agentsclimarketplace

Trade reporting

Skill yogeshg665/quill-trading-agent/skills/trade-reporting

Produce an audit-ready report with a per-order reasoning trail, decision counts, execution outcomes, and a deterministic narrative. WHEN: "summarize the run", "explain the decisions", "produce the trade report", "audit trail", "what did the agent do and why", "report the executions".From its SKILL.md

Install
npx -y skills add yogeshg665/quill-trading-agent --skill trade-reporting

Assembled 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

1.9 KB, 367 tokens by cl100k_base, as published. Nobody here has run it

Trade Reporting

Overview

The final stage. It assembles a structured, audit-ready report: per-order decisions with their findings, decision counts, execution outcomes, and an explicit reasoning trail. A deterministic narrative is always produced; an optional language model may refine the wording without changing any fact.

When to Use

  • After execution, to close out the run.
  • Do NOT let the optional model add facts not present in the decisions.

Inputs

InputRequiredDescription
decisionsyesThe TradeDecision list.
executionsyesThe ExecutionReport list.
contextyesThe run context for portfolio value and metadata.

Process

  1. For each decision, record the symbol, side, quantity, strategy, notional, outcome, risk score, and findings.
  2. Build a reasoning trail with one explicit line per decision.
  3. Summarize decision counts by outcome and the number of filled orders.
  4. Generate a deterministic narrative; optionally refine it with a model.

Outputs

A report dictionary with run_id, counts, per-decision detail, executions, a reasoning trail, and a narrative. Optionally written to an output directory.

Rationalizations

ExcuseRebuttal
"Let the model summarize freely."The narrative may be refined, but every fact must come from the decisions.

Red Flags

  • A report whose counts disagree with the decisions.
  • A narrative claiming a fill that did not occur.

Verification

  • The report's counts match the decisions and executions.
  • The reasoning trail has one line per decision and cites the findings.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,452. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.