Fintool
second-state/fintool
Financial trading CLIs — spot and perp trading on Hyperliquid, Binance, Coinbase, OKX.
用户用自然语言描述币种、回测时间区间和策略风格时,自动创建加密货币交易 Bot,读取内置 Hyperliquid CSV 覆盖并运行本地回测/进化;若币种、时间区间或策略风格缺失,则主动询问缺失项并展示 CSV 解析出的可用回测区间。也可在回测后上传平台 verify 或创建模拟实盘 Bot。适用于创建bot、交易策略、回测、backtest、evolve、upload verify、live…
$ npx skills add moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install moss-site/moss-trade-bot-skills moss-trade-bot-factory --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/moss-site/moss-trade-bot-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/moss-trade-bot-factory-1.0.26 .claude/skills/moss-trade-bot-factory && 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 "moss-trade-bot-factory" agent skill from https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26 into .claude/skills/moss-trade-bot-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moss-trade-bot-factory", 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/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26Type 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 moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install moss-site/moss-trade-bot-skills moss-trade-bot-factory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/moss-site/moss-trade-bot-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/moss-trade-bot-factory-1.0.26 .agents/skills/moss-trade-bot-factory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "moss-trade-bot-factory" agent skill from https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26 into .agents/skills/moss-trade-bot-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moss-trade-bot-factory", 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 moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install moss-site/moss-trade-bot-skills moss-trade-bot-factory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/moss-site/moss-trade-bot-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/moss-trade-bot-factory-1.0.26 .cursor/skills/moss-trade-bot-factory && 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 "moss-trade-bot-factory" agent skill from https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26 into .cursor/skills/moss-trade-bot-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moss-trade-bot-factory", 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/moss-site/moss-trade-bot-skills.git --path moss-trade-bot-factory-1.0.26--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 moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install moss-site/moss-trade-bot-skills moss-trade-bot-factory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/moss-site/moss-trade-bot-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/moss-trade-bot-factory-1.0.26 .gemini/skills/moss-trade-bot-factory && 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 "moss-trade-bot-factory" agent skill from https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26 into .gemini/skills/moss-trade-bot-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moss-trade-bot-factory", 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 moss-site/moss-trade-bot-skills moss-trade-bot-factoryInstalls 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 moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/moss-site/moss-trade-bot-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/moss-trade-bot-factory-1.0.26 .github/skills/moss-trade-bot-factory && 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 "moss-trade-bot-factory" agent skill from https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26 into .github/skills/moss-trade-bot-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moss-trade-bot-factory", 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 moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install moss-site/moss-trade-bot-skills moss-trade-bot-factory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/moss-site/moss-trade-bot-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/moss-trade-bot-factory-1.0.26 .opencode/skills/moss-trade-bot-factory && 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 "moss-trade-bot-factory" agent skill from https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.26 into .opencode/skills/moss-trade-bot-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "moss-trade-bot-factory", 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.
moss-trade-bot-factory用户用自然语言描述币种、回测时间区间和策略风格时,自动创建加密货币交易 Bot,读取内置 Hyperliquid CSV 覆盖并运行本地回测/进化;若币种、时间区间或策略风格缺失,则主动询问缺失项并展示 CSV 解析出的可用回测区间。也可在回测后上传平台 verify 或创建模拟实盘 Bot。适用于创建bot、交易策略、回测、backtest、evolve、upload verify、live…
Moss Trade Bot Factory is an agent skill from moss-site/moss-trade-bot-skills. 用户用自然语言描述币种、回测时间区间和策略风格时,自动创建加密货币交易 Bot,读取内置 Hyperliquid CSV 覆盖并运行本地回测/进化;若币种、时间区间或策略风格缺失,则主动询问缺失项并展示 CSV 解析出的可用回测区间。也可在回测后上传平台 verify 或创建模拟实盘 Bot。适用于创建bot、交易策略、回测、backtest、evolve、upload verify、live trading 等请求。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 99 other files, including scripts (for example `__init__.py`, `agents/openai.yaml` and `knowledge/backtest_commands.md`).
It sits in Business, Finance & HR, covering Trading and backtesting. It works with Hyperliquid. The repository describes itself as: LLM-powered trading agents that turn plain natural language into a five-pillar strategy: Trend, Mean-Reversion, Momentum, Volume, and Risk. Each strategy is hosted… The licence is MIT-0.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 56bf53c. 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.
Ships 7 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
ai.moss.siteFrom 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.
Moss Trade Bot Factory loads about 2.2k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 536 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); the scripts in this folder are not scanned.
The full file from moss-site/moss-trade-bot-skills at commit 56bf53c, republished under its MIT-0 licence (© moss-site). 536 words, ~2,170 tokens.
.claude/skills/moss-trade-bot-factory/SKILL.md (or your agent's skills folder). This skill also uses 94 other files; get the full folder from GitHub.你是一个专业的加密货币量化交易 Bot 工厂 + 策略调参师。支持 BTC 及主流山寨币(ETH、SOL 等)的全流程 Bot 创建。
在读取参数、杠杆、回测命令或写 /tmp/*.json 之前,先从用户当前自然语言消息解析三个必填字段:
symbol:交易币种,例如 BTC/USDC、ETH/USDC。backtest_range:回测区间,例如“全部数据”“最近90天”“2025-08 ~ 2025-12”“2025-08-15 到 2025-12-20”。strategy_style:策略风格,例如“利弗莫尔”“凉兮”“趋势跟随”“保守网格”“高频突破”。解析规则:
params_schema.json、leverage_caps.md、backtest_commands.md、evolution_guide.md,禁止写 /tmp/backtest_request.json、/tmp/bot_params.json、/tmp/evolution_schedule.json,禁止运行 fetch_data.py、run_backtest.py、run_evolve_backtest.py。在回答“有没有数据 / 能不能跑某区间 / 支持哪些币”前,必须运行脚本读取真实 CSV 文件,而不是凭 SKILL.md 的历史说明、旧文件名、ls 片段或记忆判断。
若已解析出 symbol:
cd {baseDir}/scripts && python3 dataset_catalog.py --symbol "$SYMBOL" --timeframe 15m > /tmp/dataset_catalog.json若 symbol 缺失或用户问支持范围:
cd {baseDir}/scripts && python3 dataset_catalog.py --list --timeframe 15m > /tmp/dataset_catalog_all.json展示规则:
<SYMBOL>:<start> ~ <end>(<bars> 根 15m K)。found=false 时,说明该 symbol 没有内置 CSV,展示 available_symbols 及其覆盖范围并请用户重选。found=true 时,csv_path / start / end / bars / compact 是唯一数据源;后续 DATA_CSV 必须等于 csv_path。需要解释支持范围、外部 CSV 限制或数据策略时读取 cat {baseDir}/knowledge/data_policy.md。
追问只问缺失项,并附上已经从 CSV 解析出的覆盖范围。不要把已经明确的信息再问一遍。
我已读取到 <SYMBOL 或 可选币种> 的内置 15m CSV 覆盖:
<coverage list>
还缺少:<缺失字段列表>。
请补充 <例如:回测区间 + 策略风格>。示例:2025-10-01 ~ 2025-12-31,利弗莫尔趋势突破。如果用户给出的区间超出覆盖范围,用具体日期说明:
<SYMBOL> 当前可回测区间是 <start> ~ <end>,你给的 <user_range> 超出了覆盖范围。
请改成覆盖范围内的日期、最近90天,或全部可用数据。“推荐项”不等于用户已选择。只有用户明确写出某个区间或在当前消息里已经包含可解析区间时,才能继续。
cat {baseDir}/knowledge/params_reference.mdcat {baseDir}/knowledge/data_policy.mdcat {baseDir}/knowledge/evolution_guide.mdcat {baseDir}/knowledge/platform_ops.mdcat {baseDir}/knowledge/leverage_caps.md(Step 2 写杠杆参数前必读)cat {baseDir}/knowledge/backtest_commands.mdscripts/data_cache/ 目录),不要从交易所下载数据。trade_api_url,默认值 https://ai.moss.site。--platform-url 只填站点 origin,例如 https://ai.moss.site;脚本会自动补上完整 API 前缀,并请求 https://ai.moss.site/api/v1/moss/agent/agents/bind。~/.moss-trade-bot/agent_creds.json;若 skill config agent_creds_path 已配置,优先使用该路径。凭证只发往用户指定的平台地址。--platform-url / 本地 creds 文件,不读取隐藏环境变量,也不会扫描无关系统凭证。md 仅按需读取;/tmp/*.json 只作为参数、指纹、回测结果的本地中间产物。本 skill 的步骤顺序是有依赖的(入口路由确定的 symbol、区间和风格贯穿到 Step 5;Step 2 的参数决定 Step 3 的回测;Step 3 的输出决定 Step 4 的上传素材)。除缺失必填字段、回测结果后的 A/B/C 选择、首次切换 live data source、手动模式每笔下单外,其余本地步骤在前置条件满足后直接推进。
固定配置:
15m10000dataset_catalog.py 从 CSV 内容读出,不要写死天数(如 148d)。交易品种规则:
BTC → BTC/USDC,ETH → ETH/USDC。scripts/data_cache/ 是否有对应 CSV,必须用 dataset_catalog.py 判断。package_upload.py / live_trade.py 按平台错误响应处理,Step 1 不预先查询平台。区间解析规则:
全部数据 / 全部可用数据:使用该 symbol 的实际 CSV 完整覆盖。最近90天 / 近3个月:以 CSV end 为右边界向前取对应区间。2025-08 ~ 2025-12:解释为 start=2025-08-01,end=2026-01-01(end 为 exclusive,覆盖完整 12 月)。2025-08-15 ~ 2025-12-20:解释为 start=2025-08-15,end=2025-12-21(覆盖 12 月 20 日整天)。2525、end <= start、超出数据覆盖),必须用具体日期说明可用范围并请用户确认,不要擅自改成旧区间。策略风格规则:
cat {baseDir}/knowledge/leverage_caps.md 查表,超限按上限封顶并在 Step 2 摘要里告知用户“已按上限 Nx 封顶”。进化选项默认开启:用户没有明确关闭进化时,直接按“每周进化开启”继续;用户说“不进化 / 关闭进化 / 固定参数”才走不进化模式。
所有必填字段解析并校验通过后,写入请求状态文件:
cat > /tmp/backtest_request.json << 'REQUEST_EOF'
{
"symbol": "<SYMBOL>",
"timeframe": "15m",
"strategy_style": "<解析出的策略风格>",
"data_csv": "<dataset_catalog.csv_path>",
"data_start": "<dataset_catalog.start>",
"data_end": "<dataset_catalog.end>",
"range_mode": "default 或 custom",
"start": "<custom 起始日期;全部数据时可为空>",
"end": "<custom exclusive 结束日期;全部数据时可为空>",
"evolution_enabled": true,
"source": "initial_request 或 followup_reply",
"source_text": "<产生完整请求的用户原文>"
}
REQUEST_EOFsource=initial_request 表示用户第一句话已经包含 symbol、回测区间、策略风格;source=followup_reply 表示通过追问补齐。两者都可以进入 Step 2。
硬前置条件:进入 Step 2 前必须存在 /tmp/backtest_request.json,且其中 symbol / strategy_style / data_csv / range_mode / source_text 非空;如果缺失,回到入口路由询问缺失字段并停止。
先给出简短执行摘要,再直接跑回测。不要先展示完整参数 JSON 逐项确认。
cat {baseDir}/knowledge/leverage_caps.md,确认杠杆上限。cat {baseDir}/scripts/params_schema.json。strategy_style 和用户描述赋值,保存到 /tmp/bot_params.json。name_i18n / personality_i18n / description_i18n,格式固定为 { "zh": "...", "en": "..." }。symbol / timeframe / capital / 回测区间 / 是否进化 / 数据来源。en。cat {baseDir}/knowledge/params_reference.md。双语文案约束:
name_i18n.zh/en <= 64personality_i18n.zh/en <= 64description_i18n.zh/en <= 280*_i18n.zh/en硬前置条件:只有 /tmp/backtest_request.json 存在并包含完整请求时,才能读取 knowledge/backtest_commands.md 并执行回测命令。若不存在,停止并回到入口路由询问缺失字段。
先读取命令模板:cat {baseDir}/knowledge/backtest_commands.md,里面有「模板 A 不进化 / 模板 B 进化(B1~B4)」可直接拷贝执行的 bash 范本。
决策流程:
cat {baseDir}/knowledge/evolution_guide.md 拿反思 7 原则,再据 /tmp/evolve_baseline.json 的 evolution_log 逐段分析。## 回测结果
📈 进化模式:+47.3% | Sharpe 0.84 | 84笔 | 21轮进化
关键进化: entry 0.15→0.18 | sl_atr 2.8→3.3
下一步:
A) 启动实盘自动交易(15分钟决策)
B) 上传到平台验证(用进化结果 + evolution_log,平台会做分段回放)
C) 调整参数重跑上传时:用 evolve_result_final.json 作为 result,params 用初始参数(/tmp/bot_params.json)。package_upload.py 会从该文件自动带出 evolution_log,平台做分段 stitched 回放,与本地进化结果同类,才能对上。
cat {baseDir}/knowledge/params_reference.md 中的速查表。先读取操作手册:cat {baseDir}/knowledge/platform_ops.md
然后按手册中「上传验证」章节执行。关键要点:
/tmp/evolve_result_final.json,params 用初始参数 /tmp/bot_params.json。bot.name_i18n / personality_i18n / description_i18n 必须显式带 zh/en 两份;脚本和接口都会拒绝伪双语。platform_ops.md 为准,不在此重复展开。先读取操作手册:cat {baseDir}/knowledge/platform_ops.md
然后按手册中「实盘交易」章节执行。关键要点:
zh/en 两份文案。--symbol 沿用入口路由确定的 USDC 永续值(与本地回测、上传一致,无需 quote 替换)。--data-source hyperliquid),与平台后端价格源一致。reasoning 和英文 reasoning_en,再通过 live_trade.py ... --reasoning-zh ... --reasoning-en ... 或等价上报接口透传给后端。reasoning / reasoning_en 必须是基于当次上下文生成的自然语言,至少覆盖:方向/动作、触发依据(信号/价格行为/regime/仓位变化中至少两项)、风险或退出原因;不要用“突破阻力,顺势开多”这类预制短句反复套用,也不要把中文原样复制到英文。live_runner.py 自动开仓 / 平仓时必须把运行时生成的 reasoning + reasoning_en 一起上报;需要更高质量 LLM 风格说明时,应由 skill 自己逐轮决策并调用 live_trade.py ... --reasoning-zh ... --reasoning-en ...。platform_ops.md 为准,不在此重复展开。knowledge/leverage_caps.md 逐币封顶(全表最高 SP500 50x,BTC 40x)。sl_atr_mult >= 2.5)。© moss-site, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 94 other files (scripts) in moss-trade-bot-factory-1.0.26 of moss-site/moss-trade-bot-skills.
Open the folder on GitHubat commit 56bf53c
Moss Trade Bot Factory 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 |
|---|---|---|---|---|---|---|
| Moss Trade Bot Factory this skillmoss-site/moss-trade-bot-skills | 390 | — | ~2.2k | Automated safety check: Pass | MIT-0 | |
| Fintoolsecond-state/fintool | 316 | — | ~5.9k | Automated safety check: Pass | None | |
| Opportunity RadarNunchi-trade/agent-cli | 521 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Nansen Tradingnansen-ai/nansen-cli | 139 | — | ~3.3k | Automated safety check: Notes | MIT | |
| Hyperliquidalsk1992/CloddsBot | 3k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Trading Futuresalsk1992/CloddsBot | 3k | — | ~5.6k | Automated safety check: Pass | MIT |
second-state/fintool
Financial trading CLIs — spot and perp trading on Hyperliquid, Binance, Coinbase, OKX.
Nunchi-trade/agent-cli
Screens all Hyperliquid perps and surfaces top trading setups
nansen-ai/nansen-cli
Execute DEX swaps on Solana or Base (including cross-chain bridges) and Hyperliquid perpetual trades.
alsk1992/CloddsBot
Hyperliquid L1 perps DEX (69% market share). An agent skill from alsk1992/CloddsBot.
alsk1992/CloddsBot
Trade perpetual futures on Binance, Bybit, Hyperliquid, MEXC with up to 200x leverage
Senpi-ai/senpi-skills
Answer "what makes Senpi different?" / "why Senpi?" / "Senpi vs other trading apps, bots or AI chatbots?" — the positioning answer, led by value, not a feature dump.
Works with
Categories
用户用自然语言描述币种、回测时间区间和策略风格时,自动创建加密货币交易 Bot,读取内置 Hyperliquid CSV 覆盖并运行本地回测/进化;若币种、时间区间或策略风格缺失,则主动询问缺失项并展示 CSV 解析出的可用回测区间。也可在回测后上传平台 verify 或创建模拟实盘 Bot。适用于创建bot、交易策略、回测、backtest、evolve、upload verify、live…. Moss Trade Bot Factory is an agent skill from moss-site/moss-trade-bot-skills.
Moss Trade Bot Factory fits situations like: tasks that involve Trading and backtesting.
Run `npx skills add moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a claude-code`. Or copy the skill folder (moss-trade-bot-factory-1.0.26 in moss-site/moss-trade-bot-skills) into .claude/skills/moss-trade-bot-factory in your project. Claude Code loads it when a task matches its description.
Run `npx skills add moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a codex`. Or copy the skill folder (moss-trade-bot-factory-1.0.26 in moss-site/moss-trade-bot-skills) into .agents/skills/moss-trade-bot-factory 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 moss-site/moss-trade-bot-skills --skill moss-trade-bot-factory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/moss-trade-bot-factory, .gemini/skills/moss-trade-bot-factory, .github/skills/moss-trade-bot-factory and .opencode/skills/moss-trade-bot-factory in your project.
Going by SKILL.md and its folder, Moss Trade Bot Factory needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: ai.moss.site; the agent is likely to contact it when it follows the instructions. 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Moss Trade Bot Factory is published under the MIT-0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.7k 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 Moss Trade Bot Factory: Fintool (second-state/fintool, 316 stars), Opportunity Radar (Nunchi-trade/agent-cli, 521 stars), Nansen Trading (nansen-ai/nansen-cli, 139 stars) and Hyperliquid (alsk1992/CloddsBot, 3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
moss-site (a GitHub organization) maintains it in moss-site/moss-trade-bot-skills, which has 390 GitHub stars. The repository was last updated on September 9, 2026.
Source: moss-site/moss-trade-bot-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.