Agent skill

Openwhale Dev

by OpenWhale-Org in OpenWhale-Org/OpenWhale

Write runnable OpenWhale components — strategies, monitors, executors, account implementations, venue adapters, full plugins, and kind extensions.

No licenceAuto-check passedBusiness, Finance & HR

Install Openwhale Dev

skills CLI
$ npx skills add OpenWhale-Org/OpenWhale --skill openwhale-dev -a claude-code

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

GitHub CLI
$ gh skill install OpenWhale-Org/OpenWhale openwhale-dev --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/OpenWhale-Org/OpenWhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openwhale-dev .claude/skills/openwhale-dev && 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
openwhale-dev
GitHub stars
150
Token cost
~4.2k tokens
SKILL.md length
2,088 words
Files
7 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Write runnable OpenWhale components — strategies, monitors, executors, account implementations, venue adapters, full plugins, and kind extensions.

  • Works in 10 steps: TS5 standard decorators — never set… → Decorators only attach metadata.… → IDs are short and get plugin-qualified… → …
  • The user wants to build
  • SKILL.md covers The 8 concepts (fixed…, What are you being asked to…, Since 2026-08-26 (newest first) and Since 2026-08-06, plus 4 more sections
  • Calls pnpm

What it does

Openwhale Dev is an agent skill from OpenWhale-Org/OpenWhale. Write runnable OpenWhale components — strategies, monitors, executors, account implementations, venue adapters, full plugins, and kind extensions. Use whenever the user wants to build, extend, or debug anything that plugs into the OpenWhale trading framework.

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/executor.md`, `references/monitor.md` and `references/plugin.md`).

It sits in Business, Finance & HR, covering Trading and backtesting. The repository describes itself as: A framework for AI-driven economic activity. Declarative, composable, observable, deterministic.

When your agent uses it

  • The user wants to build
  • Debug anything that plugs into the OpenWhale trading framework

Example prompts

  • “/openwhale-dev”

Workflow steps

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

  1. TS5 standard decorators — never set experimentalDecorators. Build with tsc targeting
  2. Decorators only attach metadata. Registration happens exclusively through the
  3. IDs are short and get plugin-qualified at load. Write id: 'my-monitor'; the runtime turns
  4. Strategies are structurally read-only. They receive Account read views (no write methods
  5. No venue parameter when an account binding implies it. The runtime injects
  6. Monitor keys are clean: no credential or instance identifiers inside a key. Data lives in
  7. Params are read once, at activation — triggers, subscriptions and executor slots all derive
  8. Instructions are serializable JSON referencing executor slot labels — never object refs.
  9. All fields of tunableParamsSchema must have .default(); baseParamsSchema holds the
  10. ESM only. "type": "module" in package.json, .js extensions on relative imports.

What it can do on your machine

Read from SKILL.md and the folder at commit b15e838. 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:

    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, 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

Openwhale Dev loads about 4.2k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 2,088 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~23k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 2,088 words (~4,167 tokens).

“OpenWhale is an AI-native trading framework: Monitor → Trigger → Strategy → Queue → Executor. You are writing a plugin package — an npm package whose default export is a definePlugin({...}) manifest. The user installs it from the Dashboard (Plugins…”

— opening of SKILL.md by OpenWhale-Org
name
openwhale-dev

Read the full SKILL.md on GitHub

Files

SKILL.md and 6 other files (references) in skills/openwhale-dev of OpenWhale-Org/OpenWhale.

  • SKILL.md
  • references/executor.md
  • references/monitor.md
  • references/plugin.md
  • references/spec.md
  • references/strategy.md
  • references/testing.md

Open the folder on GitHubat commit b15e838

Compare with similar skills

Openwhale Dev 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.

Openwhale Dev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openwhale Dev this skillOpenWhale-Org/OpenWhale150—~4.2kAutomated safety check: PassNone
Tushare Datazillionare/zillionare3192 repos~2.3kAutomated safety check: PassNone
Tradingview MCPatilaahmettaner/tradingview-mcp5k—~1.3kAutomated safety check: PassMIT
Digital Oraclekomako-workshop/digital-oracle870—~5.9kAutomated safety check: PassMIT
Fintoolsecond-state/fintool3161 repos~5.9kAutomated safety check: PassNone
Polyclawchainstacklabs/polyclaw3601 repos~2kAutomated safety check: PassApache-2.0

Similar skills

  • 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
  • Tradingview MCP

    atilaahmettaner/tradingview-mcp

    AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…

    5k GitHub stars~1.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Digital Oracle

    komako-workshop/digital-oracle

    Answer prediction questions using market trading data, not opinions.

    870 GitHub stars~5.9k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Fintool

    second-state/fintool

    Financial trading CLIs — spot and perp trading on Hyperliquid, Binance, Coinbase, OKX.

    316 GitHub starsUsed in 1 repo~5.9k tokens
    Business, Finance & HRAuto-check passed
  • Polyclaw

    chainstacklabs/polyclaw

    Trade on Polymarket via split + CLOB execution. An agent skill from chainstacklabs/polyclaw.

    360 GitHub starsUsed in 1 repo~2k tokens
    Business, Finance & HRAuto-check passed
  • Markdown

    facioquo/stock-indicators-dotnet

    Format and lint Markdown in this repository against GitHub Flavored Markdown and its markdownlint-cli2 configuration — headers, lists, code fences, callouts (VitePress containers on docs-site pages…

    1.2k GitHub stars~812 tokensUpdated today
    Business, Finance & HRAuto-check passed

Questions about Openwhale Dev

What does Openwhale Dev do?

Write runnable OpenWhale components — strategies, monitors, executors, account implementations, venue adapters, full plugins, and kind extensions. Openwhale Dev is an agent skill from OpenWhale-Org/OpenWhale. Write runnable OpenWhale components — strategies, monitors, executors, account implementations, venue adapters, full plugins, and kind extensions.

When should I use Openwhale Dev?

Openwhale Dev fits situations like: the user wants to build; debug anything that plugs into the OpenWhale trading framework.

How do I install Openwhale Dev in Claude Code?

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

How do I install Openwhale Dev in Codex?

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

Can I use Openwhale Dev 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 OpenWhale-Org/OpenWhale --skill openwhale-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openwhale-dev, .gemini/skills/openwhale-dev, .github/skills/openwhale-dev and .opencode/skills/openwhale-dev in your project.

What does Openwhale Dev need to run?

Going by SKILL.md and its folder, Openwhale Dev needs the command-line tools its instructions call (pnpm).

Does Openwhale Dev 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 Openwhale Dev 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 Openwhale Dev use?

No licence was found for Openwhale Dev or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Openwhale Dev use?

About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.

What are the alternatives to Openwhale Dev?

Skills that share tags, products or a category with Openwhale Dev: Tushare Data (zillionare/zillionare, 319 stars), Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars), Digital Oracle (komako-workshop/digital-oracle, 870 stars) and Fintool (second-state/fintool, 316 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openwhale Dev?

OpenWhale-Org (a GitHub organization) maintains it in OpenWhale-Org/OpenWhale, which has 150 GitHub stars. The repository was last updated on October 3, 2026.

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