quota-watch
查询并巡检 AI API 订阅额度与余额(任何提供额度/余额查询接口的平台均可接入,通用中转站方式优先,另有常用平台内置适配),按周窗口理想消耗曲线判定用量偏快还是偏慢,支持 HTML 邮件与 macOS 本地通知推送。当用户想查 API 余额、剩余额度、套餐用量,或要做定时额度巡检时使用。
Skill by huyikai
Chalk Labs
Need help deploying quota-watch?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/huyikai-quota-watch
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend, backend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/quota-watch
What's inside
- Skill name
quota-watch- Description
- 查询并巡检 AI API 订阅额度与余额(任何提供额度/余额查询接口的平台均可接入,通用中转站方式优先,另有常用平台内置适配),按周窗口理想消耗曲线判定用量偏快还是偏慢,支持 HTML 邮件与 macOS 本地通知推送。当用户想查 API 余额、剩余额度、套餐用量,或要做定时额度巡检时使用。
- License
- MIT
- Instructions
- 67 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (6)
- .gitignore
- LICENSE
- README.md
- SKILL.md
- config.example.json
- quota_check.py · scripts/
SKILL.md (first lines)
# quota-watch — AI API 额度巡检 查询订阅制 AI 平台的额度消耗进度,与「按剩余时间线性均摊」的理想曲线对比, 直观回答:**现在用得偏快了还是偏慢了?要不要调整使用力度?** ## 使用步骤 ### 1. 配置 复制 `config.example.json` 为 `./quota-watch.json` 或 `~/.config/quota-watch/config.json`, 填入各平台的 API Key。密钥支持 `"env:VARNAME"` 形式引用环境变量,避免明文落盘。 每个 provider 是一个条目,`type` 指定接入方式: | 接入方式 | type | 说明 | |---|---|---| | 通用中转站(推荐) | `relay_quota` | 任何兼容 `/v1/usage` 配额窗口的平台/中转站,填 `base_url` 即可接入,密钥在站点控制台获取 | | 内置适配 | `zhipu` / `minimax` / `deepseek` | 常见订阅/按量平台的内置适配,密钥在各平台开放平台控制台获取 | ### 2. 运行 ```bash python3 scripts/quota_check.py # 巡检 + 按配置推送 python3 scripts/quota_check.py --dry-run # 只看报告,不推送 python3 scripts/quota_check.py --json # JSON 输出(便于其他工具消费) python3 scripts/quota_check.py --config ~/my.json ``` ### 3. 解读判定 偏差 = 实际已用% − 理想已用%(理想 = 已过周窗口时间 ÷ 窗口总长): | 偏差 | 判定 | 建议 | |---|---|---| | > +15pp | 🔥 明显偏快 | 大幅收敛用量 | | > +5pp | ⚡ 偏快 | 收敛用量 | | −5 ~ +5pp | ✅ 正常 | 贴近理想曲线 | | < −5pp | 🐢 偏慢 | 可以加大用量 | | < −15pp | 🐌 明显偏慢 | 额度在闲置 | 脚本还会按当前平均速度外推耗尽时间点:若早于窗口结束,会在卡片中给出 ⚠ 预警。 ### 4. 定时自动化 crontab 方式(每小时): ```cron 0 * * * * /usr/bin/python3 /path/to/quota-watch/scripts/quota_check.py >> ~/.quota-watch/cron.log 2>&1 ``` 在 ZCode / Claude Code 等智能体里,可用定时任务每小时执行本脚本并汇报结果。 ## 输出说明 - **终端**:纯文本摘要 - **邮件**(`email.enabled: true`):HTML 卡片周报,主题即状态(名称即配置里的 provider `name`), 如 `[额度用量] 主力套餐 7%【🐢偏慢7%】 备用中转 32%【✅正常】 14:00` - **macOS 通知**(`mac_notify: true`):通知中心弹窗,存在偏快/耗尽预警时带提示音 - **历史**:每次运行追加到 `history_path`(JSONL),报告自动带「小时增量」 ## 注意事项 - 邮件用 SMTP 授权码(不是登录密码):QQ 邮箱在 设置→账号→开启 SMTP服务 处生成 - 密钥与配置只存本地,脚本不上传任何数据 - 各平台接口若变更(鉴权方式、路径),以官方文档为准
From huyikai/skills, MIT.
More from huyikai/skills
- 0.567score
zentao17
huyikai
通过 zentao17 命令行工具查询和操作公司自部署禅道(ZenTao 17.8,v1 RESTful API)。当用户提到禅道、zentao、查 Bug、获取 Bug 列表、解决 Bug、关闭 Bug、激活 Bug、指派 Bug 等操作时使用本技能。不适用于禅道 22+(那应该用官方 zentao-cli)。
SkillAFreshness: AClaude Code +9 - 0.479score
my-skill-name
huyikai
一句话说明这个 skill 做什么、什么场景下触发。agent 依靠这句决定是否使用本 skill,要写清触发条件和能力边界。
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/huyikai/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from huyikai
- 0.567score
zentao17
huyikai
通过 zentao17 命令行工具查询和操作公司自部署禅道(ZenTao 17.8,v1 RESTful API)。当用户提到禅道、zentao、查 Bug、获取 Bug 列表、解决 Bug、关闭 Bug、激活 Bug、指派 Bug 等操作时使用本技能。不适用于禅道 22+(那应该用官方 zentao-cli)。
SkillAFreshness: AClaude Code +9 - 0.479score
my-skill-name
huyikai
一句话说明这个 skill 做什么、什么场景下触发。agent 依靠这句决定是否使用本 skill,要写清触发条件和能力边界。
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get quota-watch running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
quota-watch skill. Agent Mart. https://agentmart.dev/skills/huyikai-quota-watch (last updated 2026-10-24)