Skip to content
Agentmart
Submit a tool

backtest-leader-board

Show the agent leaderboard ranking top-performing agents by backtest return percentage.

Skill by scom-repos

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/scom-repos-backtest-leader-board

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Show the agent leaderboard ranking top-performing agents by backtest return percentage. Use when the user asks about leaderboard, rankings, best agents, or top performers. Supports filtering by chain, pair, mode, and market type.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/backtest-leader-board

What's inside

Skill name
backtest-leader-board
Description
Show the agent leaderboard ranking top-performing agents by backtest return percentage. Use when the user asks about leaderboard, rankings, best agents, or top performers. Supports filtering by chain, pair, mode, and market type.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Backtest Leaderboard

Follow these steps to show the backtest leaderboard.

## Step 1 — Determine the lookback period

Ask the user which lookback period they want to see, or infer from their message. These are lookback windows (how far back the backtest covers):

- **daily** / **1d** — backtest over the last 1 day
- **weekly** / **1w** — backtest over the last 7 days
- **monthly** / **1m** — backtest over the last 30 days

If the user asks for multiple periods, call the tool once per period.

## Step 2 — Determine optional filters

Ask the user if they want to filter the leaderboard by:

- **Blockchain chain** — filter by specific network (e.g., Ethereum, BSC, Arbitrum). Pass the chain ID (e.g., 1 for Ethereum, 56 for BSC).
- **Trading pair** — filter by pair symbol (e.g., "ETH/USDC", "BTC/USDT"). Pass the symbol string.
- **Trading mode** — filter by live or paper trading ("live" or "paper").
- **Market type** — filter by spot or perpetual futures ("spot" or "perp").

If the user specifies any filters, include them in the tool call. Otherwise, show the global leaderboard across all filters.

## Step 3 — Fetch the leaderboard

Call `backtest_leader_board` with the chosen `period`, optional `limit` (default 10), and any filters specified in Step 2.

Each leaderboard entry includes the agent identifier as `agent_id` / `agentId`. Treat that as required output when summarizing results for the user.

If the response contains no data, inform the user that no completed backtests are available for that period/filter combination yet.

## Step 4 — Present results

Start with a title: **Agent's backtest leaderboard ({lookback_time}{filters}) with total return - top {N}** where:
- `{lookback_time}` is "1-day lookback", "7-day lookback", or "30-day lookback"
- `{filters}` shows active filters if any (e.g., " · Ethereum · ETH/USDC · Live")
- `{N}` is the number of results

Do NOT use a markdown table. For each agent, show: rank, name, symbol, and return %. Add a blank line between each agent. Keep it concise.
Always include the agent ID next to the name, for example: `#1 Agent 3027 — Trend Follower · ETH/USDC · +12.4%`.

From scom-repos/openclaw-trading-plugin, MIT.

Signals

Stars
2
Forks
2
Open issues
0
Last commit (this folder)
May 12, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from scom-repos

Cite this page

backtest-leader-board skill. Agent Mart. https://agentmart.dev/skills/scom-repos-backtest-leader-board (last updated 2026-10-24)