn 23 tokens original MIT

Trading

15

KCNyu/clawock

Skill Claude CodeCodex

Trading analysis and education. Technical analysis, chart patterns, risk management, and position sizing for stocks, forex, and crypto.

not rated 21 +1 today A SkillSpector: pass 27 tokens original MIT

us-stock-analysis

16

KCNyu/clawock

Skill Claude CodeCodex

Workspace-aware US stock analysis for kcn. Routes through clawock analyze-us / clawock us-quotes 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…

not rated 21 +1 changed 5d ago A SkillSpector: pass 97 tokens original MIT

shared-memory

17

KCNyu/clawock

Skill Claude CodeCodex

Recall durable preferences and prior decisions when current context is insufficient, or maintain the Markdown memory shared by this machine's coding agents. Uses Claude Code's existing auto-memory store; ordinary tasks do not require a memory lookup.

not rated 21 +1 changed 3d ago A 46 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: