Agent skill

lo2cin4bt Backtesting

by lo2cin4 in lo2cin4/lo2cin4bt

Runs and troubleshoots local lo2cin4bt backtests: strategy runs, Parameter Matrix, WFA, rolling validation, frontend startup, payload refresh and generated artifacts.

Custom licenceAuto-check passedBusiness, Finance & HR

Install lo2cin4bt Backtesting

skills CLI
$ npx skills add lo2cin4/lo2cin4bt --skill lo2cin4bt-backtesting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lo2cin4/lo2cin4bt lo2cin4bt-backtesting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lo2cin4/lo2cin4bt.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lo2cin4bt-backtesting .claude/skills/lo2cin4bt-backtesting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lo2cin4bt-backtesting
GitHub stars
288
Token cost
~1.8k tokens
SKILL.md length
739 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Custom licence

At a glance

Runs and troubleshoots local lo2cin4bt backtests: strategy runs, Parameter Matrix, WFA, rolling validation, frontend startup, payload refresh and generated artifacts.

  • Works in 4 steps: Use response_language from the PM packet… → If the user writes in Chinese or asks… → Keep code identifiers, file paths,… → …
  • Running a local strategy_run backtest and checking its generated artifacts
  • SKILL.md covers Purpose, Use When, Inputs and Workflow, plus 12 more sections
  • Calls python and uv

What it does

This is a repo-local skill for operating the lo2cin4bt backtest app. It covers the single app-managed route that takes a normalized config through the persistent Rust engine to validated canonical artifacts and the frontend on port 2424. It is used for local execution, runtime failures, performance checks, output cleanup and checking that completed runs show up in the frontend.

The agent reproduces a problem before diagnosing it, keeps every strategy on the shared engine and checks app, API and frontend evidence end to end. A pre-run checklist confirms the config path, schema version and workflow, provider, symbol, bar specification, session calendar, benchmark, costs and slippage, the metricstracker settings (defaults of 252 for traditional daily assets, 365 for crypto and a 0.04 risk-free rate), a local output path, and that no live trading or broker order path is involved.

Required reads are reference files under skills/lo2cin4bt/references, such as runtime architecture, first run, troubleshooting and the payload contract map. Replies follow the language of the user and switch to Traditional Chinese when the user writes Chinese. Backtests are described as local research artifacts, not investment or trading advice.

When your agent uses it

  • Running a local strategy_run backtest and checking its generated artifacts
  • Troubleshooting a failed WFA or rolling validation run
  • Starting the frontend on port 2424 and refreshing a stale payload
  • Checking a backtest config before a run

Example prompts

  • “Run the strategy config in ./configs/sma-cross.json and tell me whether the frontend shows it.”
  • “My Parameter Matrix run failed halfway through. Find out why.”
  • “Refresh the payload and take a screenshot of the Run Center page.”

Requirements

  • A local checkout of lo2cin4bt with its Rust engine and frontend
  • A backtest config file

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Use response_language from the PM packet when present; otherwise infer it from the latest user message.
  2. If the user writes in Chinese or asks for Chinese, write Traditional Chinese for all non-specialist wording.
  3. Keep code identifiers, file paths, commands, schema keys, agent/skill names, ticker symbols, provider names, and standard finance/quant…
  4. Return response_language in the output packet. When writing repo-local reports, apply the same language policy to the report body.

What it can do on your machine

Read from SKILL.md and the folder at commit d2e0863. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

lo2cin4bt Backtesting loads about 1.8k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 739 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 739 words (~1,755 tokens).

“Operate and diagnose the one app-managed backtest route from normalized config through the persistent Rust engine to validated canonical artifacts and port 2424.”

— opening of SKILL.md by lo2cin4, Custom licence
name
lo2cin4bt-backtesting
version
2.2.1
status
active
category
workflow
use_when
Running or troubleshooting local backtests, Parameter Matrix, WFA, or rolling validation., Checking app-managed artifacts, frontend payloads, screenshots, or…

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/lo2cin4bt-backtesting of lo2cin4/lo2cin4bt.

Open the folder on GitHubat commit d2e0863

Compare with similar skills

lo2cin4bt Backtesting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

lo2cin4bt Backtesting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
lo2cin4bt Backtesting this skilllo2cin4/lo2cin4bt288—~1.8kAutomated safety check: PassCustom licence
Manifoldbt Backtestertradermonty/claude-trading-skills3k—~1.6kAutomated safety check: PassMIT
Trader Backtestruvnet/ruflo74k—~1.4kAutomated safety check: NotesMIT
Rsigmatimescale/rsigma157—~1.2kAutomated safety check: PassMIT
Magicblocksendaifun/skills130—~2.2kAutomated safety check: PassApache-2.0
Multi-Symbol Market Scannertradesdontlie/tradingview-mcp6.8k2 repos~447Automated safety check: PassCustom licence

Similar skills

  • Manifoldbt Backtester

    tradermonty/claude-trading-skills

    Runs a declarative strategy spec over OHLCV bars with the manifoldbt Rust engine, pairs the fill log into round trips, and emits the eight inputs the backtest-expert skill scores.

    3k GitHub stars~1.6k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Trader Backtest

    ruvnet/ruflo

    Run a historical backtest using npx neural-trader with Rust/NAPI engine (8-19x faster) and walk-forward validation; Ed25519-sign the result for paper→live tamper evidence (ADR-126 Phase 4)

    74k GitHub stars~1.4k tokensUpdated today
    Business, Finance & HRAuto-check: notes
  • Rsigma

    timescale/rsigma

    Use the rsigma CLI and MCP server: engine eval, engine daemon, rule lint, rule draft, rule tune, rule backtest, backend convert, mcp serve.

    157 GitHub stars~1.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Magicblock

    sendaifun/skills

    Complete guide for MagicBlock Ephemeral Rollups - high-performance Solana execution with sub-10ms latency, gasless transactions, and Solana Plugins.

    130 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Multi-Symbol Market Scanner

    tradesdontlie/tradingview-mcp

    Scans a list of trading symbols in TradingView for setups, patterns or strategy results and reports them as a ranked comparison table.

    6.8k GitHub starsUsed in 2 repos~447 tokens
    Business, Finance & HRAuto-check passed
  • Pine Script Development Loop

    tradesdontlie/tradingview-mcp

    Runs a write, compile, fix and verify loop for TradingView Pine Script indicators and strategies, pushing code into the Pine Editor and checking it on the chart.

    6.8k GitHub starsUsed in 2 repos~617 tokens
    Business, Finance & HRAuto-check passed

More from lo2cin4/lo2cin4bt

  • Guides an agent through installing, configuring and running local backtests in the lo2cin4bt repo, then explaining the results and fixing setup problems.

    288 GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Runs a pass, revise or block acceptance review on lo2cin4bt work, checking a deliverable against the request, repo contracts, tests, docs and the public GitHub boundary.

    288 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Explains a completed lo2cin4bt backtest run's metrics, equity curve, drawdowns, and costs from canonical artifacts only, without giving trading advice.

    288 GitHub stars~3k tokensUpdated 2 mo ago
    Auto-check passed
  • Lo2cin4bt Pm

    lo2cin4/lo2cin4bt

    Repo-local PM routing skill for lo2cin4bt. An agent skill from lo2cin4/lo2cin4bt.

    288 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Repo-local strategy builder skill for lo2cin4bt. An agent skill from lo2cin4/lo2cin4bt.

    288 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Teaches the lo2cin4bt backtesting product from the repository's own docs and code, in the learner's language, ending each answer with one next step.

    288 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about lo2cin4bt Backtesting

What does lo2cin4bt Backtesting do?

Runs and troubleshoots local lo2cin4bt backtests: strategy runs, Parameter Matrix, WFA, rolling validation, frontend startup, payload refresh and generated artifacts. This is a repo-local skill for operating the lo2cin4bt backtest app. It covers the single app-managed route that takes a normalized config through the persistent Rust engine to validated canonical artifacts and the frontend on port 2424.

When should I use lo2cin4bt Backtesting?

lo2cin4bt Backtesting fits situations like: running a local strategy_run backtest and checking its generated artifacts; troubleshooting a failed WFA or rolling validation run; starting the frontend on port 2424 and refreshing a stale payload; checking a backtest config before a run.

How do I install lo2cin4bt Backtesting in Claude Code?

Run `npx skills add lo2cin4/lo2cin4bt --skill lo2cin4bt-backtesting -a claude-code`. Or copy the skill folder (skills/lo2cin4bt-backtesting in lo2cin4/lo2cin4bt) into .claude/skills/lo2cin4bt-backtesting in your project. Claude Code loads it when a task matches its description.

How do I install lo2cin4bt Backtesting in Codex?

Run `npx skills add lo2cin4/lo2cin4bt --skill lo2cin4bt-backtesting -a codex`. Or copy the skill folder (skills/lo2cin4bt-backtesting in lo2cin4/lo2cin4bt) into .agents/skills/lo2cin4bt-backtesting in your project. Codex loads it when a task matches its description.

Can I use lo2cin4bt Backtesting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lo2cin4/lo2cin4bt --skill lo2cin4bt-backtesting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lo2cin4bt-backtesting, .gemini/skills/lo2cin4bt-backtesting, .github/skills/lo2cin4bt-backtesting and .opencode/skills/lo2cin4bt-backtesting in your project.

What does lo2cin4bt Backtesting need to run?

Going by SKILL.md and its folder, lo2cin4bt Backtesting needs the command-line tools its instructions call (python and uv). Our summary lists: A local checkout of lo2cin4bt with its Rust engine and frontend; A backtest config file.

Does lo2cin4bt Backtesting access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is lo2cin4bt Backtesting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does lo2cin4bt Backtesting use?

lo2cin4bt Backtesting has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does lo2cin4bt Backtesting use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to lo2cin4bt Backtesting?

Skills that share tags, products or a category with lo2cin4bt Backtesting: Manifoldbt Backtester (tradermonty/claude-trading-skills, 3k stars), Trader Backtest (ruvnet/ruflo, 74k stars), Rsigma (timescale/rsigma, 157 stars) and Magicblock (sendaifun/skills, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains lo2cin4bt Backtesting?

lo2cin4 (a GitHub user) maintains it in lo2cin4/lo2cin4bt, which has 288 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 1, 2026.

Source: lo2cin4/lo2cin4bt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.