Market enrichment
Skill yogeshg665/quill-trading-agent/skills/market-enrichment
Quill - Deterministic, risk-governed multi-agent trading engine for US equities. A strategy swarm proposes orders; an independent risk guardian has final say. Paper mode by default, gated live Robinhood MCP execution.
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.
What its author says it does
Copied from the file, not written here
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".
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.
Gives 0 of the 12 instructions most note taking skills give in 377 tokens
Counted across 686 of the 876 authors here whose files we hold, read 2026-08-07
- include a visual element on every slidein 44 of 686, across 13 files
- use wikilinks for internal vault linksin 36 of 686, across 12 files
- commit to a single visual motif across every slidein 34 of 686, across 9 files
- use subagents to visually inspect rendered slidesin 31 of 686, across 7 files
- read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
- keep 0.5 inch minimum marginsin 30 of 686, across 7 files
- re-verify affected slides after every fixin 27 of 686, across 5 files
- run content QA checks before declaring successin 26 of 686, across 3 files
- Use Markdown links for external URLs onlyin 26 of 686, across 11 files
- pick a bold topic specific color palettein 24 of 686, across 2 files
- read editing guide before editing existing presentationsin 23 of 686, across 1 file
- use one dominant color across all slidesin 23 of 686, across 1 file
Said here and by no other author read
- use after intake and before strategies
- resolve the news provider from configuration
- fetch headlines for each target symbol
- score sentiment deterministically using the fixed lexicon
- compute portfolio weights and total value
- merge derived metrics into context.enrichment
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.