hermes-agent/skills/research/polymarket/SKILL.md
teknium1 732c66b0f3 refactor: reorganize skills into sub-categories
The skills directory was getting disorganized — mlops alone had 40
skills in a flat list, and 12 categories were singletons with just
one skill each.

Code change:
- prompt_builder.py: Support sub-categories in skill scanner.
  skills/mlops/training/axolotl/SKILL.md now shows as category
  'mlops/training' instead of just 'mlops'. Backwards-compatible
  with existing flat structure.

Split mlops (40 skills) into 7 sub-categories:
- mlops/training (12): accelerate, axolotl, flash-attention,
  grpo-rl-training, peft, pytorch-fsdp, pytorch-lightning,
  simpo, slime, torchtitan, trl-fine-tuning, unsloth
- mlops/inference (8): gguf, guidance, instructor, llama-cpp,
  obliteratus, outlines, tensorrt-llm, vllm
- mlops/models (6): audiocraft, clip, llava, segment-anything,
  stable-diffusion, whisper
- mlops/vector-databases (4): chroma, faiss, pinecone, qdrant
- mlops/evaluation (5): huggingface-tokenizers,
  lm-evaluation-harness, nemo-curator, saelens, weights-and-biases
- mlops/cloud (2): lambda-labs, modal
- mlops/research (1): dspy

Merged singleton categories:
- gifs → media (gif-search joins youtube-content)
- music-creation → media (heartmula, songsee)
- diagramming → creative (excalidraw joins ascii-art)
- ocr-and-documents → productivity
- domain → research (domain-intel)
- feeds → research (blogwatcher)
- market-data → research (polymarket)

Fixed misplaced skills:
- mlops/code-review → software-development (not ML-specific)
- mlops/ml-paper-writing → research (academic writing)

Added DESCRIPTION.md files for all new/updated categories.
2026-03-09 03:35:53 -07:00

76 lines
3 KiB
Markdown

---
name: polymarket
description: Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
version: 1.0.0
author: Hermes Agent + Teknium
tags: [polymarket, prediction-markets, market-data, trading]
---
# Polymarket — Prediction Market Data
Query prediction market data from Polymarket using their public REST APIs.
All endpoints are read-only and require zero authentication.
See `references/api-endpoints.md` for the full endpoint reference with curl examples.
## When to Use
- User asks about prediction markets, betting odds, or event probabilities
- User wants to know "what are the odds of X happening?"
- User asks about Polymarket specifically
- User wants market prices, orderbook data, or price history
- User asks to monitor or track prediction market movements
## Key Concepts
- **Events** contain one or more **Markets** (1:many relationship)
- **Markets** are binary outcomes with Yes/No prices between 0.00 and 1.00
- Prices ARE probabilities: price 0.65 means the market thinks 65% likely
- `outcomePrices` field: JSON-encoded array like `["0.80", "0.20"]`
- `clobTokenIds` field: JSON-encoded array of two token IDs [Yes, No] for price/book queries
- `conditionId` field: hex string used for price history queries
- Volume is in USDC (US dollars)
## Three Public APIs
1. **Gamma API** at `gamma-api.polymarket.com` — Discovery, search, browsing
2. **CLOB API** at `clob.polymarket.com` — Real-time prices, orderbooks, history
3. **Data API** at `data-api.polymarket.com` — Trades, open interest
## Typical Workflow
When a user asks about prediction market odds:
1. **Search** using the Gamma API public-search endpoint with their query
2. **Parse** the response — extract events and their nested markets
3. **Present** market question, current prices as percentages, and volume
4. **Deep dive** if asked — use clobTokenIds for orderbook, conditionId for history
## Presenting Results
Format prices as percentages for readability:
- outcomePrices `["0.652", "0.348"]` becomes "Yes: 65.2%, No: 34.8%"
- Always show the market question and probability
- Include volume when available
Example: `"Will X happen?" — 65.2% Yes ($1.2M volume)`
## Parsing Double-Encoded Fields
The Gamma API returns `outcomePrices`, `outcomes`, and `clobTokenIds` as JSON strings
inside JSON responses (double-encoded). When processing with Python, parse them with
`json.loads(market['outcomePrices'])` to get the actual array.
## Rate Limits
Generous — unlikely to hit for normal usage:
- Gamma: 4,000 requests per 10 seconds (general)
- CLOB: 9,000 requests per 10 seconds (general)
- Data: 1,000 requests per 10 seconds (general)
## Limitations
- This skill is read-only — it does not support placing trades
- Trading requires wallet-based crypto authentication (EIP-712 signatures)
- Some new markets may have empty price history
- Geographic restrictions apply to trading but read-only data is globally accessible