“debugging”

Diagnoses and resolves memory leaks in JavaScript/Node.js applications.

This skill should be used when debugging frontend/UI bugs that need runtime evidence.

Gates test-only code behind one literal TEST_ONLY switch: debug menu, debug link, simulated clock and offline.

Diagnose WHY a failing verification won't converge — reproduce first, hypothesis + discriminating experiment, classify the defect (code / test / plan /…

Diagnoses and resolves memory leaks in JavaScript/Node.js applications.

Diagnosis loop for bugs and failing behavior.

Apply Cursor's Debug Mode system prompt when investigating reproducible bugs with non-obvious root causes.

Use when encountering any technical failure or unexpected behavior, including production incidents, test/build/CI failures, crashes, integration issues…

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts.

Observe and troubleshoot WhatsApp in Kapso: search Logs across API, Meta webhook, workflow, and webhook-delivery events; debug message delivery; inspect…

Build and debug Kapso WhatsApp workflows, triggers, functions, and executions.

数学研究助手：将 AI 研究目标转成数学对象、可实现机制和可验证结论；用于架构/算子构造、理论分析、跨数学领域思路发现与结构迁移、研究相关数学查询，以及密码学定义、构造、归约与协议审查。纯实现型 debug、重构、调参和一般代码审查不触发。 English: Turn AI research goals into…

Create, wire up, test and debug agent hooks: Claude Code settings.json or plugin hooks, Cursor hooks.json, or a shared hooks/ tree, with working recipes.

Use when designing, reviewing, adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP…

用于诊断（debug）疑难 bug、测试失败、性能退化和偶发问题；用户附报错或堆栈请求修复时也触发。

Use when developing or reviewing LazyCat/LightOS WebShell provider LPK apps, debugging provider discovery, launch URL, session restore, mobile terminal UX…

Deploy, protect, debug, and verify a private Cloudflare Workers site for an exact user or email allowlist.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts.

Create, implement, deploy, and debug Adobe Runtime actions with consistent layout, validation, and error handling.

Operates HyperExecute end-to-end for TestMu AI/LambdaTest cloud test execution: analyze projects, create YAML, validate locally, run CLI jobs, debug failures…

Build, bootstrap, upgrade, test, debug or review applications that consume NewHeap Platform packages.

Use when creating, authoring, refining, or debugging skills for AI agents.

Use only when replaying or debugging the legacy Dasheng finalization step; the standard mainline now splits this logic across rewrite, material, publish, and…