A skill your agent uses when writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout, momentum, trend following, 12-hour high, range expansion, riding new…

MITAuto-check passedBusiness, Finance & HR

Install Breakout

skills CLI
$ npx skills add Superior-Trade/superior-skills --skill breakout -a claude-code

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

GitHub CLI
$ gh skill install Superior-Trade/superior-skills breakout --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/Superior-Trade/superior-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/breakout .claude/skills/breakout && 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
breakout
GitHub stars
214
Token cost
~1.5k tokens
SKILL.md length
449 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout, momentum, trend following, 12-hour high, range expansion, riding new…

  • Works in 4 steps: Long-only in downtrends. As shown by the… → process_only_new_candles = False.… → Conflict between minimal_roi and… → …
  • Writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout
  • SKILL.md covers When to use, Honest framing, Backtest reference and Reference implementation, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Breakout is an agent skill from Superior-Trade/superior-skills. Use when writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout, momentum, trend following, 12-hour high, range expansion, riding new highs, Donchian breakout. Note this template was unprofitable in our reference backtest (long-only in a -13% market); explain regime sensitivity to the user.

Its SKILL.md is about 1.5k 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, covering Trading and backtesting. It works with Circle USDC. The repository describes itself as: Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid. The licence is MIT.

When your agent uses it

  • Writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout
  • Trend following
  • Range expansion
  • Riding new highs

Example prompts

  • “/breakout”

Requirements

  • Python 3

Workflow steps

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

  1. Long-only in downtrends. As shown by the reference. Add a regime filter or accept the strategy will lose money in bear markets.
  2. process_only_new_candles = False. Default True is correct here; setting it false fires on every tick during backtest dry-run and…
  3. Conflict between minimal_roi and trailing stop. Setting minimal_roi: { "0": 0.05 } exits at +5% before the trailing stop activates at…
  4. startup_candle_count too small for ATR-14. ATR needs 14 bars of warmup; the default 30 is fine. If you switch to ATR-100, bump startup to…

What it can do on your machine

Read from SKILL.md and the folder at commit 9d41db5. 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 python and json).

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

  • Network

    Links to these hosts (documentation or services it may open):

    • freqtrade.io

    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

Breakout loads about 1.5k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 449 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 Superior-Trade/superior-skills at commit 9d41db5, republished under its MIT licence (© Superior-Trade). 449 words, ~1,480 tokens.

Download SKILL.mdSave it as .claude/skills/breakout/SKILL.md (or your agent's skills folder).
name
breakout
description
Use when writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout, momentum, trend following, 12-hour high, range expansion, riding new highs, Donchian breakout. Note this template was unprofitable in our reference backtest (long-only in a -13% market); explain regime sensitivity to the user.
metadata.version
0.1.0
metadata.updated
2026-05-07

Strategy: Momentum · Breakout

When to use

A user asks for "breakout", "momentum", "trend following", "buy new highs", "Donchian breakout", "range expansion". Single or multi-pair, hour-scale, with a trailing stop.

Honest framing

The reference backtest was unprofitable (36% WR, −0.95% PnL) on BTC/USDC:USDC 1h Jan-May 2026 — but BTC fell −13% in that window. Long-only breakouts in a downtrend are structurally a losing setup. The strategy is correct; the regime was wrong.

Two practical paths to make this work:

  • Add a regime filter (e.g. only enter when close > ema_200 on the higher timeframe).
  • Run on a wider, multi-pair scan so trending alts contribute even when BTC is weak.

Backtest reference

WindowBTC/USDC:USDC 1h, 2026-01-01 → 2026-05-01 (BTC −13%)
Trades64
Win rate36%
Wallet PnL−0.95%
Backtest ID01kqypw5bqsaezpgm8pxcrpvyb

Trailing stop kept losses small per trade, but the entry signal fired into too many failed breakouts in a downtrend. Re-run on Q4 2025 or a trending alt to see the strategy in its native regime.

Reference implementation

python
from freqtrade.strategy import IStrategy
import pandas as pd
import talib.abstract as ta


class MomentumBreakoutStrategy(IStrategy):
    minimal_roi = {"0": 100.0}   # let trailing stop manage exits
    stoploss = -0.05
    trailing_stop = True
    trailing_stop_positive = 0.015
    trailing_stop_positive_offset = 0.025
    trailing_only_offset_is_reached = True
    timeframe = "1h"
    process_only_new_candles = True
    startup_candle_count = 30
    can_short = False

    def populate_indicators(self, dataframe: pd.DataFrame, metadata: dict) -> pd.DataFrame:
        dataframe["high_12h"] = dataframe["high"].rolling(12).max().shift(1)
        dataframe["low_6h"] = dataframe["low"].rolling(6).min().shift(1)
        dataframe["vol_avg20"] = dataframe["volume"].rolling(20).mean()
        dataframe["atr_14"] = ta.ATR(dataframe, timeperiod=14)
        return dataframe

    def populate_entry_trend(self, dataframe: pd.DataFrame, metadata: dict) -> pd.DataFrame:
        # Break the prior 12h high on above-average volume.
        dataframe.loc[
            (dataframe["close"] > dataframe["high_12h"])
            & (dataframe["volume"] > dataframe["vol_avg20"]),
            "enter_long",
        ] = 1
        return dataframe

    def populate_exit_trend(self, dataframe: pd.DataFrame, metadata: dict) -> pd.DataFrame:
        # Break the prior 6h low → exit (momentum failed).
        dataframe.loc[(dataframe["close"] < dataframe["low_6h"]), "exit_long"] = 1
        return dataframe

Config requirements

json
{
  "exchange": { "name": "hyperliquid", "pair_whitelist": ["BTC/USDC:USDC"] },
  "stake_currency": "USDC",
  "stake_amount": 100,
  "timeframe": "1h",
  "max_open_trades": 1,
  "stoploss": -0.05,
  "minimal_roi": { "0": 100.0 },
  "trading_mode": "futures",
  "margin_mode": "cross",
  "trailing_stop": true,
  "trailing_stop_positive": 0.015,
  "trailing_stop_positive_offset": 0.025,
  "trailing_only_offset_is_reached": true,
  "entry_pricing": { "price_side": "same" },
  "exit_pricing": { "price_side": "same" },
  "pairlists": [{ "method": "StaticPairList" }]
}

The trailing-stop block is what makes this template worth keeping — it locks in profits once a breakout extends past +2.5%, then trails 1.5% behind.

Tunable parameters

KnobEffect
12 (rolling high length)Shorter (6) → more entries, lower-quality breakouts. Longer (24) → fewer, higher-conviction.
volume > vol_avg20Stricter (> vol_avg20 × 1.5) → only volume-confirmed breakouts.
trailing_stop_positive_offset (0.025)Higher → trailing stop activates later, gives more room. Lower → locks in earlier, exits more often.
trailing_stop_positive (0.015)Tighter trail → exits closer to highs, more stops out.
low_6h exitShorter window → faster invalidation. Longer → patience but bigger giveback.
Show full SKILL.md (194 more words)Show less

Variants worth testing

  • Higher-timeframe regime filter: only enter when 1d close > 1d ema_50. Removes trades in clear downtrends (would have killed most of the −0.95% in the reference).
  • Donchian channel proper: rolling 20-bar high (instead of 12) is the textbook breakout. Test with longer rolling window.
  • Multi-pair (top 30 perps): replace StaticPairList with VolumePairList filtered to top 30 by 24h volume. Diversifies regime risk.
  • Add ATR-scaled position sizing: smaller stake when ATR is high (more risk per trade) keeps risk-per-trade flat.

Common pitfalls

  1. Long-only in downtrends. As shown by the reference. Add a regime filter or accept the strategy will lose money in bear markets.
  2. process_only_new_candles = False. Default True is correct here; setting it false fires on every tick during backtest dry-run and triple-counts entries.
  3. Conflict between minimal_roi and trailing stop. Setting minimal_roi: { "0": 0.05 } exits at +5% before the trailing stop activates at +2.5% offset. Use {"0": 100.0} and let the trailing stop run.
  4. startup_candle_count too small for ATR-14. ATR needs 14 bars of warmup; the default 30 is fine. If you switch to ATR-100, bump startup to 100+.

Sources

© Superior-Trade, MIT. 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/breakout of Superior-Trade/superior-skills.

Open the folder on GitHubat commit 9d41db5

Compare with similar skills

Breakout 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.

Breakout compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Breakout this skillSuperior-Trade/superior-skills214—~1.5kAutomated safety check: PassMIT
Polymarket TradingBlockRunAI/ClawRouter6.6k—~1.4kAutomated safety check: PassMIT
Solana Payments Wallets Tradingnpc-live/clawfirm1561 repos~4.7kAutomated safety check: PassMIT
Nansen Tradingnansen-ai/nansen-cli139—~3.3kAutomated safety check: NotesMIT
Shipp Sports Datamoonpay/skills113—~1.4kAutomated safety check: PassMIT
Aomi Transactjeremylongshore/tons-of-skills-marketplace2.8k—~2.3kAutomated safety check: PassMIT

Similar skills

  • Polymarket Trading

    BlockRunAI/ClawRouter

    A skill your agent uses when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools).

    6.6k GitHub stars~1.4k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed
  • Pay people in SOL or USDC, buy and sell tokens, check prices, discover trending and new tokens, create and manage Solana wallets, stake SOL, earn yield through lending and managed vaults, borrow…

    156 GitHub starsUsed in 1 repo~4.7k tokens
    Business, Finance & HRAuto-check passed
  • Nansen Trading

    nansen-ai/nansen-cli

    Execute DEX swaps on Solana or Base (including cross-chain bridges) and Hyperliquid perpetual trades.

    139 GitHub stars~3.3k tokensUpdated today
    Business, Finance & HRAuto-check: notes
  • Shipp Sports Data

    moonpay/skills

    Real-time sports & events data for AI agents via Shipp. An agent skill from moonpay/skills.

    113 GitHub stars~1.4k tokensUpdated 29 days ago
    Business, Finance & HRAuto-check passed
  • Aomi Transact

    jeremylongshore/tons-of-skills-marketplace

    Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state.

    2.8k GitHub stars~2.3k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Aero Stock Lp

    BankrBot/skills

    LP tokenized stocks onchain — range-LP Coinbase tokenized equities (NVDA, AAPL, GOOGL, META) and AERO/USDC on Aerodrome Slipstream (Base) for trading-fee + AERO emission yield.

    1.2k GitHub stars~5.8k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed

More from Superior-Trade/superior-skills

All 31 skills in this repo
  • Superior Trade Auth

    Superior-Trade/superior-skills

    A skill your agent uses when an agent needs to register a Superior Trade account, verify an email OTP, configure x-api-key authentication, or recover from missing or invalid credentials before using…

    214 GitHub stars~950 tokensUpdated 29 days ago
    Auto-check passed
  • Deposit Qr

    Superior-Trade/superior-skills

    A skill your agent uses when a user needs a QR code or wallet payment URI to fund a Superior-managed EVM wallet on a specific chain before using Lighter, Polymarket, Hyperliquid, or other Superior…

    214 GitHub stars~1.1k tokensUpdated 29 days ago
    Auto-check passed
  • External Deposit

    Superior-Trade/superior-skills

    A skill your agent uses when a user wants to fund or bridge from an external wallet through a third-party UI such as Relay, especially when asking for MetaMask Mobile QR codes, bridge links…

    214 GitHub stars~1.7k tokensUpdated 29 days ago
    Auto-check passed
  • Aerodrome

    Superior-Trade/superior-skills

    A skill your agent uses when creating, validating, backtesting, deploying, sizing, or troubleshooting Aerodrome/Base spot trading strategies through the Superior Trade API, especially Freqtrade…

    214 GitHub stars~2.3k tokensUpdated 29 days ago
    Auto-check passed
  • Polymarket

    Superior-Trade/superior-skills

    A skill your agent uses when the user wants to trade, research, or backtest Polymarket prediction markets through Superior Trade — finding markets by slug or event URL, placing a single immediate…

    214 GitHub stars~4.2k tokensUpdated 29 days ago
    Auto-check passed
  • Backtesting

    Superior-Trade/superior-skills

    A skill your agent uses when running, interpreting, or designing backtests on Superior Trade — anything about backtest windows, trade-count thresholds, exit-reason mix, parameter sweeps…

    214 GitHub stars~2.9k tokensUpdated 29 days ago
    Auto-check passed

Works with

Questions about Breakout

What does Breakout do?

A skill your agent uses when writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout, momentum, trend following, 12-hour high, range expansion, riding new…. Breakout is an agent skill from Superior-Trade/superior-skills. Use when writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout, momentum, trend following, 12-hour high, range expansion, riding new highs, Donchian breakout.

When should I use Breakout?

Breakout fits situations like: writing a swing/intraday breakout strategy on Superior Trade — anything described as breakout; trend following; range expansion; riding new highs.

How do I install Breakout in Claude Code?

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

How do I install Breakout in Codex?

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

Can I use Breakout 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 Superior-Trade/superior-skills --skill breakout -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/breakout, .gemini/skills/breakout, .github/skills/breakout and .opencode/skills/breakout in your project.

What does Breakout need to run?

SKILL.md names no scripts, command-line tools or credentials: Breakout is instructions for the agent only. Our summary lists: Python 3.

Does Breakout access the network?

SKILL.md names 1 domain. As links in the text: freqtrade.io. This is read from the text; nothing was executed.

Is Breakout 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 Breakout use?

Breakout is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Breakout use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 Breakout?

Skills that share tags, products or a category with Breakout: Polymarket Trading (BlockRunAI/ClawRouter, 6.6k stars), Solana Payments Wallets Trading (npc-live/clawfirm, 156 stars), Nansen Trading (nansen-ai/nansen-cli, 139 stars) and Shipp Sports Data (moonpay/skills, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Breakout?

Superior-Trade (a GitHub organization) maintains it in Superior-Trade/superior-skills, which has 214 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on September 10, 2026.

Source: Superior-Trade/superior-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.