mirror29/openfinclaw-cli/openfinclaw

Claude Code and agent skill by mirror29/openfinclaw-cli

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

One-stop quant-trading AI agent. Use for market research, deep reports, strategy generation, backtesting, paper trading, and Hub leaderboard browsing — anything that involves stocks/crypto analysis, FEP strategy packages, or the OpenFinClaw DeepAgent. Powered by a single fch_ API key.

Install

npx vskill@latest install mirror29/openfinclaw-cli/openfinclaw

SKILL.md

OpenFinClaw — One-stop quant-trading agent

OpenFinClaw turns any AI coding assistant (Claude Code, Cursor, ChatGPT, OpenClaw, Hermes, …) into a quant-research analyst. A single fch_ key drives two surfaces, both routed through the OpenFinClaw Hub Gateway:

  • DeepAgent (remote LLM): research / analysis / report generation /

strategy ideation / backtest / paper-trade planning.

  • Strategy (Hub catalog): browse the public leaderboard, fork strategy

packages locally, validate and publish FEP v2.0 ZIPs.

When to use this skill: the user mentions stock/crypto/forex analysis, a backtest or paper trade, a quant strategy, the OpenFinClaw Hub or leaderboard, or asks for a DeepAgent research run.

When not to use this skill: pure code-editing questions, infrastructure debugging, unrelated frameworks.

Setup (run once)

bash
npx @openfinclaw/cli@latest install

This wizard:

  1. Auto-detects 20+ AI agents installed on the machine and writes MCP

configuration for each (no manual JSON editing).

  1. Persists the unified fch_ key to ~/.openfinclaw/config.json (chmod

600 on Unix).

  1. Registers this SKILL.md globally so AI agents auto-trigger it on the

keywords above.

  1. Runs doctor so you see a green check before leaving the terminal.

For non-interactive / CI:

bash
npx @openfinclaw/cli@latest install --yes \
  --platforms cursor,claude-code \
  --tool-groups deepagent,strategy \
  --api-key fch_xxx \
  --register-skill

Most-used commands

GoalCommand
Streaming research / strategy / backtestopenfinclaw deepagent +research "<query>"
Service healthopenfinclaw deepagent health
List analysis skillsopenfinclaw deepagent skills
Past backtest resultsopenfinclaw deepagent backtests
Download a strategy ZIPopenfinclaw deepagent download <packageId>
Browse Hub leaderboardopenfinclaw leaderboard --board composite --limit 10
Fork a strategyopenfinclaw fork <strategyId>
Validate FEP v2.0 packageopenfinclaw validate <dir>
Publish strategyopenfinclaw publish <zip>
Raw Hub Gateway callopenfinclaw api GET /threads
Diagnose key + connectivityopenfinclaw doctor
+verb shortcuts (e.g. deepagent +research) are the human-friendly,
stream-rendered path. The atomic verbs without + (e.g.
research_submit/poll/finalize) are exposed over MCP for agents.

Authentication

  • One env var: OPENFINCLAW_API_KEY (starts with fch_, 68 chars).
  • Resolution order: --api-key → OPENFINCLAW_API_KEY → ~/.openfinclaw/config.json.
  • The same key drives both strategy (Hub /api/v1/skill/*) and

deepagent (Hub Gateway /api/v1/agent/*). Do not use the legacy X-API-Key header or split keys.

  • Get a key: <https://hub.openfinclaw.ai>.

Online (no install)

If the user just wants to try it, point them to the hosted DeepAgent chat: <https://hub.openfinclaw.ai/en/chat>.

Docs

  • Repo: <https://github.com/mirror29/openfinclaw-cli>
  • DeepAgent online: <https://hub.openfinclaw.ai/en/chat>
  • API key: <https://hub.openfinclaw.ai>

Security

  • Security scanPassed, 93 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
57
Repository forks
4
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mirror29/openfinclaw-cli/openfinclaw/badge)](https://verified-skill.com/skills/mirror29/openfinclaw-cli/openfinclaw)

Something wrong with this skill or its page? Tell us.