Agent skill

Setup Notifications Via Wecom

by daymade in daymade/claude-code-skills

Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks.

MITAuto-check passedBackend & APIs

Install Setup Notifications Via Wecom

skills CLI
$ npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a claude-code

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

GitHub CLI
$ gh skill install daymade/claude-code-skills setup-notifications-via-wecom --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/daymade/claude-code-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/setup-notifications-via-wecom .claude/skills/setup-notifications-via-wecom && 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
setup-notifications-via-wecom
GitHub stars
1.4k
Token cost
~3.1k tokens
SKILL.md length
1,419 words
Files
8 (incl. scripts, references)
Skills in repo
103
Repo updated
First seen
Licence
MIT

At a glance

Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks.

  • Works in 8 steps: Headline First → Distinguish State vs Delta → Define Every Number → …
  • The user needs to send notifications
  • SKILL.md covers Overview, When to Use This Skill, Quick Start: Configure the… and Message Best Practices, plus 6 more sections
  • Runs Python scripts from its folder; calls uv, claude and curl; reaches qyapi.weixin.qq.com

What it does

Setup Notifications Via Wecom is an agent skill from daymade/claude-code-skills. Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, alerts, backup completion reports, or status updates via WeCom; when they mention 企业微信, 企微机器人, webhook, or alerting; or when a message needs to be clear, unambiguous, and technically precise rather than vague or condescending.

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `evals/evals.json`, `references/message_best_practices.md` and `references/sls-recurring-notifications.md`).

It sits in Backend & APIs, covering Webhooks and Messaging and chat bots. It works with WeChat. The repository describes itself as: Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows. The licence is MIT.

When your agent uses it

  • The user needs to send notifications
  • Backup completion reports
  • Status updates via WeCom
  • They mention 企业微信

Example prompts

  • “/setup-notifications-via-wecom”

Requirements

  • Python 3
  • A credential in YOUR_KEY

Workflow steps

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

  1. Headline First
  2. Distinguish State vs Delta
  3. Define Every Number
  4. Use Plain Location Names, Not Jargon
  5. Omit Noise
  6. Be Technically Precise, Not Condescending
  7. Include Verification Metrics
  8. End with a Next Action

What it can do on your machine

Read from SKILL.md and the folder at commit 872127b. 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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • claude
    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • qyapi.weixin.qq.com

    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

Setup Notifications Via Wecom loads about 3.1k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 1,419 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.9k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from daymade/claude-code-skills at commit 872127b, republished under its MIT licence (© daymade). 1,419 words, ~3,059 tokens.

Download SKILL.mdSave it as .claude/skills/setup-notifications-via-wecom/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
setup-notifications-via-wecom
description
Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, alerts, backup completion reports, or status updates via WeCom; when they mention 企业微信, 企微机器人, webhook, or alerting; or when a message needs to be clear, unambiguous, and technically precise rather than vague or condescending.

Setup Notifications via WeCom

Overview

This skill helps you send clear, unambiguous technical notifications through a WeCom group bot webhook. Use the setup and sending workflows below:

  1. One-time setup: store the webhook URL, test connectivity, and create a reusable sender script.
  2. Send messages: craft messages that distinguish state from delta, define every number, and avoid the misleading patterns that made earlier backup-sync notifications confusing.

The bundled script scripts/send_wecom.py handles the actual HTTP call, using the host network configuration. Recipient identity is explicit configuration: self may send automatically; others requires human confirmation; missing identity fails fast.

When integrating an existing Alibaba Cloud SLS notification pipeline or a recurring digest, read the SLS adapter guide. Reuse the project's sampler, scheduler and SLS sync owner; the bundled sender continues to own ordinary plain-text sends.

When to Use This Skill

Trigger this skill when the user:

  • Says "send a WeCom notification", "企业微信通知", "企微机器人", or "webhook 通知".
  • Wants to set up alerting for a backup, sync, cron job, or service status.
  • Asks you to write a status/alert message and you need to make it clear and unambiguous.
  • Mentions a message was confusing or misleading and wants it fixed.

Quick Start: Configure the Webhook

  1. Check existing config:

    bash
    cat ~/.config/setup-notifications-via-wecom/config.json

    If it exists and contains webhook_url, skip to Send a Message.

  2. Get the webhook URL from the WeCom group bot settings. It looks like:

    https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY
  3. Store it privately (outside the skill bundle, so it survives updates):

    bash
    mkdir -p ~/.config/setup-notifications-via-wecom
    echo '{"webhook_url": "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY"}' \
      > ~/.config/setup-notifications-via-wecom/config.json
    chmod 600 ~/.config/setup-notifications-via-wecom/config.json
  4. Classify the exact target and bind the canonical sender without exposing or rewriting the webhook value:

    bash
    uv run --no-project python scripts/set_recipient.py \
      --scope self --label "My private self channel"

    Use self only when the configured webhook is visible only to the user. Use others for every other person or group. Do not guess when the target is unknown. The command also records this sender's absolute path and digest; after the sender is upgraded, rerun the command before sending again.

  5. Test connectivity by sending a test message (run from the skill directory):

    bash
    uv run --no-project python scripts/send_wecom.py --message "WeCom webhook test ✅"

    If you see the message in the WeCom group, setup is done.

Message Best Practices

These rules come from real corrections. Apply them to every notification.

1. Headline First

The first line must say what happened. Do not bury the conclusion.

Claude Code 备份同步完成 ✅
2. Distinguish State vs Delta
  • State: current totals (e.g., source has 1075 main sessions, backup has 2328).
  • Delta: what changed in this run (e.g., 13 main sessions + 230 other files were added since 03:00).

Never say "synced 1075 sessions" if only 13 were new today.

3. Define Every Number

Every count must be accompanied by what it counts. Prefer:

- 源目录主 session:1075 个
- 备份主 session:2328 个

Avoid undefined terms like "session" alone — it may include workflow journals, subagent files, or tool outputs.

4. Use Plain Location Names, Not Jargon

Prefer:

  • "电脑上" / "源目录"
  • "备份里" / "备份仓库"

Avoid:

  • "当前"
  • "含历史"
  • "旧 session" (unless defined)
5. Omit Noise

Do not include commit hashes, file paths, internal documentation references, or verbose explanations unless the user explicitly asks for them.

6. Be Technically Precise, Not Condescending

Use correct technical terms and define them. Do not translate everything into "大白话" simplifications that hide precision.

7. Include Verification Metrics

When the user asked "does it miss anything?", answer directly:

- 验证:0 缺失,0 滞后
8. End with a Next Action

Tell the user whether they need to do anything:

- 下一步:无需操作,下次自动同步 03:00

Notification Templates

Backup Sync Completion

Use when a backup/sync job finishes and you need to report completeness.

Claude Code 备份同步完成 ✅

- 自动同步:今日 03:00 正常执行
- 本次手动同步:补充 03:00 后的增量
  - 主 session:13 个
  - 子代理/工具输出/工作流:230 个
  - 合计:243 个文件
- 验证:0 缺失,0 滞后
- 当前状态:
  - 源目录主 session:1075 个
  - 备份主 session:2328 个
- 下一步:无需操作,下次自动同步 03:00
Alert

Use when something requires immediate action. Do not use this template for routine "all good" updates.

🚨 [P?] [服务/任务名] [症状]

- 影响:[谁/什么受影响,程度如何]
- 严重程度:[P1–P5 等级]
- 开始时间:[YYYY-MM-DD HH:MM TZ]
- 已采取:[正在做的动作]
- 下一步:[建议动作或预计下次更新时间]
- 相关链接:[dashboard/runbook,可选]

Rules:

  • Alert on symptoms, not causes (e.g., "API error rate > 10%" not "CPU 99%").
  • If the recipient cannot do anything concrete, do not send it as an alert.
  • Be honest about uncertainty; do not guess at root cause.
Status Update

Use for routine "all good" updates.

[任务名] 状态正常 ✅

- 检查时间:2026-06-24 03:00 CST
- 关键指标:
  - 源目录主 session:1075 个
  - 备份主 session:2328 个
- 本次变更:无
- 下一步:无需操作

Send a Message

Read recipient_scope and recipient_label before sending. A self target is the user's own delivery channel and needs no authorization. An others target is an external send: show the exact label and message and wait for the active human-confirmation gate. Missing/invalid metadata is a configuration error, not permission to guess.

Matching webhook URLs proves the same endpoint, not the recipient scope. If new observations conflict with the stored self label, pause only that send and verify the exact group and audience. A displayed member name alone does not prove a different person's identity. Preserve normal automatic delivery for a confirmed self binding; do not relabel a group or rewrite shared metadata to bypass the confirmation boundary. For recurring delivery to others, confirmation must cover the exact group, report content and schedule, plus any separately required deployment approval.

Option A: Use the bundled script directly
bash
uv run --no-project python scripts/send_wecom.py \
  --message "你的消息内容"

For multiline messages, use a file:

bash
cat > /tmp/wecom_msg.txt <<'EOF'
Claude Code 备份同步完成 ✅

- 验证:0 缺失,0 滞后
EOF

uv run --no-project python scripts/send_wecom.py \
  --file /tmp/wecom_msg.txt
Option B: Inline curl

If you prefer not to use the script:

bash
curl -s -X POST 'https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "msgtype": "text",
    "text": {
      "content": "YOUR_MESSAGE"
    }
  }'

Network: Inherit the host/project HTTP(S) proxy and no_proxy policy. A required proxy must remain in use; do not infer a direct-connect requirement from the Tencent domain. Configure an HTTP(S) proxy explicitly when the host requires one: Python urllib does not implement generic SOCKS ALL_PROXY routing. On macOS, an empty proxy environment can still select the system proxy. For proxy selection, exceptions and HTTP-bypass versus TUN diagnosis, load tunnel-doctor and its proxy-conflict reference (proxy_conflict_reference.md, NO_PROXY section); inspect the sender process rather than clearing all proxies.

After upgrading the sender, refresh its configured digest using the existing set_recipient.py workflow, preserving the same scope and label. Do not relabel a group as self merely to pass the guard.

Show full SKILL.md (529 more words)Show less

Workflow: Add WeCom Notification to a Script

When a user asks "let my backup script send WeCom notifications", do the following:

  1. Confirm the webhook is configured (see Quick Start).
  2. Read the explicit recipient scope/label; auto-send only when scope is self.
  3. Identify the notification type (backup-complete, alert, status-update, custom).
  4. Collect the exact numbers and their definitions from the script output.
  5. Craft the message using the templates above.
  6. For others, obtain human confirmation; then call scripts/send_wecom.py.
  7. Verify the message arrived at the configured target. For automatic monitor/worker integration, follow the receipt contract below.
Automatic worker receipts

Use the existing bound sender and target; keep event identity and delivery state in the owning worker. For one automatic event, call send_message(..., max_attempts=1) or the supported guard-owned outbox path. The general manual-send retry default is not the worker's delivery policy.

Classify the parsed response before deciding whether a later attempt is permitted:

EvidenceWorker outcome
JSON object with integer errcode=0API accepted; receiver confirmation is a separate observation
JSON object with nonzero integer errcodeExplicit API rejection
Missing/null errcode, boolean, string, non-integer, invalid JSON, timeout or lost connectionUnknown; keep the event identity and do not automatically replay it

For Python, test type(code) is int; isinstance(False, int) is true and False == 0 must not become acceptance. If the generic sender raises before returning a valid response, the owning worker keeps the result unknown. A new test must exercise a genuinely distinct event with an explicit test label, not rename or resubmit an ambiguous old event. Verify the actual scheduler/worker → event → sender → receipt path; a standalone bot call does not validate the background chain.

What This Skill Does NOT Do

  • It does not create or manage WeCom group bots — get the webhook key from WeCom first.
  • It does not infer who a webhook reaches — classify the target explicitly with set_recipient.py.
  • It does not handle rich media messages (markdown cards, news, images) — only plain text.
  • Manual --message / --file sends retry transient errors up to 3 times. Guard-owned automatic --outbox delivery makes exactly one HTTP attempt and requires the guard-approved payload digest; a later run never sends a pre-existing payload.
  • It does not change host proxy configuration or switch routes automatically after a failure.

Troubleshooting

Connection closed or timeout

Inspect the configured route without printing proxy credentials. Follow the host's approved direct/proxy policy and diagnose the failing connection on that route. Do not silently clear proxies, try another endpoint, or replay an ambiguous send.

Message not received, but curl returned 200

Check the response body: HTTP 200 with nonzero errcode is failure. errcode=0 means API acceptance, not recipient receipt. Verify the intended group and message where receipt matters. A direct bot test cannot validate an SLS/other scheduler: exercise and inspect that native path separately within the authorized test count.

Config file not found

Run the setup step again. The script expects ~/.config/setup-notifications-via-wecom/config.json with a webhook_url field.

References

  • references/message_best_practices.md — condensed checklist distilled from this session's corrections.
  • references/sls-recurring-notifications.md — read for SLS-backed recurring reports: result-size limits, evaluation dates, existing-owner reuse and native delivery acceptance.
  • scripts/send_wecom.py — the sender script.
  • scripts/set_recipient.py — atomically records self versus others plus the canonical sender path/digest without printing the webhook.

© daymade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in setup-notifications-via-wecom of daymade/claude-code-skills.

  • SKILL.md
  • evals/evals.json
  • references/message_best_practices.md
  • references/sls-recurring-notifications.md
  • scripts/send_wecom.py
  • scripts/set_recipient.py
  • tests/test_network_policy.py
  • tests/test_recipient_config.py

Open the folder on GitHubat commit 872127b

Compare with similar skills

Setup Notifications Via Wecom 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.

Setup Notifications Via Wecom compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Setup Notifications Via Wecom this skilldaymade/claude-code-skills1.4k—~3.1kAutomated safety check: PassMIT
PR Review Provideryansongda/pay5.4k—~2.4kAutomated safety check: PassMIT
AI Model NodejsTencentCloudBase/CloudBase-AI-Toolkit1.1k2 repos~5kAutomated safety check: PassMIT
X Twitter ScraperXquik-dev/x-twitter-scraper2101 repos~2.6kAutomated safety check: PassMIT
Integrate Whatsappgokapso/agent-skills177—~4.8kAutomated safety check: PassNone
Paper Feishu Digestchtc66/academic-skills360—~348Automated safety check: PassMIT

Similar skills

  • PR Review Provider

    yansongda/pay

    A skill your agent uses when reviewing PRs that add or modify a payment Provider in yansongda/pay - covers plugin pipeline, multi-tenant safety, signature verification, docs, and naming conventions.

    5.4k GitHub stars~2.4k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • AI Model Nodejs

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses for Node.js backend AI via @cloudbase/node-sdk (=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration.

    1.1k GitHub starsUsed in 2 repos~5k tokens
    Backend & APIsAuto-check passed
  • X Twitter Scraper

    Xquik-dev/x-twitter-scraper

    Use Xquik to fetch X (Twitter) data or act through a connected account: search, profiles, followers, replies, threads, timelines, media downloads, bulk exports, trends, monitors, signed webhooks…

    210 GitHub starsUsed in 1 repo~2.6k tokens
    Backend & APIsAuto-check passed
  • Integrate Whatsapp

    gokapso/agent-skills

    Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media.

    177 GitHub stars~4.8k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • Paper Feishu Digest

    chtc66/academic-skills

    monitor recent arxiv papers and produce a chinese digest when the user needs a filtered paper watchlist, a ranked update for agent or rag related topics, or an optional feishu webhook push from…

    360 GitHub stars~348 tokensUpdated 6 mo ago
    Backend & APIsAuto-check passed
  • Specfusion

    LiangNiang/OpenMantis

    企业微信 飞书 钉钉 淘宝 小红书 抖音电商 微信小程序 微信小店 拼多多 有赞 微信支付 支付宝 京东 SHEIN 得物 火山引擎 阿里云百炼 泛微 北森 API文档搜索。

    110 GitHub stars~2.1k tokensUpdated 4 mo ago
    Backend & APIsAuto-check: notes

More from daymade/claude-code-skills

All 103 skills in this repo
  • Video Comparer

    daymade/claude-code-skills

    This skill should be used when comparing two videos to analyze compression results or quality differences.

    1.4k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check: notes
  • CLI Demo Generator

    daymade/claude-code-skills

    Generates professional animated CLI demos as GIFs using VHS terminal recordings.

    1.4k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Doc To Markdown

    daymade/claude-code-skills

    Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing.

    1.4k GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Interaction Design Board

    daymade/claude-code-skills

    Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation.

    1.4k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Auto Repo Setup

    daymade/claude-code-skills

    Diagnoses and repairs repository setup and guarded Git workflows for Claude Code or Codex — environment repair, startup sync, hook auditing, collaborator handoff.

    1.4k GitHub stars~2.8k tokensUpdated today
    Auto-check: notes
  • Bigdata Skill

    daymade/claude-code-skills

    Pulls Bigdata.com (RavenPack) financial and news data via the official bigdata-client SDK and /v1/ REST endpoints — structured financials, prices, analyst estimates, entity-sentiment series…

    1.4k GitHub stars~3.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Setup Notifications Via Wecom

What does Setup Notifications Via Wecom do?

Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Setup Notifications Via Wecom is an agent skill from daymade/claude-code-skills. Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks.

When should I use Setup Notifications Via Wecom?

Setup Notifications Via Wecom fits situations like: the user needs to send notifications; backup completion reports; status updates via WeCom; they mention 企业微信.

How do I install Setup Notifications Via Wecom in Claude Code?

Run `npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a claude-code`. Or copy the skill folder (setup-notifications-via-wecom in daymade/claude-code-skills) into .claude/skills/setup-notifications-via-wecom in your project. Claude Code loads it when a task matches its description.

How do I install Setup Notifications Via Wecom in Codex?

Run `npx skills add daymade/claude-code-skills --skill setup-notifications-via-wecom -a codex`. Or copy the skill folder (setup-notifications-via-wecom in daymade/claude-code-skills) into .agents/skills/setup-notifications-via-wecom in your project. Codex loads it when a task matches its description.

Can I use Setup Notifications Via Wecom 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 daymade/claude-code-skills --skill setup-notifications-via-wecom -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup-notifications-via-wecom, .gemini/skills/setup-notifications-via-wecom, .github/skills/setup-notifications-via-wecom and .opencode/skills/setup-notifications-via-wecom in your project.

What does Setup Notifications Via Wecom need to run?

Going by SKILL.md and its folder, Setup Notifications Via Wecom needs Python for the scripts in its folder and the command-line tools its instructions call (uv, claude and curl). Our summary lists: Python 3; A credential in YOUR_KEY.

Does Setup Notifications Via Wecom access the network?

SKILL.md names 1 domain. In commands or code: qyapi.weixin.qq.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Setup Notifications Via Wecom 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Setup Notifications Via Wecom use?

Setup Notifications Via Wecom is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Setup Notifications Via Wecom use?

About 3.1k tokens (SKILL.md is roughly 12k 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 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Setup Notifications Via Wecom?

Skills that share tags, products or a category with Setup Notifications Via Wecom: PR Review Provider (yansongda/pay, 5.4k stars), AI Model Nodejs (TencentCloudBase/CloudBase-AI-Toolkit, 1.1k stars), X Twitter Scraper (Xquik-dev/x-twitter-scraper, 210 stars) and Integrate Whatsapp (gokapso/agent-skills, 177 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Setup Notifications Via Wecom?

daymade (a GitHub user) maintains it in daymade/claude-code-skills, which has 1,447 GitHub stars. The repository holds 103 skills in this directory. The repository was last updated on October 9, 2026.

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