搜索「Agent Memory」的结果

io.github.ToolJet/ToolJet/manage-skills

在本仓库中添加、移动或修复代理技能——决定放在公开根目录还是私有 EE 子模块，并接好符号链接，使技能在 Claude Code、Cursor 与 Codex 中可从仓库根目录直接调用。当被要求添加、创建、移动、迁移或重命名技能，或技能未出现时使用。

io.github.Significant-Gravitas/AutoGPT/perf-compare

Shared measurement recipe for AutoGPT performance work. Compares a baseline and a candidate in Sentry (two releases, two environments such as preview pr-<n> deploys, or two time windows) per transaction: count, p50/p95/p99, failure rate, and a trace-clustered bootstrap verdict of faster / slower / no detectable change / not enough data, with exit codes agents can branch on. Works for span duration, web vitals (measurements.lcp) or any numeric span field. TRIGGER when an agent needs to show a change made the backend or frontend faster or slower, compare a preview against a control or dev, check a release after merge on dev or prod, or check for regressions.

io.github.affaan-m/ECC/gateguard

PreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit and NotebookEdit) attempt until the agent presents concrete facts (importers, data schemas, verbatim user instruction), then allows retry; A/B-tested at +2.25 quality points. Use when enabling or configuring the GateGuard hook, exempting paths via env vars, or handling first-touch denials.

io.github.manaflow-ai/cmux/cmux-cua

仅在用户明确提出要使用 Computer Use 时使用：通过内置引擎，从 cmux 智能体会话中驱动真实的 macOS 应用（无障碍树加截图，支持点击、输入、滚动、拖拽，并带可辨识的光标），或向用户说明其由用户授权的权限设置。阅读或发现本技能不构成同意。

io.github.debpalash/VoiceStudio/voicestudio

Generate local speech with saved or designed voices, transcribe audio, and automate dubbing or narration workflows through VoiceStudio's REST API or MCP server. Use when the user wants to work with VoiceStudio audio or connect it to an agent or automation.

io.github.affaan-m/ECC/token-card

Render a token-usage stat card from local Claude Code, Codex, Gemini CLI, and OpenCode session logs and commit it into the repository as a file. Use when someone wants a current usage figure in a README, or asks for a shareable card of their coding-agent activity.

io.github.affaan-m/ECC/hookify-rules

Create and configure hookify rules — markdown files with YAML frontmatter that match bash, file, prompt, or stop events by regex or conditions and show warn/block messages to the agent. Use when creating a hookify rule, writing hook rule syntax, configuring hookify, or adding pattern guardrails such as blocking dangerous commands, .env edits, or debug code.

io.github.anthropics/skills/claude-api

Claude API / Anthropic SDK 参考——模型 id、定价、参数、流式输出、工具调用、MCP、agent、缓存、token 计数、模型迁移。触发条件：提示中出现任何 Claude/Anthropic 相关名称（Claude、Anthropic、Fable、Opus、Sonnet、Haiku 等）；用户询问 LLM 相关问题（定价/选型/限额/缓存）时不要凭记忆回答；或任务属于 LLM 类且未指明供应商。仅当明确针对其他供应商（OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama）时跳过。

io.github.vercel/next.js/create-pr

为 Next.js 创建 Git 分支、commit、push 和 GitHub pull request。当用户要求建分支、提交当前改动、开 PR 或草稿 PR、发布 pull request，或从 gh pr create / PR 模板问题中恢复时使用。涵盖 .github/pull_request_template.md、--body 格式、codex/ 分支命名以及 Codex 应用的 git 指令。

io.github.mattpocock/skills/wizard

生成交互式 bash 向导，引导人类完成只有他们能做的步骤。适用于开通基础设施、配置凭据或 CI secret、操作陌生的第三方面板，或执行一次性迁移/切换。代理自己能完成的步骤不要调用本技能。

io.github.github/awesome-copilot/python-mcp-server-generator

生成包含工具、资源和规范配置的完整 Python MCP server 项目。

io.github.stas00/ml-engineering/ml-engineering

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/st

io.github.ruvnet/ruflo/workflow-create

Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script (agent/parallel/pipeline fan-out)

io.github.mem0ai/mem0/mem0-integrate

以目标驱动、TDD 的流程将 Mem0 集成到现有仓库。自动检测仓库语言,并让用户在 Mem0 Platform(托管)与 Mem0 开源(自托管)之间选择。先写失败测试再做实现。产出本地功能分支和供配套验证技能使用的 .mem0-integration/ 产物。触发条件:用户说 "integrate mem0"、"add mem0 to this repo"、"wire mem0 into <repo>",或询问如何在现有项目中加入记忆。不触发:一般 SDK 使用(用 skill:mem0)、CLI 使用(用 mem0-cli)、Vercel AI SDK(用 skill:mem0-vercel-ai-sdk)。成功后调用 skill:mem0-test-integration 在同一工作区验证(松耦合)。

io.github.mem0ai/mem0/mem0-cli

Mem0 CLI——mem0 记忆操作的命令行界面。触发条件:用户提到 "mem0 cli"、"mem0 command line"、"@mem0/cli"、"mem0-cli"、"pip install mem0-cli"、"npm install -g @mem0/cli",或在终端/shell 中运行 mem0 命令(mem0 add、mem0 search、mem0 list、mem0 get、mem0 init、mem0 config、mem0 import)。查询包含 --user-id、--output、--json、--agent 等 CLI 参数,或描述 bash/zsh/终端使用时也触发。不触发:Python/TS 代码中的 SDK 集成(用 mem0 技能),或 Vercel AI SDK provider(用 mem0-vercel-ai-sdk)。

io.github.mem0ai/mem0/mem0-vercel-ai-sdk

Mem0 为 Vercel AI SDK 提供的 provider(@mem0/vercel-ai-provider)。触发条件:用户提到 "vercel ai sdk"、"@mem0/vercel-ai-provider"、"createMem0"、"retrieveMemories"、"addMemories"、"getMemories"、"searchMemories"、"mem0 vercel"、"AI SDK provider"、"AI SDK memory",或在 generateText/streamText 中使用 mem0。也适用于需要记忆增强 AI 的 Next.js 应用。不触发:不经 Vercel 的直接 Python/TS SDK 调用(用 mem0 技能),或 CLI 终端命令(用 mem0-cli 技能)。

io.github.mattpocock/skills/wayfinder

把超出单次代理会话容量的大块工作，规划成 issue 跟踪器上共享的决策工单地图，逐条解决，直到通往目标的路径清晰。

io.github.garrytan/gbrain/postgres-adopt

Detect which gbrain engine is in use (PGLite vs Postgres), prefer Postgres for agent-harness installs, install/provision Postgres (Supabase discovery via SUPABASE_ACCESS_TOKEN, local Postgres, opt-in Docker), and move an existing PGLite brain to Postgres with its history (plan, ask, run). Detection is one engine-free command; the install ladder is one flag.

io.github.garrytan/gbrain/postgres-adopt

检测当前 gbrain 使用的是哪种引擎（PGLite 还是 Postgres），在智能体安装场景中优先选择 Postgres，并安装或开通 Postgres（通过 SUPABASE_ACCESS_TOKEN 发现 Supabase、本地 Postgres、需显式选择的 Docker），再用受保护的引擎迁移把已有的 PGLite brain 搬移过去。检测只需一条与引擎无关的命令，安装阶梯也只需一个参数。

io.github.mattpocock/skills/claude-handoff

把当前对话移交给一个全新的后台代理，让它立即接手工作。

io.github.mattpocock/skills/handoff

把当前对话压缩成交接文档，供另一个代理接手。

io.github.topoteretes/cognee/company-brain-company-qa

Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use when someone wants to connect their company's database, tickets and docs, or asks who owns, decided or is handling something across them. Runs locally; reads the sources, writes only to cognee's memory.

io.github.nrwl/nx/setup-review-sandbox

一次性安装 reproduce-issue 技能与 reproduce-verifier 智能体所需的沙箱前置条件——Docker、隔离运行时（Linux 上用 gVisor，macOS 上用 Colima）、健康的容器网络，以及 nx-review-sandbox 工具链镜像（依据仓库的 mise.toml 构建）。操作幂等，可随时重跑以校验或修复。当用户说搭建审查沙箱、安装沙箱前置条件、构建沙箱镜像，或 reproduce-issue 的预检报告某项缺失时使用。

io.github.vercel/next.js/next-dev-loop

验证编辑应用代码后的 Next.js 运行时行为。用于确认改动在真正运行的应用中可用——而不仅仅是能编译或通过类型检查。将 /_next/mcp（Next.js 的视角）与 agent-browser（浏览器的视角）结合使用。需要正在运行的 next dev。