Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yecllsl/trae-agent-skills --skill coros-activity-downloadergit clone --depth 1 https://github.com/yecllsl/trae-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yecllsl/trae-agent-skills/coros-activity-downloader)<a href="https://agentmods.dev/skills/yecllsl/trae-agent-skills/coros-activity-downloader"><img src="https://agentmods.dev/badge/skills/yecllsl/trae-agent-skills/coros-activity-downloader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yecllsl/trae-agent-skills/coros-activity-downloader"><img src="https://agentmods.dev/badge/skills/yecllsl/trae-agent-skills/coros-activity-downloader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.01591 |
| Opus 5 | $0.00010 | $0.00796 |
| Sonnet 5 | $0.00004 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
coros-activity-downloader scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
│ urllib → https://oss.coros.com/fit/{userId}/{labelId}.fit │ How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coros活动数据下载技能
Purpose
从 COROS Training Hub 自动下载跑步活动记录(FIT 格式),支持智能去重和增量同步,适用于:
- 定期备份运动数据
- 批量导出活动记录
- 自动化数据同步任务
Prerequisites
- COROS 账户:已登录 COROS Training Hub(https://t.coros.com)
- Chrome DevTools MCP:已配置 Chrome DevTools MCP 连接器,确保浏览器已登录 COROS 账户
- Python 环境:Python 3.6+(用于辅助脚本)
- 配置文件:
config.json中设置正确的downloadDir
Usage
自动化任务调用
调用 coros-activity-downloader 技能,下载最新的不重复的跑步记录
执行步骤
- 使用
mcp_Chrome_DevTools_MCP_navigate_page访问活动列表页面https://t.coros.com/admin/views/activities - 使用
mcp_Chrome_DevTools_MCP_evaluate_script执行 JavaScript 提取活动列表数据(labelId、name、sportType) - 筛选
sportType=100的跑步活动 - 扫描下载目录,基于 labelId 去重
- 将未下载的活动列表作为
--activities-json参数传入 Python 脚本 - 脚本通过 HTTP 直接请求 COROS CDN 下载 FIT 文件
- 保存到配置的下载目录
命令行脚本
# 使用 Chrome DevTools MCP 获取活动后,通过脚本下载
python scripts/download_coros.py --count 15 --activities-json '<JSON>'
# 指定下载目录
python scripts/download_coros.py --download-dir "D:\COROS_Backup" --activities-json '<JSON>'
# 仅验证现有文件
python scripts/download_coros.py --validate-only
# JSON 输出模式(便于程序化调用)
python scripts/download_coros.py --json-output --activities-json '<JSON>'
参数说明
| 参数 | 类型 | 默认值 | 说明 |
|---|---|---|---|
--count |
int | 10 | 下载数量 |
--activities-json |
string | - | 活动列表 JSON 字符串 |
--label-ids |
string | - | 直接指定 labelId(逗号分隔) |
--user-id |
string | config.json 配置值 | COROS 用户 ID |
--download-dir |
string | config.json 配置值 | 下载目录 |
--sport-type |
int | 100 | 运动类型(100=跑步) |
--validate-only |
flag | false | 仅验证,不下载 |
--json-output |
flag | false | JSON 格式输出 |
--show-config |
flag | false | 显示当前配置并退出 |
Architecture
┌──────────────────────────────────────────────────────────────────────────┐
│ 执行流程 │
├──────────────────────────────────────────────────────────────────────────┤
│ │
│ 1. 访问活动页面 │
│ navigate_page(url="https://t.coros.com/admin/views/activities") │
│ │ │
│ ▼ │
│ 2. 提取活动数据 │
│ evaluate_script(提取 labelId + name + sportType) │
│ │ │
│ ▼ │
│ 3. 筛选跑步活动 │
│ filter(sportType === 100) │
│ │ │
│ ▼ │
│ 4. 去重检查 │
│ scan(downloadDir) → existing labelIds │
│ │ │
│ ▼ │
│ 5. 传入 Python 脚本 │
│ --activities-json '<新活动JSON>' │
│ │ │
│ ▼ │
│ 6. 脚本通过 HTTP 请求 COROS CDN 下载 FIT │
│ urllib → https://oss.coros.com/fit/{userId}/{labelId}.fit │
│ │ │
│ ▼ │
│ 7. 保存文件 │
│ {name}_{labelId}.fit │
│ │
└──────────────────────────────────────────────────────────────────────────┘
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 161 lines · 19 tokens per session scan A fe216723b576
coros-activity-downloader is a skill published in the GitHub repository yecllsl/trae-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,591 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wechat-article-downloader
Download WeChat official account articles in multiple formats (HTML, PDF, Word, Markdown, TXT, MHTML), including single article download, collection (appmsgalbum) download, local bulk workflows, and metadata export. Use this skill when users ask to download WeChat articles, download public account collections, batch…
c-video
Download videos, extract audio, convert formats, and clip segments using yt-dlp and ffmpeg. Supports YouTube, Vimeo, and hundreds of other sites.
s3-storage-operations
A guide for managing files in S3-compatible object storage, such as Amazon S3, MinIO, or Qiniu Kodo. Object storage keeps files online and can provide links for sharing or downloading.
media-download
Download video (or audio) from YouTube, Rumble, and other yt-dlp-supported sites via the media-downloader MCP server, and natively store the downloaded media into the epistemic-graph knowledge graph as a content-addressed blob + :MediaAsset. Use when the agent must fetch a video by URL and optionally persist the raw…
analyze-quantified-self
Compare the user's authorized Quantified Self data across two or more health and fitness domains through its read-only MCP tools. Use for cross-domain questions such as sleep versus training, weight versus activity, or recovery trends that require combining measurements, Training metrics, sleep, activities, or routes…
analyze-quantified-self-sleep
Analyze the user's authorized Quantified Self sleep data through its read-only MCP tools. Use for sleep sessions, duration, stages, efficiency, naps, bedtime or wake-time patterns, HRV, sleep heart rate, blood oxygen, respiration, and sleep-oriented recovery trends; use the cross-domain Quantified Self skill when…