Market enrichment
Skill yogeshg665/quill-trading-agent/skills/market-enrichment
Derive deterministic market context for a trading run, including portfolio weights and an aggregated daily company-news sentiment summary. WHEN: "enrich the market context", "compute portfolio weights", "summarize the news for my holdings", "add derived metrics", "prepare context for the strategies".From its SKILL.md
npx -y skills add yogeshg665/quill-trading-agent --skill market-enrichmentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.0 KB, 377 tokens by cl100k_base, as published. Nobody here has run it
Market Enrichment
Overview
The enrichment stage attaches derived, deterministic context that strategies consume: per-symbol portfolio weights, total portfolio value, and an aggregated news-sentiment summary for each target symbol. News is fetched through the configured provider (offline by default) and scored with a fixed keyword lexicon.
When to Use
- After intake and before the strategy swarm.
- Do NOT use it to make trade decisions; it only prepares inputs.
Inputs
| Input | Required | Description |
|---|---|---|
context | yes | The TradingContext from intake. |
goals.news_targets | no | Symbols to summarize daily news for. |
Process
- Resolve the news provider from configuration (offline serves the snapshot).
- For each
news_targetssymbol, fetch headlines within the lookback window and score each deterministically to an average sentiment in [-1, 1]. - Compute portfolio weights and total value.
- Merge the derived metrics into
context.enrichment, preserving any caller-provided values.
Outputs
context.enrichment populated with portfolio_weights, total_value, and
news_sentiment (average sentiment, article count, and latest headline per
symbol).
Rationalizations
| Excuse | Rebuttal |
|---|---|
| "Let the model read the news and decide sentiment." | Sentiment must be deterministic; use the fixed lexicon so runs reproduce. |
Red Flags
- A news-sentiment value outside [-1, 1].
- Enrichment that depends on a live network call in the default offline mode.
Verification
- The summarized news-target count matches the available news.
- Re-running on the same snapshot yields identical sentiment values.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.