Agent skill

Fatecat

FateCat 执行型测算基础设施 skill：安装并校验当前仓库，执行生产化 capability，输出 JSON / Markdown，启动 Web / API / Telegram 交付层，并在发布前运行仓库卫生与生产就绪门禁。Use when 用户要求测算、排盘、生成报告、启动 Web/API/Bot、验收 skill、导出 bundle、检查生产可用性。

MITAuto-check: notesBackend & APIs

Install Fatecat

skills CLI

$ npx skills add tradecatlabs/fatecat --skill fatecat -a claude-code

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

GitHub CLI

$ gh skill install tradecatlabs/fatecat fatecat --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "fatecat" agent skill from https://github.com/tradecatlabs/fatecat/tree/main into .claude/skills/fatecat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fatecat", 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.

skills CLI

$ npx skills add tradecatlabs/fatecat --skill fatecat -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install tradecatlabs/fatecat fatecat --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "fatecat" agent skill from https://github.com/tradecatlabs/fatecat/tree/main into .agents/skills/fatecat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fatecat", 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.

skills CLI

$ npx skills add tradecatlabs/fatecat --skill fatecat -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install tradecatlabs/fatecat fatecat --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "fatecat" agent skill from https://github.com/tradecatlabs/fatecat/tree/main into .cursor/skills/fatecat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fatecat", 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.

skills CLI

$ npx skills add tradecatlabs/fatecat --skill fatecat -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install tradecatlabs/fatecat fatecat --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "fatecat" agent skill from https://github.com/tradecatlabs/fatecat/tree/main into .gemini/skills/fatecat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fatecat", 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.

GitHub CLI

$ gh skill install tradecatlabs/fatecat fatecat

Installs 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).

skills CLI

$ npx skills add tradecatlabs/fatecat --skill fatecat -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "fatecat" agent skill from https://github.com/tradecatlabs/fatecat/tree/main into .github/skills/fatecat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fatecat", 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.

skills CLI

$ npx skills add tradecatlabs/fatecat --skill fatecat -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install tradecatlabs/fatecat fatecat --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "fatecat" agent skill from https://github.com/tradecatlabs/fatecat/tree/main into .opencode/skills/fatecat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fatecat", 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.

Facts

Skill name: fatecat
GitHub stars: 202
Token cost: ~1.7k tokens
SKILL.md length: 390 words
Files: 12,191 (incl. scripts, references)
Skills in repo: 5
Repo updated: Aug 25, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 12 steps: 确认仓库位置 → 首次安装运行时 → 标准纯分析预检 → …
用户要求测算、排盘、生成报告、启动 Web/API/Bot、验收 skill、导出 bundle、检查生产可用性
SKILL.md covers When to Use This Skill, Not For / Boundaries, Quick Reference and Execution Logic, plus 3 more sections
Calls bash and git

What it does

Fatecat is an agent skill from tradecatlabs/fatecat. FateCat 执行型测算基础设施 skill：安装并校验当前仓库，执行生产化 capability，输出 JSON / Markdown，启动 Web / API / Telegram 交付层，并在发布前运行仓库卫生与生产就绪门禁。Use when 用户要求测算、排盘、生成报告、启动 Web/API/Bot、验收 skill、导出 bundle、检查生产可用性。

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12192 other files, including scripts and reference files (for example `.auto-github.json`, `.github/AGENTS.md` and `.github/workflows/acceptance.yml`).

It sits in Backend & APIs. It works with Telegram and FastAPI. The repository describes itself as: FateCat measurement infrastructure for Agents and apps: reproducible Bazi/Ziwei calculations, evidence-oriented reports, FastAPI, Web, Telegram and CLI. The licence is MIT.

When your agent uses it

用户要求测算、排盘、生成报告、启动 Web/API/Bot、验收 skill、导出 bundle、检查生产可用性

Example prompts

“/fatecat”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

确认仓库位置
首次安装运行时
标准纯分析预检
预检并生成样例输出
用输入文件生成 JSON
用 JSON 字符串生成 JSON
启动 Web / API 前验收
启动 Telegram Bot 前验收
发布前完整验收
清理本地运行态
导出 lite skill 包并检查卫生
生产就绪门禁

What it can do on your machine

Read from SKILL.md and the folder at commit c9b9857. 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
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- bash
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, 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

Fatecat loads about 1.7k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 390 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~48
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~12k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:193

- 没有运行态、缓存、真实 `.env` 或数据库文件混入版本控制。

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.

SKILL.md

The full file from tradecatlabs/fatecat at commit c9b9857, republished under its MIT licence (© tradecatlabs). 390 words, ~1,681 tokens.

Download SKILL.mdSave it as .claude/skills/fatecat/SKILL.md (or your agent's skills folder). This skill also uses 12190 other files; get the full folder from GitHub.

name: fatecat
description: FateCat 执行型测算基础设施 skill：安装并校验当前仓库，执行生产化 capability，输出 JSON / Markdown，启动 Web / API / Telegram 交付层，并在发布前运行仓库卫生与生产就绪门禁。Use when 用户要求测算、排盘、生成报告、启动 Web/API/Bot、验收 skill、导出 bundle、检查生产可用性。

fatecat Skill

把 FateCat 从“仓库已存在”推进到“依赖就绪、健康通过、能真实执行测算 capability 并交付结果”。FateCat 是面向 Agent 与应用开发者的测算基础设施，提供统一的能力协议、可复现计算核心、证据化解释层和多端交付接口。本 skill 只编排当前仓库能力，不重写命理算法，不用文档替代真实命令证据。

When to Use This Skill

Trigger when any of these applies:

用户要生成八字 / 紫微等命理排盘结果，且结果需要落到 JSON 或 Markdown 文件。
用户要打开 Web HTML 页面录入出生日期、时间、地区、姓名并复制 Markdown。
用户要启动或验收 FastAPI、Telegram Bot、CLI 或 Agent 交付入口。
用户要首次安装仓库、修复虚拟环境、检查 pure / delivery 健康状态。
用户要发布、导出、审计、检查仓库卫生、检查隐私样例或验证 skill bundle。
用户要求“能不能生产复用”“上线前检查”“完整验收”“live Bot smoke”。

Not For / Boundaries

不在 tools/reference-repos/ 内魔改第三方算法源码；vendor 默认只读，除非任务明确是供应链治理。
不得新增第二套业务源码或旧路径 fallback；源码根是 domains/*/services/*，运行资产根是 infra/、contracts/、tools/ 和 domains/fate-analysis/data-products/。
不把缺少真实 token、真实 API URL、生产 CORS、远程服务器权限的 dry-run 说成生产 live 验证。
不在缺少 birthDateTime、gender、longitude、latitude 时直接执行纯分析。
不把未来功能塞回默认综合八字报告；紫微、黄历、梅花、六爻、奇门、大六壬、风水、姓名合婚等必须走独立体系契约。
不向用户前端展示除北京以外的真实地区样例；第一方示例统一使用北京 / 测试用户口径。

Quick Reference

1. 确认仓库位置

bash

test -f SKILL.md && test -d domains && test -d governance && test -d references

2. 首次安装运行时

bash

bash scripts/bootstrap.sh --with-dev

3. 标准纯分析预检

bash

bash scripts/preflight.sh --mode pure --bootstrap --pretty

4. 预检并生成样例输出

bash

bash scripts/preflight.sh --mode pure --bootstrap --smoke --output-file output/preflight-sample.json --pretty

5. 用输入文件生成 JSON

bash

mkdir -p output
bash scripts/pure-analysis.sh --input-file input.json --output-file output/result.json --pretty

6. 用 JSON 字符串生成 JSON

bash

mkdir -p output
bash scripts/pure-analysis.sh \
  --input-json '{"birthDateTime":"1990-01-01 08:00:00","gender":"男","longitude":116.4074,"latitude":39.9042,"birthPlace":"北京市","name":"测试用户"}' \
  --output-file output/result.json \
  --pretty

7. 启动 Web / API 前验收

bash

bash scripts/preflight.sh --mode delivery --bootstrap --pretty
bash scripts/delivery-smoke.sh --target api
bash scripts/serve-api.sh

Web 地址：

text

http://127.0.0.1:8001/web

8. 启动 Telegram Bot 前验收

bash

bash scripts/preflight.sh --mode delivery --bootstrap --pretty
bash scripts/delivery-smoke.sh --target bot --startup-timeout 8
bash scripts/serve-bot.sh

9. 发布前完整验收

bash

bash scripts/acceptance.sh --with-dev
bash scripts/acceptance.sh --with-dev --with-mingli-bench

完整验收包含 wheel clean-room、核心性能预算、全量测试、静态检查、交付 smoke 和导出包 smoke。内部 lite 运行包不等于公共分发包；公共发布还必须通过 vendor 许可证门禁。

10. 清理本地运行态

bash

bash scripts/clean-runtime.sh

彻底重建虚拟环境时才加：

bash

bash scripts/clean-runtime.sh --venv

11. 导出 lite skill 包并检查卫生

bash

rm -rf /tmp/fatecat-export
bash scripts/export-runtime.sh --output-parent /tmp/fatecat-export --mode lite
bash scripts/check-export-hygiene.sh /tmp/fatecat-export/fatecat

12. 生产就绪门禁

bash

bash scripts/production-readiness.sh --api-url https://your-domain.example --require-live-bot

没有真实生产 URL、CORS allowlist、API token 和 Telegram token 时，只能记录为“外部连通验证待执行”。

13. 校验当前 skill

bash

/home/lenovo/.codex/skills/auto-skill/scripts/validate-skill.sh /home/lenovo/.projects/fatecat --strict

Execution Logic

先定位目标：纯分析输出文件走 pure；Web / API / Bot 走 delivery；发布交付走 acceptance；公网生产走 production-readiness。
再补运行时：优先 bash scripts/preflight.sh --mode <pure|delivery> --bootstrap --pretty，不要手工拼散命令。
再验输入：排盘必须有出生时间、性别、经纬度；前端示例必须使用北京 / 测试用户。
再执行目标命令：生成文件、启动服务、导出 bundle 或跑门禁。
最后复核证据：退出码、输出文件、健康检查、smoke 日志、导出包卫生、Git 状态。

Examples

Example 1: 首次接手仓库

Input: 用户说“先检查这个 skill 能不能跑”。
Steps:
1. bash scripts/preflight.sh --mode pure --bootstrap --pretty
2. bash scripts/health.sh --mode pure --json --pretty
3. 必要时执行 bash scripts/acceptance.sh --with-dev
Expected output / acceptance:
- 虚拟环境创建成功。
- CLI 可执行。
- pure 健康检查通过。

Example 2: 生成排盘 JSON

Input: 用户给出出生时间、性别、经纬度、姓名，要求保存结果。
Steps:
1. 检查字段包含 birthDateTime、gender、longitude、latitude。
2. bash scripts/preflight.sh --mode pure --bootstrap --pretty
3. bash scripts/pure-analysis.sh --input-file input.json --output-file output/result.json --pretty
Expected output / acceptance:
- 命令退出码为 0。
- output/result.json 存在且可解析。
- 输出不是空文件、报错栈或模型臆造文本。

Show full SKILL.md (150 more words)Show less

Example 3: 启动 Web HTML 页面

Input: 用户要浏览器输入出生日期、出生时间、出生地区、姓名，并复制 Markdown。
Steps:
1. bash scripts/preflight.sh --mode delivery --bootstrap --pretty
2. bash scripts/delivery-smoke.sh --target api
3. bash scripts/serve-api.sh
Expected output / acceptance:
- API smoke 通过。
- /web 可访问。
- 页面输出 Markdown，可复制。

Example 4: 发布前完整门禁

Input: 用户说“提交前检查到能交付”。
Steps:
1. bash scripts/clean-runtime.sh
2. bash scripts/acceptance.sh --with-dev
3. git status --short --branch
Expected output / acceptance:
- acceptance 全部通过。
- 未跟踪非忽略文件为 0。
- 没有运行态、缓存、真实 .env 或数据库文件混入版本控制。

References

references/index.md: 文档导航。
references/execution-playbook.md: 标准执行顺序、模式判断和失败处理。
references/commands.md: 命令入口与使用场景。
references/io-contract.md: 输入输出契约。
references/architecture.md: 企业根结构、skill 入口、包装脚本与 canonical runtime 边界。
references/ops-pack.md: 运维包、delivery smoke 与生产边界。
references/live-bot-verification.md: 真实 Telegram token 验证。
domains/fate-analysis/data-products/calendar/solar_terms/golden/: 1900-2030 节气 golden 回归 fixture。
contracts/fate/evidence_schema.json: 综合八字机器可读依据契约。
contracts/fate/weight_policy.json: 综合八字核心、动态、辅助、民俗权重边界。
contracts/fate/classics_rule_index.json: 典籍规则索引种子。
references/stage-gates.md: 从可运行到可生产的阶段门禁。
references/troubleshooting.md: 常见失败与修复路径。
references/migration-plan.md: 当前目录迁移与根卫生口径。

Maintenance

Sources:
- scripts/bootstrap.sh
- scripts/preflight.sh
- scripts/health.sh
- scripts/pure-analysis.sh
- scripts/delivery-smoke.sh
- scripts/export-runtime.sh
- scripts/acceptance.sh
- domains/fate-analysis/services/fate-core/src/fate_core/cli.py
- domains/experience-delivery/services/fatecat-delivery/src/web_ui.py
- domains/experience-delivery/services/fatecat-delivery/src/main.py
Quality gate:
- /home/lenovo/.codex/skills/auto-skill/scripts/validate-skill.sh /home/lenovo/.projects/fatecat --strict
- bash scripts/preflight.sh --mode pure --bootstrap --pretty
- bash scripts/acceptance.sh --with-dev
Last updated: 2026-05-07
Known limits:
- delivery-smoke 的 Bot 检查默认是 dry-run，不等于 Telegram live。
- 生产 live 验证必须依赖真实外部 URL、token、CORS 与网络权限。
- vendor 体积偏大是完整复用外部源码快照的取舍，不能无门禁删除。

Files

SKILL.md and 12,190 other files (scripts, references) in the repository root of tradecatlabs/fatecat.

SKILL.md
.auto-github.json
.dockerignore
.editorconfig
.github/AGENTS.md
.github/workflows/acceptance.yml
.github/workflows/container.yml
.github/workflows/evaluation-nightly.yml
.github/workflows/hf-space-deploy.yml
.github/workflows/quick.yml
.gitignore
.gitmodules
.pre-commit-config.yaml
.python-version
AGENTS.md
CHANGELOG.md
CONSTITUTION.md
DEBUG.md
LICENSE
… and 12,172 more

Open the folder on GitHubat commit c9b9857

Compare with similar skills

Fatecat 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.

Fatecat compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Fatecat this skilltradecatlabs/fatecat	202	—	~1.7k	Automated safety check: Notes	MIT	1 mo ago
Fomo Agentcvxv666/fomo-robinhood-radar	127	—	~3k	Automated safety check: Warn	MIT	3 days ago
LangBot EBA Adapter Developmentlangbot-app/LangBot	18k	—	~4k	Automated safety check: Pass	Apache-2.0	yesterday
Caspian Connect DiscordTryCaspian/caspian-sdk	973	—	~376	Automated safety check: Notes	Apache-2.0	1 mo ago
Tg Bot Opsserejaris/personal-corp-os	229	—	~1.6k	Automated safety check: Notes	MIT	2 days ago
Workspace APIfriday-platform/friday-studio	104	—	~9.3k	Automated safety check: Notes	Custom licence	1 mo ago

Similar skills

Fomo Agent
cvxv666/fomo-robinhood-radar
FOMO Robinhood Radar — a research watchlist of Robinhood Chain memecoin traders discovered through fomo.family.
127 GitHub stars~3k tokensUpdated 3 days ago
Backend & APIsAuto-check: warnings
LangBot EBA Adapter Development
langbot-app/LangBot
Guides building, migrating and testing LangBot messaging-platform adapters for the Event-Based Agents layout, with unified event and message conversion.
18k GitHub stars~4k tokensUpdated yesterday
Backend & APIsAuto-check passed
Caspian Connect Discord
TryCaspian/caspian-sdk
Connect Caspian Discord for OpenCode (install OAuth or BYO bot token), enable discord in caspian.json channels, and tell the user to restart.
973 GitHub stars~376 tokensUpdated 1 mo ago
Backend & APIsAuto-check: notes
Tg Bot Ops
serejaris/personal-corp-os
A skill your agent uses when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway.
229 GitHub stars~1.6k tokensUpdated 2 days ago
Backend & APIsAuto-check: notes
Workspace API
friday-platform/friday-studio
Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYDURL.
104 GitHub stars~9.3k tokensUpdated 1 mo ago
Backend & APIsAuto-check: notes
Whatsapp Telegram
ericrisco/rsc-harness
A skill your agent uses when wiring an app or agent to message customers over the WhatsApp Cloud API or a Telegram bot — order updates, OTP codes, reminders, alerts and broadcasts — or when…
174 GitHub stars~2.9k tokensUpdated yesterday
Backend & APIsAuto-check passed

Questions about Fatecat

What does Fatecat do?

When should I use Fatecat?

Fatecat fits situations like: 用户要求测算、排盘、生成报告、启动 Web/API/Bot、验收 skill、导出 bundle、检查生产可用性.

How do I install Fatecat in Claude Code?

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

How do I install Fatecat in Codex?

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

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

What does Fatecat need to run?

Going by SKILL.md and its folder, Fatecat needs the command-line tools its instructions call (bash and git).

Does Fatecat access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Fatecat safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. 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.

What licence does Fatecat use?

Fatecat is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fatecat use?

About 1.7k tokens (SKILL.md is roughly 6.7k 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 9.9k tokens, read only when the agent opens those files.

What are the alternatives to Fatecat?

Skills that share tags, products or a category with Fatecat: Fomo Agent (cvxv666/fomo-robinhood-radar, 127 stars), LangBot EBA Adapter Development (langbot-app/LangBot, 18k stars), Caspian Connect Discord (TryCaspian/caspian-sdk, 973 stars) and Tg Bot Ops (serejaris/personal-corp-os, 229 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fatecat?

tradecatlabs (a GitHub user) maintains it in tradecatlabs/fatecat, which has 202 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 25, 2026.

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

Install Fatecat

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

fatecat Skill

When to Use This Skill

Not For / Boundaries

Quick Reference

1. 确认仓库位置

2. 首次安装运行时

3. 标准纯分析预检

4. 预检并生成样例输出

5. 用输入文件生成 JSON

6. 用 JSON 字符串生成 JSON

7. 启动 Web / API 前验收

8. 启动 Telegram Bot 前验收

9. 发布前完整验收

10. 清理本地运行态

11. 导出 lite skill 包并检查卫生

12. 生产就绪门禁

13. 校验当前 skill

Execution Logic

Examples

Example 1: 首次接手仓库

Example 2: 生成排盘 JSON

Example 3: 启动 Web HTML 页面

Example 4: 发布前完整门禁

References

Maintenance

Files

Compare with similar skills

Similar skills

More from tradecatlabs/fatecat

Related

Questions about Fatecat