agentleFS
Sign inStart free
YichengYang-EthanYichengYang-Ethan/oracle3/.claude/skills/pm-data-discovery/SKILL.md

pm-data-discovery

Skill466 starsChanged 34 days agoApache-2.0View on GitHub

Find out what prediction-market data is available, locate the target markets, and save research samples to files. Data discovery and collection only; no strategy hypotheses.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to look at data, find markets, or collect research samples before any strategy work.

    line 8
  2. Very specific:

    Use market search or market list to define the candidate markets.

    line 47
  3. Distinctive:

    Every conclusion comes with a command that reproduces it.

    line 55
  4. Very specific:

    If the network is unavailable, switch to the local research commands instead of stopping.

    line 56
  5. Distinctive:

    Do not propose strategy logic in this skill.

    line 60
  6. Distinctive:

    Only discover, filter, sample and save data.

    line 61
  7. Very specific:

    Prefer --json output so that later agents can consume it.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PM Data Discovery

Use this skill when the user wants to look at data, find markets, or collect research samples before any strategy work.

Goals

Answer three questions:

  • Which data sources are available?
  • How do I find the target markets?
  • How do I save the data as files that later strategy research can use?

Data entry points

  1. Market metadata and search (online)
  • oracle3 market list --exchange polymarket --limit 50 --json
  • oracle3 market search --exchange polymarket --query "<keyword>" --limit 50 --json
  • oracle3 market info --exchange polymarket --market-id <market_id> --json
  • oracle3 market history --market-id <market_id> --interval 1h --limit 500 --json
  1. News and external events (online)
  • oracle3 news fetch --source google --query "<keyword>" --limit 30 --json
  • oracle3 news fetch --source rss --query "<keyword>" --limit 30 --json
  1. Local history files (offline)
  • oracle3 research markets --history-file <history.jsonl> --sort-by points --limit 50 --json
  • oracle3 research slice --history-file <history.jsonl> --market-id <M> --event-id <E> --output <slice.jsonl> --json
  1. Raw stream recording (online)
  • oracle3 data record --exchange polymarket --output <events.jsonl> --duration 3600 --json
  1. Through the MCP server (oracle3-mcp)
  • search_markets, get_market, get_orderbook, get_quote for Kalshi and Polymarket.

Recommended flow

  1. Use market search or market list to define the candidate markets.
  2. Pull market info and market history for the candidates to check liquidity and price behavior.
  3. For offline research, record with data record or use an existing history file.
  4. Produce slices of the key markets for the strategy agent to read.

Output requirements

  • A clear data inventory: markets, time range, file paths.
  • Every conclusion comes with a command that reproduces it.
  • If the network is unavailable, switch to the local research commands instead of stopping.

Hard rules

  • Do not propose strategy logic in this skill.
  • Only discover, filter, sample and save data.
  • Prefer --json output so that later agents can consume it.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free