polymarket-analyzer

polymarket-analyzer is a skill for Claude Code, Codex from cyberelf/agent_skills. It costs 69 tokens per session (3,062 once invoked), scanned C, original, MIT.

A workflow for collecting Polymarket prediction-market data and other market signals about Chinese stocks. Polymarket is a website where people trade contracts based on the outcomes of future events.

In plain words
What is it for?
Use it to study prediction-market sentiment related to Chinese or Hong Kong companies and A-shares, including companies such as BYD, NIO, Alibaba, Tencent, and SMIC.
Why use it?
It gathers raw information from several sources so market sentiment can be considered alongside other evidence instead of relying on one signal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to study prediction-market sentiment related to Chinese or Hong Kong companies and A-shares, including companies such as BYD, NIO, Alibaba, Tencent, and SMIC.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyberelf/agent_skills/polymarket-analyzer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add cyberelf/agent_skills --skill polymarket-analyzer
Clone the repo
git clone --depth 1 https://github.com/cyberelf/agent_skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for polymarket-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyberelf/agent_skills/polymarket-analyzer.svg)](https://agentmods.dev/skills/cyberelf/agent_skills/polymarket-analyzer)
Your own site
<a href="https://agentmods.dev/skills/cyberelf/agent_skills/polymarket-analyzer"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/polymarket-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,062 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.03062
Opus 5 $0.00034 $0.01531
Sonnet 5 $0.00014 $0.00612
Haiku 4.5 $0.00007 $0.00306

Measured 8d ago against content hash 8327e8f202a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

polymarket-analyzer scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/fetch-cn-news.py, scripts/fetch-market-data.py, scripts/filter-markets.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -sSL https://raw.githubusercontent.com/Polymarket/polymarket-cli/main/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sSL https://raw.githubusercontent.com/Polymarket/polymarket-cli/main/install.sh | sh
skills/polymarket-analyzer/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Polymarket + Multi-Source China Market Sentiment Analyzer

Collect data from multiple information channels to support comprehensive sentiment analysis for Chinese concept stocks (中概股) and A-shares.

The agent performs all judgment and interpretation. The scripts in this skill are pure data collectors — they fetch raw information without making directional calls.


When to Use

  • The user asks about Polymarket prediction market data for China/HK topics
  • The user wants sentiment context for A-share or 中概股 investment decisions
  • The user requests multi-source market intelligence (news, macro, market proxies)
  • The user asks about specific stocks: BYD, NIO, Alibaba, Tencent, SMIC, etc.

Prerequisites

Polymarket CLI (required for prediction market data)

brew tap Polymarket/polymarket-cli https://github.com/Polymarket/polymarket-cli
brew install polymarket
# or
curl -sSL https://raw.githubusercontent.com/Polymarket/polymarket-cli/main/install.sh | sh
polymarket --version

yfinance (optional — enables market proxy data)

pip install yfinance

Skill Structure

polymarket-analyzer/
├── SKILL.md
├── references/
│   ├── china_stock_mapping.json        # 21 China concept stocks → A-share sector/ticker mapping
│   ├── signal_weights.json             # Configurable source weights for composite analyzer
│   ├── workflows/
│   │   ├── scenario-1-macro-geopolitical.md  # Top-down macro & geopolitical risk workflow
│   │   ├── scenario-2-sector-catalyst.md     # Bottom-up sector/company catalyst workflow
│   │   └── scenario-3-daily-pulse.md         # Fast daily digest / delta-only briefing
│   └── templates/
│       ├── comprehensive-insight-report.md   # Full deep-dive report template (Scenarios 1 & 2)
│       └── quick-brief.md                    # 30-second pulse template (Scenario 3)
└── scripts/
    ├── polymarket_analyzer.py     # Full 7-source composite analyzer
    ├── query-markets.py           # Polymarket search — active markets only by default
    ├── filter-markets.py          # Polymarket multi-filter — active markets only by default
    ├── fetch-market-data.py       # Raw price/volume for China proxy instruments
    └── fetch-cn-news.py           # Raw headlines from Chinese domestic + global sources

Read the full file on GitHub · 259 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 259 lines · 69 tokens per session scan C 8327e8f202a4

Subscribe to this mod's changes

polymarket-analyzer is a skill published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 13d ago), licensed MIT. It adds 69 tokens to every session and 3,062 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories