Skip to content

wenyupapa-sys/tradingagents-codex-skill

tradingagents-codex

Verified

Run the local TradingAgents Codex fork for multi-agent stock and ETF research. Use when the user asks to analyze tickers with TradingAgents, run codex-analyze, batch stock/ETF research, summarize TradingAgents reports, validate the TradingAgents Codex setup, or turn QQQ/TSLA-style full-chain analysis into a repeatable workflow.

FileKindSize
SKILL.mdskill md4.0 KB
agents/openai.yamlconfig242 B
assets/tradingagents-codex-skill-flow.pngbinary1.2 MB
references/troubleshooting.mdmarkdown1.5 KB
references/workflow.mdmarkdown2.1 KB
scripts/check_setup.pyexecutablescript4.2 KB
scripts/quick_validate.pyexecutablescript4.8 KB
scripts/run_analysis.pyexecutablescript5.4 KB
scripts/summarize_report.pyexecutablescript4.0 KB

references/workflow.md

View on GitHub
# TradingAgents Codex Workflow

## Project discovery

Use this order:

1. User-provided `--project`
2. `TRADINGAGENTS_PROJECT`
3. `~/TradingAgents_codex`

Run setup validation before a live analysis:

```bash
SKILL_DIR="${CLAUDE_SKILL_DIR:-${CODEX_HOME:-$HOME/.codex}/skills/tradingagents-codex}"
python3 "$SKILL_DIR/scripts/check_setup.py"
```

## Full-chain vs analysts-only

Use full-chain for portfolio decisions. It runs analyst reports, bull/bear debate, research manager, trader, risk roles, and portfolio manager.

Use `--analysts-only` for a cheaper smoke test or when the user only wants raw analyst perspectives.

## Date choice

If the user does not provide a date, `run_analysis.py` uses the previous likely completed US trading day and skips weekends. It does not model US exchange holidays.

## Dry run

Use `--dry-run` to print the exact command and expected output paths without API calls:

```bash
SKILL_DIR="${CLAUDE_SKILL_DIR:-${CODEX_HOME:-$HOME/.codex}/skills/tradingagents-codex}"
python3 "$SKILL_DIR/scripts/run_analysis.py" \
  --ticker QQQ --ticker TSLA --dry-run
```

## Live run

Use English output for speed, then summarize in Chinese:

```bash
SKILL_DIR="${CLAUDE_SKILL_DIR:-${CODEX_HOME:-$HOME/.codex}/skills/tradingagents-codex}"
python3 "$SKILL_DIR/scripts/run_analysis.py" \
  --ticker QQQ --ticker TSLA \
  --date 2026-05-08 \
  --output-language English \
  --confirm
```

Use Chinese output when the user explicitly needs all role reports translated:

```bash
SKILL_DIR="${CLAUDE_SKILL_DIR:-${CODEX_HOME:-$HOME/.codex}/skills/tradingagents-codex}"
python3 "$SKILL_DIR/scripts/run_analysis.py" \
  --ticker QQQ \
  --date 2026-05-08 \
  --output-language Chinese
```

## Report layout

Expected run directory:

```text
<project>/codex_runs/<TICKER>/<YYYY-MM-DD>/
```

Final decision:

```text
<run-dir>/reports/portfolio_manager.json
```

Complete Markdown report:

```text
<run-dir>/reports/complete_report.md
```

## Summarization

```bash
SKILL_DIR="${CLAUDE_SKILL_DIR:-${CODEX_HOME:-$HOME/.codex}/skills/tradingagents-codex}"
python3 "$SKILL_DIR/scripts/summarize_report.py" \
  --ticker TSLA \
  --date 2026-05-08
```

Use `--output json` for automation.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall