Skip to main content
skills
mp
Skills
クリエイター
職種
ドキュメント
JA
Manusで任意のスキルを実行
ワンクリックで
ワンクリックでManusで任意のスキルを実行
始める
トップに戻る
ワンクリックで任意のスキルを実行
デバッグ - Agent Skills | SkillsMP
ホーム
カテゴリ
debugging
デバッグ
デバッグ、プロファイリング、トラブルシューティング向けエージェントスキルを閲覧。バグを効率的に発見・修正。
スター順
更新順
channel-message-flows
376.6k
openclaw/openclaw
Use when previewing local channel message flow fixtures.
2026-05-19
clawdtributor
376.6k
openclaw/openclaw
Use for OpenClaw clawtributors PR/issue triage: Discrawl discovery, live-open rechecks, deep review, topic grouping, and compact @handle/LOC/type/blast/verification summaries.
2026-05-28
discrawl
376.6k
openclaw/openclaw
Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.
2026-05-29
gitcrawl
376.6k
openclaw/openclaw
GitHub archive: issue/PR search, sync freshness, duplicate clusters, gh-shim PR status, and Gitcrawl repo work.
2026-05-17
notcrawl
376.6k
openclaw/openclaw
Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.
2026-05-17
openclaw-debugging
376.6k
openclaw/openclaw
Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.
2026-05-13
openclaw-landable-bug-sweep
376.6k
openclaw/openclaw
Find or repair small high-confidence non-SDK-boundary OpenClaw bugfix PRs until five are landable.
2026-05-25
openclaw-qa-testing
376.6k
openclaw/openclaw
Run, watch, debug, extend, or explain OpenClaw qa-lab and qa-channel scenarios, artifacts, and live lanes.
2026-05-13
openclaw-secret-scanning-maintainer
376.6k
openclaw/openclaw
Triage, redact, clean up, and resolve OpenClaw GitHub Secret Scanning alerts in issues or PRs.
2026-05-31
openclaw-test-heap-leaks
376.6k
openclaw/openclaw
Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.
2026-05-01
openclaw-test-performance
376.6k
openclaw/openclaw
Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.
2026-05-25
release-openclaw-ci
376.6k
openclaw/openclaw
Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.
2026-06-01
slacrawl
376.6k
openclaw/openclaw
Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.
2026-05-17
telegram-crabbox-e2e-proof
376.6k
openclaw/openclaw
Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
2026-05-18
browser-automation
376.6k
openclaw/openclaw
Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
2026-05-31
canvas
376.6k
openclaw/openclaw
Present HTML on connected OpenClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.
2026-05-17
node-connect
376.6k
openclaw/openclaw
Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
2026-05-22
node-inspect-debugger
376.6k
openclaw/openclaw
Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.
2026-05-17
python-debugpy
376.6k
openclaw/openclaw
Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
2026-05-17
session-logs
376.6k
openclaw/openclaw
Search and analyze your own session logs (older/parent conversations) using jq.
2026-05-17
feature-flags
245.4k
facebook/react
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
2026-01-24
flags
245.4k
facebook/react
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.
2026-01-24
systematic-debugging
216.9k
obra/superpowers
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
2026-05-04
automation-audit-ops
205.5k
affaan-m/ECC
面向ECC的以证据为先的自动化清单与重叠审计工作流。当用户希望在修复任何内容之前了解哪些作业、钩子、连接器、MCP服务器或包装器是活跃的、损坏的、冗余的或缺失时使用。
2026-05-11
benchmark
205.5k
affaan-m/ECC
使用此技能测量性能基线，检测PR前后的回归，并比较堆栈替代方案。
2026-05-11
deep-research
205.5k
affaan-m/ECC
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
2026-04-29
exa-search
205.5k
affaan-m/ECC
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
2026-04-29
frontend-patterns
205.5k
affaan-m/ECC
React, Next.js, 상태 관리, 성능 최적화 및 UI 모범 사례를 위한 프론트엔드 개발 패턴.
2026-03-30
canary-watch
205.5k
affaan-m/ECC
使用此技能在部署、合并或依赖升级后监控已部署的URL是否存在回归问题。
2026-05-11
click-path-audit
205.5k
affaan-m/ECC
追踪每个面向用户的按钮/触点的完整状态变化序列，以发现功能单独工作但相互抵消、产生错误最终状态或使UI处于不一致状态的错误。适用于：系统调试未发现错误但用户报告按钮失效，或在任何涉及共享状态存储的重大重构之后。
2026-05-11
context-budget
205.5k
affaan-m/ECC
审核Claude Code上下文窗口在代理、技能、MCP服务器和规则中的消耗情况。识别膨胀、冗余组件，并提供优先的令牌节省建议。
2026-03-30
deep-research
205.5k
affaan-m/ECC
使用firecrawl和exa MCPs进行多源深度研究。搜索网络、综合发现并交付带有来源引用的报告。适用于用户希望对任何主题进行有证据和引用的彻底研究时。
2026-03-22
ecc-tools-cost-audit
205.5k
affaan-m/ECC
证据优先的ECC工具燃烧和计费审计工作流。用于调查ECC工具仓库中的失控PR创建、配额绕过、高级模型泄漏、重复作业或GitHub App成本激增。
2026-05-11
exa-search
205.5k
affaan-m/ECC
通过Exa MCP进行神经搜索，适用于网络、代码和公司研究。当用户需要网络搜索、代码示例、公司情报、人员查找，或使用Exa神经搜索引擎进行AI驱动的深度研究时使用。
2026-03-22
flutter-dart-code-review
205.5k
affaan-m/ECC
库无关的Flutter/Dart代码审查清单，涵盖Widget最佳实践、状态管理模式（BLoC、Riverpod、Provider、GetX、MobX、Signals）、Dart惯用法、性能、可访问性、安全性和整洁架构。
2026-03-21
laravel-plugin-discovery
205.5k
affaan-m/ECC
通过LaraPlugins.io MCP发现和评估Laravel包。当用户想要查找插件、检查包的健康状况或评估Laravel/PHP兼容性时使用。
2026-05-11
manim-video
205.5k
affaan-m/ECC
构建可复用的Manim解释器，用于技术概念、图表、系统图和产品演示，并在需要时移交给更广泛的ECC视频栈。当用户希望获得清晰的动画解释而非通用的人物讲解脚本时使用。
2026-05-11
messages-ops
205.5k
affaan-m/ECC
面向ECC的以证据为先的实时消息工作流。当用户想要阅读短信或私信、恢复最近的一次性验证码、在回复前检查对话线程，或证明实际检查了哪个消息来源时使用。
2026-05-11
perl-security
205.5k
affaan-m/ECC
全面的Perl安全指南，涵盖污染模式、输入验证、安全进程执行、DBI参数化查询、Web安全（XSS/SQLi/CSRF）以及perlcritic安全策略。
2026-03-13
prompt-optimizer
205.5k
affaan-m/ECC
分析原始提示，识别意图和差距，匹配ECC组件（技能/命令/代理/钩子），并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机：当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发：“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机：当用户希望直接执行任务，或说“直接做”时。不触发时机：当用户说“优化代码”、“优化性能”、“optimize performance”、“optimize this code”时——这些是重构/性能优化任务，而非提示优化。
2026-05-12
repo-scan
205.5k
affaan-m/ECC
跨栈源代码资产审计——对每个文件进行分类，检测嵌入的第三方库，并为每个模块提供可操作的四级判定结果，附带交互式HTML报告。
2026-05-11
research-ops
205.5k
affaan-m/ECC
以证据为先的ECC当前状态研究工作流程。当用户希望基于当前公开证据和提供的本地上下文获取最新事实、比较、丰富信息或建议时使用。
2026-05-11
seo
205.5k
affaan-m/ECC
审计、规划并实施SEO改进，涵盖技术SEO、页面优化、结构化数据、核心网页指标和内容策略。当用户希望提升搜索可见性、进行SEO修复、使用架构标记、处理站点地图/robots文件或进行关键词映射时使用。
2026-05-11
skill-comply
205.5k
affaan-m/ECC
可视化技能、规则和代理定义是否被实际遵循——自动生成3种提示严格级别的场景，运行代理，分类行为序列，并报告完整工具调用时间线的合规率
2026-05-11
skill-stocktake
205.5k
affaan-m/ECC
用于审计Claude技能和命令的质量。支持快速扫描（仅变更技能）和全面盘点模式，采用顺序子代理批量评估。
2026-05-11
social-graph-ranker
205.5k
affaan-m/ECC
加权社交图谱排名，用于在X和LinkedIn上发现温暖介绍、桥梁评分和网络差距分析。当用户想要可重用的图谱排名引擎本身，而不是其上层更广泛的推广或网络维护工作流时使用。
2026-05-11
workspace-surface-audit
205.5k
affaan-m/ECC
审计活跃仓库、MCP服务器、插件、连接器、环境表面和工具设置，然后推荐最高价值的ECC原生技能、钩子、代理和操作员工作流。当用户希望帮助设置Claude Code或了解其环境中实际可用的功能时使用。
2026-05-11
agent-architecture-audit
205.5k
affaan-m/ECC
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
2026-05-12
