Agent 工作流
可复用的 Agent 工作流和编排模式
Skills 列表

llm-security
Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.
semgrep
ralph-wiggum
Autonomous AI coding with spec-driven development. Implements Geoffrey Huntley's iterative bash loop methodology where agents work through specs one at a time, outputting a completion signal only when acceptance criteria are 100% met.
fstandhartinger
skill-doctor
Grades agent skills by scoring agent conversations against efficiency and code-quality rubrics, then drafts concrete skill edits and a shareable report. Use when the user wants their agent setup graded from real conversation history, or asks which of their installed skills are actually working.
warpdotdev
ultrathink
Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.
intellectronica
youtube-transcript
从YouTube视频中提取转录文本。当用户要求获取YouTube视频的转录、字幕或隐藏式字幕,并提供YouTube网址(youtube.com/watch?v=、youtu.be/等格式)时使用。支持带或不带时间戳的输出。
intellectronica
adversarial-review
Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".
poteto
day2-create-context-sync-skill
AI Native Camp Day 2 Context Sync 스킬 만들기. 여러 외부 도구에서 컨텍스트를 수집하여 하나의 sync 문서로 만드는 나만의 스킬을 직접 구축한다. "2일차", "Day 2", "context sync", "컨텍스트 싱크", "sync 스킬", "스킬 만들기", "정보 수집 스킬" 요청에 사용.
ai-native-camp
day2-supplement-mcp
Day 2 보충 자료 - MCP 딥다이브. Claude Code에 외부 도구를 연결하는 MCP를 체계적으로 배운다. "MCP 배우기", "MCP 보충", "MCP 강의", "MCP 학습" 요청에 사용.
ai-native-camp
day4-wrap-and-analyze
AI Native Camp Day 4 Wrap & Analyze. session-wrap 스킬을 직접 만들고, history-insight와 session-analyzer로 세션을 분석한다. "4일차", "Day 4", "wrap", "세션 분석", "session wrap", "세션 래핑" 요청에 사용.
ai-native-camp
day5-fetch-and-digest
AI Native Camp Day 5 콘텐츠 소화 스킬 만들기. fetch-tweet, fetch-youtube, content-digest 3개 스킬을 직접 만들고 활용한다. "5일차", "Day 5", "fetch", "콘텐츠 스킬", "트윗 스킬", "유튜브 스킬", "다이제스트 스킬" 요청에 사용.
ai-native-camp
day1-onboarding
AI Native Camp Day 1 온보딩. Claude와 대화하면서 Claude Code를 익힌다. "1일차", "Day 1", "온보딩" 요청에 사용.
ai-native-camp
baidu-drive
百度网盘(Baidu Drive)文件管理 — 上传、下载、转存、分享、搜索、移动、复制、重命名、创建文件夹。 同时支持 Agent 记忆备份/恢复(kimiclaw/maxclaw/qclaw/openclaw)。 TRIGGER: 用户提及"百度网盘/bdpan/网盘/云盘/baidu drive/Baidu Drive"并涉及文件操作; 或用户提及"备份记忆"、"恢复记忆"、"查看记忆备份"等记忆相关操作。 DO NOT TRIGGER: 非文件存储操作,或使用其他云盘服务时;本地记忆整理/清理操作;PPT 生成操作(已独立为 baidu-wenku-aippt skill)。
baidu-netdisk
assistant-mcp
Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the `mcp-grafana` Model Context Protocol server. Installs the server with `go install`, generates a Grafana service-account token, wires `~/.claude/settings.json` or `~/.cursor/mcp.json` with the `command` + `env` block, runs `--disable-write` for safer read-only sessions, switches to SSE transport for team-shared / VS Code setups, and verifies with `/mcp` + a `list_datasources` round-trip. Use when connecting Claude Code to Grafana, setting up MCP for Grafana, configuring the Grafana MCP server, using Grafana tools in Cursor/VS Code, querying Grafana from an AI agent, sharing the MCP server across a team — even when the user says "give my agent Grafana access", "let Claude see my metrics", or "Cursor + Grafana" without saying "MCP".
grafana
byted-mediakit-shared
MediaKit 是面向音视频与图像处理的专业工具集,覆盖视频剪辑与合成、音频处理、视频理解与增强、图像处理与内容理解等工作流。用户明确提出剪辑、拼接、裁剪、转场、滤镜、运镜、混音、提取字幕、语音转字幕、音视频处理、图片处理、视频分析或画质增强目标时,先加载本 Skill,再按对象和目标选择 audio、editing、image 或 video。不承担具体能力参数说明。
volcengine
cmake
用于C/C++项目的CMake构建系统技能。在编写或重构CMakeLists.txt、配置外部构建、选择生成器(Ninja、Make、VS)、使用target_link_libraries管理目标和依赖、通过find_package或FetchContent集成外部包、启用sanitizers、设置交叉编译工具链文件或导出CMake包时使用。在有关CMakeLists.txt、cmake配置错误、目标属性、安装规则、CPack或CMake预设的查询时激活。
mohitmishra786
linkedin-ghostwriting
B2B LinkedIn ghostwriting — strategic interview, hook engineering, and post body. Use when the user wants to write LinkedIn content, create ghostwritten posts, ghostwrite for a founder or executive, develop a B2B social strategy, or needs hooks, post structures, or copywriting frameworks for LinkedIn. Apply when the user shares a story, result, or insight and wants it turned into a post.
samber
conventional-git
Conventional Commits v1.0.0 branch naming, worktree naming, and commit message standards for GitHub and GitLab projects. Use when creating branches, naming worktrees, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent git history, SemVer-driven releases, parseable changelog generation, or automatic issue closing. Trigger when the user asks how to name a worktree, create a git worktree, or organize worktrees alongside branches.
samber
press-release-writer
Write professional press releases for any occasion, media type, and country. Use when the user wants to write, draft, or improve a press release, communiqué de presse, media announcement, news release, or PR statement — including product launches, funding rounds, partnerships, crisis communications, earnings, executive hires, events, M&A, open source milestones, and media advisories. Covers all release types, media targets (print, digital/wire, broadcast, social/SMPR, trade press), and region-specific conventions (Western/Eastern Europe, Americas, Middle East, Africa, Asia, Oceania). Also trigger when the user says 'I need to announce something' or 'how do I tell the press about X.'
samber
humaniseur-fr
Remove AI-writing patterns from French text and inject voice, personality, and soul. Use when editing, reviewing, rewriting, or cleaning up French content that reads like ChatGPT/Claude output. Humanize, humanise, déslopifier. Detects and fixes 27 patterns: AI vocabulary overuse (crucial, essentiel, notamment, par ailleurs, dans le paysage), anglicisms from English-first models (faire du sens, adresser un problème), copula avoidance, formulaic openings (À l'ère de, Dans le paysage actuel), superficial participle analyses (-ant), em dash overuse, redundant adjective doublets, rule of three, sycophantic tone, typographic tells (curly quotes instead of guillemets). Trigger on: humaniser, déslopifier, rendre plus humain, nettoyer le texte IA, enlever le slop, réécrire pour que ça sonne humain, make it sound human.
samber
promql-cli
CLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Grafana Mimir, Grafana Tempo...) — instant queries, range queries, metric discovery (metrics/labels/meta subcommands), output formats (table/csv/json/graph). Apply when executing PromQL queries, troubleshooting performance issues on a software having observability, investigating latency/error rates/saturation, or analyzing time series data.
samber
training-report
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a training session, workshop, or onboarding event with individual participant feedback and recommendations. Also trigger when the user says things like "I just ran a workshop and need to write it up", "help me summarize what happened in my training session", or "I need to report back to management about a session I ran". Always use this skill — for short or long sessions, across any discipline (technical, soft skills, creative, compliance, onboarding, etc.) — whenever a structured written deliverable about a training event is needed.
samber
getnote-auth
安装和连接得到大脑,完成浏览器授权、环境诊断、配额检查、CLI 升级与领域 Skill 同步。用户说“安装/连接/登录/更新得到大脑”“检查为什么不能用”“查看额度”时使用。
iswalle
getnote-tag
查看得到大脑笔记已有标签,为笔记添加标签,或按真实标签 ID 安全删除标签,并避免误删系统标签或覆盖其他标签。
iswalle
mongodb-natural-language-querying
使用自然语言生成只读的 MongoDB 查询(find)或聚合管道,并附带集合模式上下文和示例文档。当用户要求编写、创建或生成 MongoDB 查询,想要过滤/查询/聚合 MongoDB 中的数据,询问“如何查询...”,需要查询语法帮助,或讨论查找/过滤/分组 MongoDB 文档时,请使用此技能。也可用于将类似 SQL 的请求转换为 MongoDB 语法。不处理 Atlas Search($search 操作符)、向量/语义搜索($vectorSearch 操作符)、模糊匹配、自动补全索引或相关性评分——这些请使用 search-and-ai。不分析或优化现有查询——请使用 mongodb-query-optimizer。不处理涉及写入操作的聚合管道。需要 MongoDB MCP 服务器。
mongodb