663 个 · 按相关度排序
Guide Pi agents through repeated failures or unverified completion using competing hypotheses, small verifiable actions, and relevant checks. It separates self-review from external pass-or-fail decisions and requires evidence and remaining risks in delivery reports.
中文简介正在准备中。当前显示英语简介。
Test an idea, strategy, or investment against 11 future time horizons, from six months to 50 years. Compare scenarios with probability ranges, identify structural risks, and review or update the underlying world models.
中文简介正在准备中。当前显示英语简介。
Map sensitive data across the systems you manage, explore what a compromised asset could expose, and maintain a risk register. Record likelihood, impact, owners, mitigations, and review dates to support ongoing security planning.
中文简介正在准备中。当前显示英语简介。
Build, run, and troubleshoot Docker containers, which package applications and their dependencies. Improve Dockerfiles and Compose configurations to create smaller images, manage persistent data, and address startup, networking, and resource issues.
中文简介正在准备中。当前显示英语简介。
Diagnose why an AI agent becomes less reliable as conversations and documents accumulate. Distinguish missed information, persistent false claims, irrelevant material, mixed tasks, and conflicting sources, then choose ways to clean, reorganize, or separate the context.
中文简介正在准备中。当前显示英语简介。
Set up a new Obsidian vault, a folder for linked notes, or adopt an existing one. Select the working vault and route requests to the appropriate skills for importing sources, answering questions, saving results, or maintenance.
中文简介正在准备中。当前显示英语简介。
Carry out website tasks in a remote browser, including expense submissions, authorized orders, and retrieving data behind a login. Personal browser profiles preserve sign-ins, while users handle login and verification screens themselves.
中文简介正在准备中。当前显示英语简介。
Draws points, lines, arrows, boxes, and text over a running CARLA world to visually check positions, paths, and objects. Sets colors and display lifetimes for temporary debugging overlays, without creating persistent actors or output files.
中文简介正在准备中。当前显示英语简介。
Build AI agents by connecting workflow blocks in AutoGPT's visual editor. This skill covers multi-step automation, scheduled runs, webhooks that start work after external events, execution monitoring, and custom agent development.
中文简介正在准备中。当前显示英语简介。
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
中文简介正在准备中。当前显示英语简介。
Automate website navigation, form filling, data extraction, and web app checks while keeping page state between scripts. Use a new Chromium session or connect to an existing Chrome session through an extension.
中文简介正在准备中。当前显示英语简介。
Use persistent virtual terminal sessions to keep directories and environment variables across commands, interact with Python or database consoles, and answer prompts. The skill explains sending input, reading responses, detecting prompts, and closing sessions when finished.
中文简介正在准备中。当前显示英语简介。
Investigate bugs through symptom gathering and hypothesis testing, with saved investigation state across context resets. Resume earlier sessions, check their status, or request a root cause report without applying a fix.
中文简介正在准备中。当前显示英语简介。
Build and maintain a Markdown knowledge base from source materials, with linked pages and traceable evidence. Use accumulated knowledge to answer questions, preserve reusable research, and check for conflicting claims, outdated information, broken links, or missing index entries.
中文简介正在准备中。当前显示英语简介。
Turn law study outlines, notes, or textbook excerpts into flashcards, then practice one question at a time in chat. Self-assessment updates learning stages and review dates, while subject-level statistics highlight concepts that need more work.
中文简介正在准备中。当前显示英语简介。
Plan international hiring by comparing an employer of record, a provider that employs staff locally, with a local entity. Prepare stakeholder questions, draft local counsel briefing requests, and track unresolved tasks across sessions.
中文简介正在准备中。当前显示英语简介。
Start planning hiring in a new country by gathering requirements, comparing an employer of record with a local entity, identifying questions for different teams and country-specific concerns, and creating a tracker for ongoing follow-up.
中文简介正在准备中。当前显示英语简介。
Add an AI agent backend to a Convex app with persistent conversations, streamed messages, and tool calls. It also supports document retrieval for grounded answers, using Convex AI Gateway for model calls where available.
中文简介正在准备中。当前显示英语简介。
Guide an AI agent through ClawWork, an economic survival simulation where task rewards must cover API token costs. Defines a daily choice between work and learning, artifact submission, knowledge storage, and priorities based on the remaining balance.
中文简介正在准备中。当前显示英语简介。
Execute an implementation plan by assigning each independent task to a fresh helper agent in sequence. Review specification compliance and code quality after each task, track decisions in files, and finish with a review of the entire branch.
中文简介正在准备中。当前显示英语简介。
Hand off OpenRig work through persistent queue items that record the next owner, blockers, and closure reasons. The skill covers notifying recipients, escalating to a human, and keeping supporting evidence accessible across interruptions and missed messages.
中文简介正在准备中。当前显示英语简介。
Review how an AI agent loads, retains, summarizes, and shares working information. This historical guide helps examine forgotten constraints, repeated actions, tool selection, and handoffs using context engineering practices published in 2024–2025.
中文简介正在准备中。当前显示英语简介。
Ask questions about documents in Google NotebookLM from Claude Code and receive source-grounded answers with citations. Manage a local notebook library, find notebooks by topic, and combine follow-up answers into a response.
中文简介正在准备中。当前显示英语简介。
Decide when repeated search failures justify continuing document creation with existing knowledge. Track errors, distinguish retryable problems, and record verification limits, while excluding tasks that require current information or explicit external verification.
中文简介正在准备中。当前显示英语简介。