Agent skill

Strategy Coder

by YicunAI in YicunAI/Pnlclaw-community

Generate valid EngineStrategyConfig YAML for PnLClaw strategies

AGPL-3.0Auto-check passedBusiness, Finance & HR

Install Strategy Coder

skills CLI
$ npx skills add YicunAI/Pnlclaw-community --skill strategy-coder -a claude-code

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

GitHub CLI
$ gh skill install YicunAI/Pnlclaw-community strategy-coder --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/YicunAI/Pnlclaw-community.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/strategy-coder .claude/skills/strategy-coder && 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
strategy-coder
GitHub stars
197
Token cost
~1.2k tokens
SKILL.md length
161 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate valid EngineStrategyConfig YAML for PnLClaw strategies

  • Works in 5 steps: Always use indicators from the Available… → Entry rules and exit rules must use… → Always include risk_params with at least… → …
  • Business, Finance & HR work in your project
  • SKILL.md covers EngineStrategyConfig Schema, Available Indicators, Template: SMA Crossover and Template: RSI Reversal, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Strategy Coder is an agent skill from YicunAI/Pnlclaw-community. Generate valid EngineStrategyConfig YAML for PnLClaw strategies

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR. The repository describes itself as: PnLClaw — local-first crypto and prediction market quant engine. The licence is AGPL-3.0.

When your agent uses it

  • Business, Finance & HR work in your project

Example prompts

  • “/strategy-coder”

Workflow steps

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

  1. Always use indicators from the Available Indicators table
  2. Entry rules and exit rules must use matching directions (long entry needs close_long exit)
  3. Always include risk_params with at least stop_loss_pct
  4. After generating, call strategy_validate to verify correctness
  5. Use crosses_above/crosses_below for crossover strategies, greater_than/less_than for threshold strategies

What it can do on your machine

Read from SKILL.md and the folder at commit 933014f. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

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

  • Network

    No URLs in SKILL.md.

    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

Strategy Coder loads about 1.2k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 161 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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

The full file from YicunAI/Pnlclaw-community at commit 933014f, republished under its AGPL-3.0 licence (© YicunAI). 161 words, ~1,209 tokens.

Download SKILL.mdSave it as .claude/skills/strategy-coder/SKILL.md (or your agent's skills folder).
name
strategy-coder
description
Generate valid EngineStrategyConfig YAML for PnLClaw strategies
version
1.0
tags
strategy, coding, yaml

Strategy Coder

You are a PnLClaw strategy coding expert. Generate valid EngineStrategyConfig YAML configurations.

EngineStrategyConfig Schema

yaml
id: string          # Unique ID, e.g. "strat-abc123"
name: string        # Human-readable name
type: enum          # sma_cross | rsi_reversal | macd | custom
description: string # Optional description
symbols:            # List of trading pairs
  - BTC/USDT
interval: string    # 1m | 5m | 15m | 30m | 1h | 4h | 1d | 1w
direction: enum     # long_only | short_only | neutral (default: long_only)

entry_rules:
  long:             # List of ConditionRule (all must be true to enter long)
    - indicator: string
      params: {period: int, ...}
      operator: string   # crosses_above | crosses_below | greater_than | less_than | equal
      comparator: float | {indicator: string, params: {...}}
  short: []         # Same structure for short entries

exit_rules:
  close_long: []    # Conditions to close long positions
  close_short: []   # Conditions to close short positions

risk_params:
  stop_loss_pct: float    # 0.0-1.0, e.g. 0.02 = 2%
  take_profit_pct: float  # 0.0-1.0, e.g. 0.05 = 5%
  max_position_pct: float # Fraction of portfolio, default 0.1
  max_open_positions: int # Default 1

Available Indicators

IndicatorParamsOutput
smaperiod: intSimple Moving Average
emaperiod: intExponential Moving Average
rsiperiod: intRelative Strength Index (0-100)
macdfast_period: int, slow_period: int, signal_period: intMACD line value
macd_signalsame as macdSignal line value
macd_histogramsame as macdHistogram (macd - signal)
bbandsperiod: int, std_dev: floatMiddle Bollinger Band (SMA)
bbands_uppersame as bbandsUpper Band (SMA + std_dev × σ)
bbands_middlesame as bbandsMiddle Band (SMA)
bbands_lowersame as bbandsLower Band (SMA - std_dev × σ)

Template: SMA Crossover

yaml
id: template-sma-cross
name: SMA Crossover
type: sma_cross
symbols: [BTC/USDT]
interval: 1h
entry_rules:
  long:
    - indicator: sma
      params: {period: 20}
      operator: crosses_above
      comparator: {indicator: sma, params: {period: 50}}
exit_rules:
  close_long:
    - indicator: sma
      params: {period: 20}
      operator: crosses_below
      comparator: {indicator: sma, params: {period: 50}}
risk_params:
  stop_loss_pct: 0.03
  take_profit_pct: 0.06

Template: RSI Reversal

yaml
id: template-rsi-reversal
name: RSI Reversal
type: rsi_reversal
symbols: [BTC/USDT]
interval: 1h
entry_rules:
  long:
    - indicator: rsi
      params: {period: 14}
      operator: less_than
      comparator: 30
exit_rules:
  close_long:
    - indicator: rsi
      params: {period: 14}
      operator: greater_than
      comparator: 70
risk_params:
  stop_loss_pct: 0.02
  take_profit_pct: 0.05

Template: MACD Momentum

yaml
id: template-macd-momentum
name: MACD Momentum
type: macd
symbols: [BTC/USDT]
interval: 1h
parameters: {fast_period: 12, slow_period: 26, signal_period: 9}
entry_rules:
  long:
    - indicator: macd
      params: {fast_period: 12, slow_period: 26, signal_period: 9}
      operator: crosses_above
      comparator: {indicator: macd_signal, params: {fast_period: 12, slow_period: 26, signal_period: 9}}
exit_rules:
  close_long:
    - indicator: macd
      params: {fast_period: 12, slow_period: 26, signal_period: 9}
      operator: crosses_below
      comparator: {indicator: macd_signal, params: {fast_period: 12, slow_period: 26, signal_period: 9}}
risk_params:
  stop_loss_pct: 0.03
  take_profit_pct: 0.08

Template: Bollinger Breakout

yaml
id: template-bollinger-breakout
name: Bollinger Breakout
type: custom
symbols: [BTC/USDT]
interval: 1h
parameters: {bb_period: 20, bb_std: 2.0}
entry_rules:
  long:
    - indicator: sma
      params: {period: 1}
      operator: crosses_above
      comparator: {indicator: bbands_upper, params: {period: 20}}
exit_rules:
  close_long:
    - indicator: sma
      params: {period: 1}
      operator: crosses_below
      comparator: {indicator: bbands_middle, params: {period: 20}}
risk_params:
  stop_loss_pct: 0.02
  take_profit_pct: 0.06

Rules

  1. Always use indicators from the Available Indicators table
  2. Entry rules and exit rules must use matching directions (long entry needs close_long exit)
  3. Always include risk_params with at least stop_loss_pct
  4. After generating, call strategy_validate to verify correctness
  5. Use crosses_above/crosses_below for crossover strategies, greater_than/less_than for threshold strategies

© YicunAI, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/strategy-coder of YicunAI/Pnlclaw-community.

Open the folder on GitHubat commit 933014f

Compare with similar skills

Strategy Coder 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.

Strategy Coder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Strategy Coder this skillYicunAI/Pnlclaw-community197—~1.2kAutomated safety check: PassAGPL-3.0
Technical Analysttradermonty/claude-trading-skills3k5 repos~4.6kAutomated safety check: PassMIT
Creating Financial ModelsChen-zexi/open-ptc-agent7294 repos~1.3kAutomated safety check: PassMIT
Stock APIzhangxiangliang/stock-api2k—~507Automated safety check: PassMIT
Theme Detectortradermonty/claude-trading-skills3k2 repos~4.9kAutomated safety check: PassMIT
Itr Walakaranb192/itr-wala871—~3.6kAutomated safety check: PassMIT

Similar skills

  • Technical Analyst

    tradermonty/claude-trading-skills

    This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.

    3k GitHub starsUsed in 5 repos~4.6k tokens
    Business, Finance & HRAuto-check passed
  • Creating Financial Models

    Chen-zexi/open-ptc-agent

    This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

    729 GitHub starsUsed in 4 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Stock API

    zhangxiangliang/stock-api

    Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.

    2k GitHub stars~507 tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Theme Detector

    tradermonty/claude-trading-skills

    Detect and analyze trending market themes across sectors. An agent skill from tradermonty/claude-trading-skills.

    3k GitHub starsUsed in 2 repos~4.9k tokens
    Business, Finance & HRAuto-check passed
  • Itr Wala

    karanb192/itr-wala

    File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27.

    871 GitHub stars~3.6k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed
  • Tushare Data

    zillionare/zillionare

    面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

    319 GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed

More from YicunAI/Pnlclaw-community

All 8 skills in this repo
  • Backtest Explain

    YicunAI/Pnlclaw-community

    Analyzes backtest results in plain language, connecting metrics to what they mean for the strategy

    197 GitHub stars~378 tokensUpdated 6 mo ago
    Auto-check passed
  • Exchange Setup

    YicunAI/Pnlclaw-community

    Guides the user through exchange connectivity and configuration safely, without handling secrets in chat

    197 GitHub stars~394 tokensUpdated 6 mo ago
    Auto-check passed
  • Indicator Guide

    YicunAI/Pnlclaw-community

    Explains common technical indicators (SMA, EMA, RSI, MACD) with quantitative intuition and example calculations

    197 GitHub stars~389 tokensUpdated 6 mo ago
    Auto-check passed
  • Market Analysis

    YicunAI/Pnlclaw-community

    Analyzes current market state and short-term trends using ticker, candle, and narrative context

    197 GitHub stars~364 tokensUpdated 6 mo ago
    Auto-check passed
  • Pnl Explain

    YicunAI/Pnlclaw-community

    Explains profit and loss composition and attribution for paper accounts using engine-calculated breakdowns

    197 GitHub stars~339 tokensUpdated 6 mo ago
    Auto-check passed
  • Risk Report

    YicunAI/Pnlclaw-community

    Generates a risk assessment for current or hypothetical positions using engine rules and paper state

    197 GitHub stars~375 tokensUpdated 6 mo ago
    Auto-check passed

Questions about Strategy Coder

What does Strategy Coder do?

Generate valid EngineStrategyConfig YAML for PnLClaw strategies. Strategy Coder is an agent skill from YicunAI/Pnlclaw-community.

When should I use Strategy Coder?

Strategy Coder fits situations like: business, Finance & HR work in your project.

How do I install Strategy Coder in Claude Code?

Run `npx skills add YicunAI/Pnlclaw-community --skill strategy-coder -a claude-code`. Or copy the skill folder (skills/strategy-coder in YicunAI/Pnlclaw-community) into .claude/skills/strategy-coder in your project. Claude Code loads it when a task matches its description.

How do I install Strategy Coder in Codex?

Run `npx skills add YicunAI/Pnlclaw-community --skill strategy-coder -a codex`. Or copy the skill folder (skills/strategy-coder in YicunAI/Pnlclaw-community) into .agents/skills/strategy-coder in your project. Codex loads it when a task matches its description.

Can I use Strategy Coder 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 YicunAI/Pnlclaw-community --skill strategy-coder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/strategy-coder, .gemini/skills/strategy-coder, .github/skills/strategy-coder and .opencode/skills/strategy-coder in your project.

What does Strategy Coder need to run?

SKILL.md names no scripts, command-line tools or credentials: Strategy Coder is instructions for the agent only.

Does Strategy Coder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Strategy Coder 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 Strategy Coder use?

Strategy Coder is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Strategy Coder use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Strategy Coder?

Skills that share tags, products or a category with Strategy Coder: Technical Analyst (tradermonty/claude-trading-skills, 3k stars), Creating Financial Models (Chen-zexi/open-ptc-agent, 729 stars), Stock API (zhangxiangliang/stock-api, 2k stars) and Theme Detector (tradermonty/claude-trading-skills, 3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Strategy Coder?

YicunAI (a GitHub user) maintains it in YicunAI/Pnlclaw-community, which has 197 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on April 8, 2026.

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