GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
agentsight-code-review
对当前分支的变更执行 AgentSight 专属代码审查。覆盖 6 个维度:硬性规则合规、eBPF 安全、FFI 边界、Footprint Ladder、流水线测试覆盖、文档同步。输出编号的 findings 列表,每条包含文件路径和行号。
agentsight-bugfix
AgentSight fix issues 流程。了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复,五阶段标准化调试迭代循环。确保 AI agent 遵循最小改动、逐轮验证的修复规范。
agentsight-auto-format
编辑代码文件后自动运行对应格式化工具,保持代码风格一致。适用于任何 AI coding agent。
skill-ledger
Skill 安全状态查看、风险暴露审查、用户决策、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill;当用户要求 agent 安装 Skill 且安装成功后,必须自动对最终本地目录执行快速扫描认证。
security-observability
只读查询 agent-sec-cli 已落盘的历史安全事件记录,并据此生成会话级安全复盘。仅当用户显式要求查看或审计已发生的安全事件、安全告警、安全审计记录,或要求按 session/run/trace/时间/类别筛选与统计已有安全事件,或要求复盘某次会话的安全判定时使用。不用于扫描新内容:检查代码安全性用 code-scanner,检测 prompt 注入用 prompt-scanner,审查 Skill 安全状态用 skill-ledger。不要因为对话中出现“安全”“工具调用”等字样、或为了主动自查而触发。
prompt-scanner
使用 agent-sec-cli 扫描 prompt 文本中的注入攻击和越狱尝试,返回结构化 JSON 扫描结果。当用户提到 prompt 安全、prompt 注入检测、越狱检测、提示词攻击检测,或者需要判断一段文本是否包含恶意 prompt 注入时,都应使用此技能。即使用户没有明确说"扫描",只要涉及评估 prompt 文本的安全性,也应触发此技能。
policy-authoring
把自然语言授权意图(允许、禁止、只允许某个范围)写成 agent-sec-core Scope/Binding 部署路径使用的 SecCore Cedar policy,不生成 sandbox 请求授权策略。Agent 按随本 Skill 分发的 schema、语法参考、示例和自检清单逐步完成:先问清歧义,再写规则,再自检,最后回译确认,全程不需要命令行工具。当用户要求"让 Agent 可以读写某个目录""禁止删除某个文件""只允许某个程序执行""把这段授权需求写成策略"时使用。只负责生成和自检策略,不代为批准、绑定或下发;查询已发生的安全事件用 security-observability,检查代码或 prompt 用 code-scanner、prompt-scanner。
pii-checker
使用 agent-sec-cli 检查文本、UTF-8 文件或日志中的个人信息与凭证,报告脱敏证据,并按需生成脱敏文本。当用户要求检查敏感信息、查找泄露的密钥或对内容脱敏时使用;查询已发生的安全事件使用 security-observability。
code-scanner
扫描 Bash / Python 代码片段中的安全风险,返回结构化 JSON 扫描结果。当用户要求检查代码安全性时使用。
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
flutter-edge-ai-speech
Use when adding speech to a flutter_edge_ai app — speech-to-text (transcribe a voice note, dictation, Whisper, moonshine, Parakeet), text-to-speech (Matcha, Qwen3-TTS, Inflect), or a push-to-talk voice assistant with VoiceSession. Also use when transcripts come back in English for non-English audio, a WAV file has to become 16 kHz PCM, synthesized audio plays at the wrong pitch, or getActiveTts throws a StateError about the language. For audio sent straight to Gemma in a chat, use flutter-edge-ai-inference.
flutter-edge-ai-rag
Use when adding or debugging on-device RAG, semantic search, embeddings (EmbeddingGemma 2 .litertlm or .gguf through flutter_edge_ai_llama, EmbeddingGemma 1 or Gecko .tflite, ONNX models such as MiniLM), metadata filters, embedding profiles, image or audio document indexes, or pluggable sqlite-vec/qdrant-edge storage in a flutter_edge_ai app with flutter_edge_ai_rag, flutter_edge_ai_sqlite or flutter_edge_ai_qdrant. Also use when moving RAG code to flutter_edge_ai 2.0 or to flutter_edge_ai_rag 1.1 — FlutterEdgeAi.rag is undefined, initialize(vectorStore:) was removed, addText/searchText/activeEmbedderProfileId are undefined, or open() throws "No vector-store provider can handle providerId" or "is bound to" — and when QdrantLegacyStoreException or an embedding-profile mismatch is thrown.
flutter-edge-ai-onnx
Use when running ONNX models with flutter_edge_ai_onnx (ModelFileType.onnx) — ORT-GenAI text generation (e.g. Phi-3.5-mini) or ONNX embeddings — on macOS arm64, Linux x64, Windows x64 and ARM64, Android arm64, iOS arm64, or in the browser through Transformers.js. Also use when an ONNX install is routed to the wrong engine, genai_config.json is missing, or getActiveModel throws "No inference engine can handle this model" on another platform. For .litertlm models use flutter-edge-ai-inference; for .task, flutter-edge-ai-mediapipe.
flutter-edge-ai-inference
Use when adding on-device LLM inference with flutter_edge_ai — offline chat, local models, Hugging Face installs, streaming, system prompts, thinking, structured JSON output, ResponseFormat or a schema-constrained reply, image/audio prompts, CPU/GPU/NPU selection, stopping generation, or setting up the recommended .litertlm engine on Android, iOS, macOS, Windows, Linux or web. Also use when a reply is empty or deterministic, maxTokens does not shorten replies, FlutterEdgeAi is undefined, getActiveModel reports no engine, a session is closed, GPU numbers are wrong, or .litertlm fails on Android. For .task or .bin models, use flutter-edge-ai-mediapipe.
flutter-edge-ai-diagnostics
Use when measuring how much memory an on-device model costs with flutter_edge_ai_diagnostics — MemorySnapshot, anonymousBytes, anonymousPeakBytes, fileBackedBytes, availableBytes, GpuMemoryReading — on Android, iOS, macOS, Linux or Windows, when an app is killed for memory (iOS jetsam, Android lmkd) while loading or running a model, when choosing between model sizes for a device, or when RSS numbers do not add up. Also use when FlutterEdgeAiDiagnostics.memorySnapshot() throws MemoryReadException or UnsupportedError, or a snapshot field is null. For running the model itself, use flutter-edge-ai-inference.
release
Release flutter_edge_ai — bump versions, optionally re-publish native prebuilts (iOS/macOS/Linux/Windows/Android dylibs) to GitHub Release, update SHA256 checksums in hook/build.dart, publish to pub.dev
send-email
Send an email.
query-wikipedia
Query summary from Wikipedia for a given topic.