搜索

搜索结果

6035 results for "skill"

skill-creator

skill-creator

386Kagent-workflows

Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.

openclaw avataropenclaw
获取
skill-creator

skill-creator

385Kagent-workflows

创建、编辑、审计、整理、校验或重构 AgentSkills 与 SKILL.md 文件。

steipete avatarsteipete
获取
skill-stocktake

skill-stocktake

240Kagent-workflows

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

affaan-m avataraffaan-m
获取
skill-scout

skill-scout

240Kwriting-content

Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.

affaan-m avataraffaan-m
获取
skill-comply

skill-comply

239Kagent-workflows

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

affaan-m avataraffaan-m
获取
skill-scout

skill-scout

238Kwriting-content

在创建新 Skill 之前,先检索本地、插件市场、GitHub 以及网络上的现有 Skill 资源。当用户想要针对某个工作流新建、构建、Fork 或查找 Skill 时使用。

affaan-m avataraffaan-m
获取
skill-stocktake

skill-stocktake

237Kagent-workflows

用于对 Claude Skill 和 Command 进行质量审计。支持 Quick Scan 快速扫描(仅针对变动的 Skill)和 Full Stocktake 全面盘点模式,并采用子 Agent 顺序分批评估机制。

affaan-m avataraffaan-m
获取
writing-skills

writing-skills

233Kresearch-knowledge

当需要创建新技能、编辑现有技能或在部署前验证技能是否正常工作时使用

obra avatarobra
获取
skill-comply

skill-comply

231Kagent-workflows

可视化技能、规则和代理定义是否被实际遵循——自动在3种提示严格级别下生成场景,运行代理,对行为序列进行分类,并报告带有完整工具调用时间线的合规率

affaan-m avataraffaan-m
获取
karpathy-guidelines

karpathy-guidelines

192Kcode-generation

减少常见大语言模型编码错误的行为指南。在编写、审查或重构代码时使用,以避免过度复杂化、进行精准修改、明确假设并定义可验证的成功标准。

multica-ai avatarmultica-ai
获取
git-guardrails-claude-code

git-guardrails-claude-code

189Kwriting-content

设置 Claude Code 钩子,在执行前阻止危险的 git 命令(push、reset --hard、clean、branch -D 等)。当用户希望防止破坏性 git 操作、添加 git 安全钩子或在 Claude Code 中阻止 git push/reset 时使用。

mattpocock avatarmattpocock
获取
karpathy-guidelines

karpathy-guidelines

185Kcode-generation

减少常见LLM编码错误的行为指南。在编写、审查或重构代码时使用,以避免过度复杂化、进行精准修改、明确假设并定义可验证的成功标准。

forrestchang avatarforrestchang
获取
academy-guide

academy-guide

172Kresearch-knowledge

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

anthropics avataranthropics
获取
discernment-nudge

discernment-nudge

172Kresearch-knowledge

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

anthropics avataranthropics
获取
doc-coauthoring

doc-coauthoring

153Kresearch-knowledge

引导用户通过结构化工作流程共同撰写文档。当用户想要编写文档、提案、技术规范、决策文档或类似结构化内容时使用。此工作流程帮助用户高效传递上下文、通过迭代完善内容,并验证文档对读者有效。当用户提到编写文档、创建提案、起草规范或类似文档任务时触发。

anthropics avataranthropics
获取
algorithmic-art

algorithmic-art

153Kdesign-ui

使用 p5.js 创建算法艺术,支持种子随机性和交互式参数探索。当用户请求使用代码创作艺术、生成艺术、算法艺术、流场或粒子系统时使用。创作原创算法艺术,而非复制现有艺术家的作品,以避免版权侵权。

anthropics avataranthropics
获取
brand-guidelines

brand-guidelines

153Kdesign-ui

将Anthropic官方品牌颜色和排版应用于任何可能受益于Anthropic外观和感觉的工件。当需要品牌颜色或样式指南、视觉格式化或公司设计标准时使用。

anthropics avataranthropics
获取
theme-factory

theme-factory

153Kdesign-ui

用于为制品(如幻灯片、文档、报告、HTML落地页等)应用主题样式的工具包。内置10套预设主题(含配色与字体),可直接应用于已有制品,也可即时生成新主题。

anthropics avataranthropics
获取
internal-comms

internal-comms

153Kwriting-content

一组资源,帮助我按照公司喜欢的格式撰写各类内部沟通内容。当需要撰写任何内部沟通(如状态报告、领导层更新、3P更新、公司通讯、常见问题解答、事件报告、项目更新等)时,Claude应使用此技能。

anthropics avataranthropics
获取
slack-gif-creator

slack-gif-creator

153Kdesign-ui

用于创建针对 Slack 优化的动画 GIF 的知识和工具。提供约束条件、验证工具和动画概念。当用户请求为 Slack 创建动画 GIF 时使用,例如“给我做一个 X 做 Y 的 Slack GIF”。

anthropics avataranthropics
获取
claude-api

claude-api

153Kresearch-knowledge

Claude API / Anthropic SDK 权威参考手册 —— 涵盖模型 ID、计费价格、参数设置、流式传输、工具调用 (tool use)、MCP、Agent 开发、缓存机制 (caching)、Token 统计以及模型迁移。 触发条件 —— 在打开目标文件之前先阅读本文件;切勿因其“看似只有一行”而跳过 —— 当满足以下任意情况时触发:提示词中包含任何形式的 Claude/Anthropic 名称(如 Claude、Anthropic、Fable、Opus、Sonnet、Haiku、`anthropic`、`@anthropic-ai`、`claude-*`、`us.anthropic.*`、`[1m]`);用户咨询大模型相关问题(如价格、模型选择、额度限制、缓存)—— 严禁仅凭记忆回答;或者任务属于大模型范畴且未明确供应商(如 agent/MCP/工具定义/多 Agent 协同/RAG/LLM 评估/Computer Use;基于自然语言生成/总结/提取/分类/改写/对话;排查拒答、截断、流式传输、工具调用、Token 问题)。 跳过条件 —— 仅当明确使用其他供应商时跳过(优先级高于所有触发条件):用户提问中提到了 OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama;或者对项目执行 `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` 找到了匹配项(如果用户未指定供应商,请先执行该 grep 命令 —— 切勿直接读取文件)。

anthropics avataranthropics
获取
webapp-testing

webapp-testing

153Ktesting-qa

用于使用 Playwright 与本地 Web 应用交互和测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图以及查看浏览器日志。

anthropics avataranthropics
获取
mcp-builder

mcp-builder

153Kresearch-knowledge

用于创建高质量 MCP(模型上下文协议)服务器的指南,使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用,无论是使用 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。

anthropics avataranthropics
获取
canvas-design

canvas-design

153Kdesign-ui

使用设计理念在 .png 和 .pdf 文档中创建精美的视觉艺术。当用户要求创建海报、艺术品、设计或其他静态作品时,应使用此技能。创作原创视觉设计,切勿抄袭现有艺术家的作品以避免版权侵权。

anthropics avataranthropics
获取