OpenParable
Skip to content

Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

review-branch

Review changes in the current Git branch and suggest improvements. Triggers: "review branch", "review changes", "code review".

868 repo stars74 repo forks
Testing & Quality

f8-editor-event-workflow

Use when working with Event editor tools — event system monitor window for debugging active listeners in F8Framework.

866 repo stars139 repo forks
Testing & Quality

diagnosing-bugs

A discipline for hard bugs, flaky tests, CI hangs, and performance regressions in this SDK. Use when the user says "diagnose" or "debug this", reports something broken/throwing/failing/hanging/slow, or a test is flaky. Builds a tight, red-capable feedback loop before hypothesizing.

864 repo stars295 repo forks
Testing & Quality

test-guidelines

Enforce Sentry Dart/Flutter SDK test conventions for naming, structure, and fixtures. Use when writing tests, adding tests, modifying tests, reviewing test code, fixing failing tests, adding test coverage, TDD, test-first / red-green, reproducing bugs with tests, regression tests, or test refactoring in any package in this Melos monorepo.

864 repo stars295 repo forks
Testing & Quality

debug-claude-session

Investigate a specific Claude Code session by session ID — correlate the local transcript (`~/.claude/projects/...jsonl`) with the router's production logs to understand what the client rendered vs. what the upstream served. Use when given a session ID and asked "why did X render?" for a Claude Code conversation routed through the router.

852 repo stars38 repo forks
Testing & Quality

test-claude-locally

Run the Weave router locally in docker compose and drive it with `claude -p` to reproduce and verify routing/translation behavior for a specific upstream model (e.g. GLM-5.1, DeepSeek, Qwen). Use when verifying a router fix end-to-end, reproducing a prod routing bug, confirming a model's streaming behavior (nudges, tool-call suppression, loop/no-progress breaks), or testing a `/force-model` route — without touching the user's global Claude Code config.

852 repo stars38 repo forks
Testing & Quality

dynamic-instrumentation

Expertise in LLVM-based dynamic binary instrumentation, runtime tracing, and program monitoring. Use this skill when implementing runtime analysis tools, code coverage systems, profilers, or dynamic security monitors.

851 repo stars101 repo forks
Testing & Quality

support

MyAgents 本地问题诊断、恢复与反馈升级流程。用户描述报错、崩溃、无响应、配置后仍不可用、状态或结果不符合预期、 Task/Goal/Channel/Provider/Runtime/MCP/Plugin/附件/Space 等功能异常,或者前端“小助理诊断/问题反馈”注入诊断上下文时使用。 先用 `/myagents-docs` 确认正确产品预期,再以本地状态、CLI、日志和必要 probe 分类、修复、验证;确认产品缺陷或功能建议后, 在用户确认下形成并提交脱敏 Issue。普通“是什么/怎么用/入口在哪”不使用本 skill,直接使用 `/myagents-docs`。

847 repo stars97 repo forks
Testing & Quality

proofshot

Visual verification of UI features. Use after building or modifying any UI component, page, or visual feature. Starts a verification session with video recording and error capture, then you drive the browser to test, then stop to bundle proof artifacts for the human.

839 repo stars44 repo forks
Testing & Quality

bk-monitor-security-audit

对前端代码进行安全审计,检测 XSS、CSRF 等漏洞。当用户请求代码审查或询问代码安全性时使用。

838 repo stars261 repo forks
Testing & Quality