Technical Analyst
tradermonty/claude-trading-skills
This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.
Example driver: drive a portfolio-rebalance hypothesis into a recorded session.
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install krakenfx/kraken-cli recipe-playground-rebalance --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recipe-playground-rebalance .claude/skills/recipe-playground-rebalance && rm -rf skills-srcUse ~/.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/
Install the "recipe-playground-rebalance" agent skill from https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalance into .claude/skills/recipe-playground-rebalance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recipe-playground-rebalance", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalanceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install krakenfx/kraken-cli recipe-playground-rebalance --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/recipe-playground-rebalance .agents/skills/recipe-playground-rebalance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "recipe-playground-rebalance" agent skill from https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalance into .agents/skills/recipe-playground-rebalance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recipe-playground-rebalance", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install krakenfx/kraken-cli recipe-playground-rebalance --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/recipe-playground-rebalance .cursor/skills/recipe-playground-rebalance && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "recipe-playground-rebalance" agent skill from https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalance into .cursor/skills/recipe-playground-rebalance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recipe-playground-rebalance", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/krakenfx/kraken-cli.git --path skills/recipe-playground-rebalance--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install krakenfx/kraken-cli recipe-playground-rebalance --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/recipe-playground-rebalance .gemini/skills/recipe-playground-rebalance && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "recipe-playground-rebalance" agent skill from https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalance into .gemini/skills/recipe-playground-rebalance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recipe-playground-rebalance", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install krakenfx/kraken-cli recipe-playground-rebalanceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/recipe-playground-rebalance .github/skills/recipe-playground-rebalance && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "recipe-playground-rebalance" agent skill from https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalance into .github/skills/recipe-playground-rebalance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recipe-playground-rebalance", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install krakenfx/kraken-cli recipe-playground-rebalance --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/krakenfx/kraken-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/recipe-playground-rebalance .opencode/skills/recipe-playground-rebalance && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "recipe-playground-rebalance" agent skill from https://github.com/krakenfx/kraken-cli/tree/main/skills/recipe-playground-rebalance into .opencode/skills/recipe-playground-rebalance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recipe-playground-rebalance", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
recipe-playground-rebalanceExample driver: drive a portfolio-rebalance hypothesis into a recorded session.
Recipe Playground Rebalance is an agent skill from krakenfx/kraken-cli. Example driver: drive a portfolio-rebalance hypothesis into a recorded session.
Its SKILL.md is about 2.5k 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. The repository describes itself as: The first AI-native CLI for trading crypto, stocks, forex, and derivatives. The licence is MIT.
Read from SKILL.md and the folder at commit aa56e59. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
jqFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Recipe Playground Rebalance loads about 2.5k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 1,046 words of instructions outside code blocks.
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.
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.
The full file from krakenfx/kraken-cli at commit aa56e59, republished under its MIT licence (© krakenfx). 1,046 words, ~2,453 tokens.
.claude/skills/recipe-playground-rebalance/SKILL.md (or your agent's skills folder).PREREQUISITE: Load the following skills to execute this recipe:
kraken-playground,kraken-rebalancing
This recipe is an example, not a boundary. Adapt its steps to your hypothesis, or write your own driver — see
kraken-playground→ Driving Your Own Hypothesis.
Test a target-allocation rebalancing hypothesis on live prices with no real money, recording the market data, paper trades, and the "why" behind each adjustment into one session for later replay and P&L analysis.
Paper results may overstate live performance: fees and slippage are simulated and there are no partial fills (see kraken-paper-strategy). This recipe records a session inside a paper workspace; it never places a live order.
Every number that gates a trade or a skip (targets, threshold_usd, drift_pct) belongs in --strategy-params — it's what makes two sessions comparable knob-for-knob. A recurring run adds rounds and interval_s (see step 8). The values in the step-2 example are placeholders: a number the operator names (band, threshold, cadence) replaces the example verbatim — params that don't match the mandate record a hypothesis nobody asked to test. Over a long window this recipe is interventional — one visit per interval_s, paced by the harness (see kraken-playground → Running over a Window).
Rebalance a portfolio toward target allocations:
Hold a portfolio 50% BTC, 35% ETH, 15% SOL over 24 hours.
Rebalance when any asset drifts more than 5% from target AND the delta exceeds $50.
Check every 2 hours. Report final weights and P&L.Work inside a paper workspace (create one once: kraken workspace create rebalance --capital 10000 --mode paper), then:
export KRAKEN_WORKSPACE=rebalance
kraken session start \
--symbols BTC/USD,ETH/USD,SOL/USD --channels ticker --to duckdb,jsonl \
--label rebalance-$(date +%Y%m%d-%H%M%S) \
--strategy recipe-playground-rebalance \
--strategy-params '{"targets":{"BTCUSD":0.50,"ETHUSD":0.35,"SOLUSD":0.15},"interval_s":7200,"drift_pct":5,"threshold_usd":50}' \
-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.
/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 2 hours" to 2h, "every 4 hours" to 4h, "every day" to 24h.
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, 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 2h "Run one rebalance round for session s<n> in workspace rebalance per recipe-playground-rebalance"Do not re-add an elapsed-time gate inside the round. /loop already enforces the spacing. The round cursor lives in the session's typed state cell — a rebalance round writes one decision per leg, so the decision log cannot count rounds; the cursor can. Reasons stay narrative (keep "round N" in them for the story; nothing parses it). Stop once the cursor reaches rounds:
LAST_ROUND=$(kraken session state get --session s<n> -o json 2>/dev/null \
| jq '.cursor.round // 0')
if [ "${LAST_ROUND:-0}" -ge "$ROUNDS" ]; then
kraken session stop -o json 2>/dev/null
exit 0
fi
ROUND=$((LAST_ROUND + 1))Between legs, record progress so a crashed firing resumes at the first
missing leg instead of re-trading executed ones; completing the round writes
only the round (the replace drops legs_done automatically):
kraken session state set --round "$LAST_ROUND" --legs-done "BTC/USD" \
--note "round $ROUND: leg 1 of 3 done" -o json 2>/dev/null # after each leg
kraken session state set --round "$ROUND" -o json 2>/dev/null # round completeOn a fresh firing, state get's legs_done names any half-done round — but
a crash can land between a leg executing and its legs_done write, so never
trust the cursor alone before re-trading: cross-check the evidence
(kraken session decisions, reasons mentioning the in-flight round) and skip
any leg that already filled. The cursor is the fast path; the decision log is
the truth.
The first firing is the seed round: every asset is underweight, so it allocates the whole portfolio toward the targets.
On each firing: READ, THINK, ACT.
READ: a fresh balance and each symbol's price. Read the balance every round — never carry a snapshot across rounds or across trades within a round; each fill mutates cash and holdings.
kraken paper balance -o json 2>/dev/null
kraken ticker BTCUSD -o json 2>/dev/null | jq -r '.[] | .last_price' # repeat per symbolkraken paper balance returns {"balances":{"USD":{"total","reserved","available"},...}}. Cash is .balances.USD.available; a holding is .balances.<ASSET>.total (0 if the key is absent). Price is the ticker's last-trade close (.[] | .last_price).
Fail loud before any leg trades: validate the cash figure and EVERY price before computing deltas — a rebalance acts on several legs, so one silently failed read sizes every order from garbage. On an empty read, note an alert and end the firing (the claimed round stays claimed; the next firing retries):
if [ -z "$CASH" ] || [ -z "$PRICE_BTC" ]; then
kraken session note --kind alert \
--reason "round $ROUND aborted: READ failed (cash='$CASH' btc='$PRICE_BTC')" -o json 2>/dev/null
exit 0
fiTHINK: value the portfolio, then decide each leg.
total_value = cash + Σ(holdings × price)value = holdings × price, current_pct = value / total_value × 100, target_pct = target × 100, drift = current_pct − target_pct, delta_usd = target_value − value where target_value = total_value × target.|drift| > drift_pct AND |delta_usd| > threshold_usd. Otherwise leave it.ACT: sells before buys. Execute every overweight leg (delta_usd < 0) first so its proceeds land back in cash, then execute the underweight legs. Size each buy against a fee/slippage reserve so the last leg never rejects: keep the buy cost at or below available_cash / (1 + fee_rate + slippage_rate) (defaults 0.0026 fee, 0.0 slippage — read them from paper status if unsure). Between legs, re-read the balance rather than assuming the pre-trade cash, and skip or shrink a buy the remaining cash can no longer fund.
# Overweight — sell the excess first
kraken order sell BTC/USD <volume> --type market \
--reason "rebalance round N: BTC/USD weight <current_pct>% above target <target_pct>%; selling <volume>" \
-o json 2>/dev/null
# Underweight — buy toward target, capped by fee-reserved cash
kraken order buy SOL/USD <volume> --type market \
--reason "rebalance round N: SOL/USD weight <current_pct>% below target <target_pct>%; buying <volume>" \
-o json 2>/dev/nullIf no leg breaches both thresholds, note a single skip:
kraken session note --kind skip --symbol BTC/USD \
--reason "skip round N: all weights within <drift_pct>%/$<threshold_usd> band" \
-o json 2>/dev/nullAlways pass the numeric reason so the decision log carries the "why" behind every round.
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[] | {kind, symbol, reason, timestamp}'Report:
drift_pct/threshold_usd band hold the portfolio?/loop drives the pace and the agent runs each round; the CLI has no scheduler and runs no strategy. The scheduler floor is 60s — no sub-minute cadence.targets, drift_pct, threshold_usd, interval_s) in --strategy-params and the arithmetic in jq/bc, so a rerun on the same tape reproduces the decisions.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, or append inside it — every trade and skip goes through kraken order buy / kraken session note, so the recorder stays the single writer.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
Just SKILL.md in skills/recipe-playground-rebalance of krakenfx/kraken-cli.
Open the folder on GitHubat commit aa56e59
Recipe Playground Rebalance 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Recipe Playground Rebalance this skillkrakenfx/kraken-cli | 751 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Technical Analysttradermonty/claude-trading-skills | 3k | 4 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Theme Detectortradermonty/claude-trading-skills | 3k | 2 repos | ~4.9k | Automated safety check: Pass | MIT | |
| Creating Financial ModelsChen-zexi/open-ptc-agent | 729 | 3 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Stock APIzhangxiangliang/stock-api | 2k | — | ~507 | Automated safety check: Pass | MIT | |
| Itr Walakaranb192/itr-wala | 871 | — | ~3.6k | Automated safety check: Pass | MIT |
tradermonty/claude-trading-skills
This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.
tradermonty/claude-trading-skills
Detect and analyze trending market themes across sectors. An agent skill from tradermonty/claude-trading-skills.
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
zhangxiangliang/stock-api
Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.
karanb192/itr-wala
File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27.
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。
krakenfx/kraken-cli
Price alerts, threshold monitoring, and notification triggers for agents.
krakenfx/kraken-cli
Progress from manual trading to full agent autonomy with controlled risk at each level.
krakenfx/kraken-cli
Capture the spot-futures price spread with delta-neutral basis trades.
krakenfx/kraken-cli
Dollar cost averaging with scheduled buys and performance tracking.
krakenfx/kraken-cli
Discover staking strategies, allocate funds, and track earn positions.
krakenfx/kraken-cli
Handle order failures, network errors, and duplicate submissions safely.
Categories
Example driver: drive a portfolio-rebalance hypothesis into a recorded session. Recipe Playground Rebalance is an agent skill from krakenfx/kraken-cli. Example driver: drive a portfolio-rebalance hypothesis into a recorded session.
Recipe Playground Rebalance fits situations like: business, Finance & HR work in your project.
Run `npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a claude-code`. Or copy the skill folder (skills/recipe-playground-rebalance in krakenfx/kraken-cli) into .claude/skills/recipe-playground-rebalance in your project. Claude Code loads it when a task matches its description.
Run `npx skills add krakenfx/kraken-cli --skill recipe-playground-rebalance -a codex`. Or copy the skill folder (skills/recipe-playground-rebalance in krakenfx/kraken-cli) into .agents/skills/recipe-playground-rebalance in your project. Codex loads it when a task matches its description.
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-rebalance -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-rebalance, .gemini/skills/recipe-playground-rebalance, .github/skills/recipe-playground-rebalance and .opencode/skills/recipe-playground-rebalance in your project.
Going by SKILL.md and its folder, Recipe Playground Rebalance needs the command-line tools its instructions call (jq).
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.
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.
Recipe Playground Rebalance is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Recipe Playground Rebalance: 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.
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.