Agent skill

Recipe Playground Price Alert

by krakenfx in krakenfx/kraken-cli

Example driver: drive a price-level-alert hypothesis into a recorded session.

MITAuto-check passedBusiness, Finance & HR

Install Recipe Playground Price Alert

skills CLI
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-price-alert -a claude-code

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

GitHub CLI
$ gh skill install krakenfx/kraken-cli recipe-playground-price-alert --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/krakenfx/kraken-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recipe-playground-price-alert .claude/skills/recipe-playground-price-alert && 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
recipe-playground-price-alert
GitHub stars
751
Token cost
~2.2k tokens
SKILL.md length
967 words
Files
1
Skills in repo
59
Repo updated
First seen
Licence
MIT

At a glance

Example driver: drive a price-level-alert hypothesis into a recorded session.

  • Business, Finance & HR work in your project
  • SKILL.md covers Important, Params, Quick Start and Start the Session, plus 4 more sections
  • Calls jq

What it does

Recipe Playground Price Alert is an agent skill from krakenfx/kraken-cli. Example driver: drive a price-level-alert hypothesis into a recorded session.

Its SKILL.md is about 2.2k 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: The first AI-native CLI for trading crypto, stocks, forex, and derivatives. The licence is MIT.

When your agent uses it

  • Business, Finance & HR work in your project

Example prompts

  • “/recipe-playground-price-alert”

What it can do on your machine

Read from SKILL.md and the folder at commit aa56e59. 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:

    • jq

    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

Recipe Playground Price Alert loads about 2.2k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 967 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 krakenfx/kraken-cli at commit aa56e59, republished under its MIT licence (© krakenfx). 967 words, ~2,224 tokens.

Download SKILL.mdSave it as .claude/skills/recipe-playground-price-alert/SKILL.md (or your agent's skills folder).
name
recipe-playground-price-alert
description
Example driver: drive a price-level-alert hypothesis into a recorded session.
version
1.0.0

Playground: Price Alert

PREREQUISITE: Load kraken-playground and kraken-alert-patterns to run this recipe. This recipe is an example, not a boundary. Adapt the steps to your hypothesis, or write your own driver (see kraken-playground → Driving Your Own Hypothesis).

Watch key price levels on live prices and record each crossing as an alert decision, capturing the market data and the "why" into one session for later replay and analysis. Alert-only: it records crossings, it never places a trade.

Use this skill for:

  • watching one or more price levels over a window
  • recording each level break as an alert with the numbers behind it
  • grading afterward which levels were hit, when, and which were never touched

Important

Alerts are informational and never execute a trade (see kraken-alert-patterns). This recipe records a session (market data + alert decisions); it never places a live order.

Pacing is external. /loop owns the schedule and fires one round per interval (see kraken-playground → Pacing). A cadence the operator names is a commitment: record it as interval_s and honor it — polls may run late, never early. A session whose params omit interval_s may not claim or imply any cadence in its report.

Over a long window this recipe is observational — a missed poll is not a missed crossing. The recorder holds every level break, so late visits (or none) still grade the hypothesis at stop time (see kraken-playground → Running over a Window).

Params

Every level that gates an alert goes in --strategy-params, not only in prose reasons. That is what makes two sessions comparable knob-for-knob:

  • upper: alert when price breaks above this level
  • lower: alert when price breaks below this level
  • interval_s: spacing between rounds; set the /loop interval to this value

The values in the example are placeholders. A level the operator names replaces the example verbatim — params that don't match the request record a hypothesis nobody asked to test.

Quick Start

Natural language:

Watch BTC for 30 minutes. Alert me if price breaks above $70,000 or below
$60,000. Check every 5 minutes. At the end, show which levels were hit and when.

Start the Session

Work inside a paper workspace (create one once: kraken workspace create alerts --capital 10000 --mode paper), then:

bash
export KRAKEN_WORKSPACE=alerts

kraken session start \
  --symbols BTC/USD --channels ticker,trade --to duckdb,jsonl \
  --label alert-btc-$(date +%Y%m%d-%H%M%S) \
  --strategy recipe-playground-price-alert \
  --strategy-params '{"upper":70000,"lower":60000,"interval_s":300}' \
  -o json 2>/dev/null &

# The session_started stdout line carries the id: {"type":"session_started","session":"s<n>",...}

Print the session id to the user right after starting, and again in the final report — it is the handle for resuming the /loop, checking kraken session show, and locating the artifacts.

Schedule the Rounds

/loop owns the pacing. Set its interval to interval_s and it fires each round on cadence (late under jitter, never early). Parse the interval from the user's request: "every 5 minutes" to 5m, "every 2 minutes" to 2m, "every hour" to 1h.

The scheduler floor is 60 seconds (/loop, cron, and ScheduleWakeup all clamp to a one-minute minimum). interval_s must be >= 60. If the user asks for a sub-minute cadence ("every 30 seconds"), clamp to 60 and tell them — never set a sub-minute interval_s and never let the report claim a cadence the harness cannot run.

/loop 5m "Run one price-alert round for session s<n> in workspace alerts per recipe-playground-price-alert"

Do not re-add an elapsed-time gate inside the round. /loop already enforces the spacing.

Show full SKILL.md (487 more words)Show less

Each Round

On each firing: READ, THINK, ACT.

READ: current price.

bash
kraken ticker BTCUSD -o json 2>/dev/null

Price is the ticker's last-trade close. Extract it with jq; do not eyeball it. Bind the band from the same --strategy-params you recorded — never hardcode the levels into the arithmetic:

bash
UPPER=70000
LOWER=60000
PRICE=$(kraken ticker BTCUSD -o json 2>/dev/null | jq -r '.[] | .last_price')

THINK — alert on the crossing, not on the level. A sustained excursion is one event, not one per round. Classify the price into a zone — above / within / below — and alert only when the zone changes into a breakout. kind alone can't carry this (an alert doesn't say which side, and the per-round skip note would erase the last alert), so the zone lives in the session's typed state cell; reasons stay narrative:

bash
PREV_ZONE=$(kraken session state get --session s<n> -o json 2>/dev/null \
  | jq -r '.cursor.zone // "within"')

# Fail loud: an empty price must not classify a zone (a fabricated "within"
# would silently swallow a real breakout).
if [ -z "$PRICE" ]; then
  kraken session note --kind alert --symbol BTC/USD \
    --reason "round skipped: READ failed (price empty)" -o json 2>/dev/null
  exit 0
fi
if   (( $(echo "$PRICE > $UPPER" | bc -l) )); then ZONE=above
elif (( $(echo "$PRICE < $LOWER" | bc -l) )); then ZONE=below
else ZONE=within; fi

# Persist the zone for the next firing (typed: a typo refuses instead of
# silently resetting the crossing detector).
kraken session state set --zone "$ZONE" -o json 2>/dev/null
  • Zone entered above from a different zone → the upper level was just crossed — alert.
  • Zone entered below from a different zone → the lower level was just crossed — alert.
  • Zone unchanged (still above, still below, or still within) → same state, no new crossing — skip.
  • within re-arms both boundaries: the next move to above or below alerts again.

Because the marker is on every line, above → below reads as a genuine change and alerts, and a sustained above → above reads as unchanged and does not.

ACT — alert on a fresh breakout, always ending the reason with the new zone= marker:

bash
# upper break (ZONE=above, PREV_ZONE != above)
kraken session note --kind alert --symbol BTC/USD \
  --reason "alert round N: BTC/USD broke above <upper> at <price>; zone=above" \
  -o json 2>/dev/null

# lower break (ZONE=below, PREV_ZONE != below)
kraken session note --kind alert --symbol BTC/USD \
  --reason "alert round N: BTC/USD broke below <lower> at <price>; zone=below" \
  -o json 2>/dev/null

ACT (skip) — no zone change; record the round and carry the current zone forward so the next round sees it:

bash
kraken session note --kind skip --symbol BTC/USD \
  --reason "skip round N: BTC/USD at <price>, no new crossing (<lower>/<upper>); zone=$ZONE" \
  -o json 2>/dev/null

Always pass the numeric reason, and always end it with the zone= marker — it is the state the next round reads to tell a fresh crossing from a sustained move.

Stop and Review

bash
kraken session stop -o json 2>/dev/null
kraken session show -o json 2>/dev/null | jq '.summary'

kraken session decisions --session s<n> -o json 2>/dev/null \
  | jq -c '.decisions[] | select(.kind=="alert") | {timestamp, reason}'

Report:

  • which levels were crossed (upper and/or lower)
  • when each crossing occurred
  • any level never touched (INCONCLUSIVE for that level)

Hard Rules

  • This recipe records a session. It never places a live order — alerts are informational only.
  • /loop drives the pace and the agent runs each round. The CLI has no scheduler and runs no strategy.
  • Do not add a pacing gate inside the round; /loop enforces spacing.
  • A scheduled /loop fire only runs what the agent may invoke unprompted. Keep kraken ticker, kraken session note, and kraken session show permitted non-interactively, or a fire stalls waiting on an approval you never see.
  • Keep every level in --strategy-params and the comparison in jq/bc, so a rerun on the same tape reproduces the decisions.
  • A session whose params omit interval_s may not claim any cadence in its report.
  • The session directory (session.json, decisions.jsonl, and the tape sinks) is owned by the CLI recorder. The agent only reads it, and only for the stop-time summary. Never write, edit, mkdir, or append inside it — every decision goes through kraken session note, so the recorder stays the single writer.
  • If you hit a mismatch between what you are trying to do and the CLI's interface or responses — including a mismatch between this skill and the installed CLI version's contract — feel free to submit feedback with kraken feedback.

© krakenfx, 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/recipe-playground-price-alert of krakenfx/kraken-cli.

Open the folder on GitHubat commit aa56e59

Compare with similar skills

Recipe Playground Price Alert 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.

Recipe Playground Price Alert compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recipe Playground Price Alert this skillkrakenfx/kraken-cli751—~2.2kAutomated safety check: PassMIT
Technical Analysttradermonty/claude-trading-skills3k4 repos~4.6kAutomated safety check: PassMIT
Theme Detectortradermonty/claude-trading-skills3k2 repos~4.9kAutomated safety check: PassMIT
Creating Financial ModelsChen-zexi/open-ptc-agent7293 repos~1.3kAutomated safety check: PassMIT
Stock APIzhangxiangliang/stock-api2k—~507Automated 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 4 repos~4.6k tokens
    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
  • 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 3 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 yesterday
    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 7 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。

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

More from krakenfx/kraken-cli

All 59 skills in this repo
  • Kraken Alert Patterns

    krakenfx/kraken-cli

    Price alerts, threshold monitoring, and notification triggers for agents.

    751 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Autonomy Levels

    krakenfx/kraken-cli

    Progress from manual trading to full agent autonomy with controlled risk at each level.

    751 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Basis Trading

    krakenfx/kraken-cli

    Capture the spot-futures price spread with delta-neutral basis trades.

    751 GitHub stars~802 tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Dca Strategy

    krakenfx/kraken-cli

    Dollar cost averaging with scheduled buys and performance tracking.

    751 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Earn Staking

    krakenfx/kraken-cli

    Discover staking strategies, allocate funds, and track earn positions.

    751 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed
  • Kraken Error Recovery

    krakenfx/kraken-cli

    Handle order failures, network errors, and duplicate submissions safely.

    751 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Recipe Playground Price Alert

What does Recipe Playground Price Alert do?

Example driver: drive a price-level-alert hypothesis into a recorded session. Recipe Playground Price Alert is an agent skill from krakenfx/kraken-cli. Example driver: drive a price-level-alert hypothesis into a recorded session.

When should I use Recipe Playground Price Alert?

Recipe Playground Price Alert fits situations like: business, Finance & HR work in your project.

How do I install Recipe Playground Price Alert in Claude Code?

Run `npx skills add krakenfx/kraken-cli --skill recipe-playground-price-alert -a claude-code`. Or copy the skill folder (skills/recipe-playground-price-alert in krakenfx/kraken-cli) into .claude/skills/recipe-playground-price-alert in your project. Claude Code loads it when a task matches its description.

How do I install Recipe Playground Price Alert in Codex?

Run `npx skills add krakenfx/kraken-cli --skill recipe-playground-price-alert -a codex`. Or copy the skill folder (skills/recipe-playground-price-alert in krakenfx/kraken-cli) into .agents/skills/recipe-playground-price-alert in your project. Codex loads it when a task matches its description.

Can I use Recipe Playground Price Alert 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 krakenfx/kraken-cli --skill recipe-playground-price-alert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recipe-playground-price-alert, .gemini/skills/recipe-playground-price-alert, .github/skills/recipe-playground-price-alert and .opencode/skills/recipe-playground-price-alert in your project.

What does Recipe Playground Price Alert need to run?

Going by SKILL.md and its folder, Recipe Playground Price Alert needs the command-line tools its instructions call (jq).

Does Recipe Playground Price Alert 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 Recipe Playground Price Alert 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 Recipe Playground Price Alert use?

Recipe Playground Price Alert 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 Recipe Playground Price Alert use?

About 2.2k tokens (SKILL.md is roughly 8.9k 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 Recipe Playground Price Alert?

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

Who maintains Recipe Playground Price Alert?

krakenfx (a GitHub organization) maintains it in krakenfx/kraken-cli, which has 751 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on August 7, 2026.

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