WxPusher Integration
Integrate and troubleshoot WxPusher notifications for scripts, backends, cron jobs, and CI.
Free
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsWxPusher Integration
Example session with this skill installed
We have already chosen WxPusher for our scheduled-job alerts. In a mock test, HTTP status is 200 and the top-level JSON code is 1000. The returned data contains two target results: target A has code 1000; target B has a non-1000 code. Should the job report delivery success? Explain the outcome, the next checks, and the regression cases we need. Do not send a real message.
- Read your context and instructions
- Compiled the wxpusher integration
Outcome
Report partial failure. HTTP 200 confirms the HTTP exchange succeeded, and the top-level code 1000 indicates the API accepted the request at that level. Target B failed its business-level check, so the job must not report that all targets succeeded. Even target A's code 1000 proves API acceptance only, not that a person received or read the message.
| Signal in the supplied mock response | Interpretation |
|---|---|
| HTTP 200 | The HTTP request succeeded. Continue checking the response body. |
| Top-level code 1000 | The request passed the top-level business check. |
| Target A code 1000 | The API accepted that target result. Receipt is still unconfirmed. |
| Target B non-1000 code | That target failed. Preserve a sanitized failure reason. |
| Overall result | Partial failure; do not mark every target as successful. |
Next checks
- Inspect target B's returned business error and the intended recipient configuration without logging appToken, SPT, or complete authenticated URLs.
- Do not retry authentication, validation, or permission errors indefinitely. Apply the project's bounded retry policy only to eligible transient failures such as network errors, 429 responses, or 5xx responses.
- Consider duplicate delivery before retrying a request that includes already accepted targets.
- If the API accepts a request but WeChat shows nothing, separately check ClawBot binding, enabling, activation, and channel limits. API acceptance and channel reception are different checks.
Regression cases
Cover complete acceptance, a non-1000 top-level code, mixed target results, HTTP failure, invalid JSON, timeout, missing configuration, 429, and 5xx responses. Also confirm that notification failure follows the scheduled job's intended failure policy and does not accidentally replace its original error.
This is an illustrative analysis of the supplied mock response. No WxPusher API request or live delivery was performed.
Connects securely to your tools. The creator never sees your data.
About this skill
A free, MIT-licensed Agent Skill for integrating WxPusher into an existing project with maintainable code, explicit failure handling, and secure configuration. The skill and its reference guides are primarily in Simplified Chinese.
What it helps with
- Add notifications to scripts, backend services, scheduled jobs, CI pipelines, and monitoring workflows.
- Choose standard POST delivery to a UID or Topic, or use SPT when that workflow has been selected.
- Check HTTP status, JSON parsing, the top-level business code, and every returned target result. API acceptance is not proof of delivery or reading.
- Reuse the project's HTTP client and notification interfaces; configure timeouts and bounded retries for eligible transient failures.
- Keep credentials in approved secret stores or named environment variables, and redact sensitive request URLs and logs.
- Diagnose missing notifications, configuration errors, rate limits, and WeChat ClawBot channel issues.
When to use it
Explicitly ask for WxPusher, or use it after WxPusher has already been selected in the conversation. Generic requests for WeChat notifications do not automatically select this service.
Example: “Add WxPusher failure notifications to my Python scheduled job. Use environment-variable placeholders and mock responses; do not send a real message.”
WeChat support
WxPusher supports its own clients and WeChat ClawBot (iLink) text notifications. WeChat reception requires binding, enabling, and activation, and is subject to channel limits. This does not provide messaging to arbitrary WeChat contacts or groups.
Package and installation
Keep the complete wxpusher-integration folder together: SKILL.md, LICENSE.md, five reference guides, and optional agents/openai.yaml metadata. Install it in your agent's supported skills directory. References cover APIs, configuration, integration patterns, troubleshooting, and provenance.
The skill consists only of Markdown and YAML. It has no bundled executable or Python/Node.js runtime dependency. During an integration task, the agent uses the project's existing tools. Live delivery requires the user's own WxPusher configuration; implementation and mock testing can start with placeholders.
Version and provenance
Version 1.0.4 · MIT · Official API documentation last verified on 2026-10-08.
The uploaded package contains 8 files matching that Git commit byte for byte. Offline structure, local references, YAML, JSON examples, and basic credential-shape checks passed. No live WxPusher delivery test was performed for this listing.
Independently maintained; not an official WxPusher project.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 10 days ago
- Free to download with an account