44 个（bojieli 的仓库） · 按人气排序
Design and troubleshoot agent workflows that stop too early or keep repeating. The skill explains how to separate creation from review, verify real results, give actionable repair instructions, and set clear completion criteria and resource limits.
中文简介正在准备中。当前显示英语简介。
Perform mathematical calculations and descriptive statistics, summaries of a dataset, using information already supplied with sources. Report expressions, units, and assumptions so results can be checked, and identify missing data rather than guessing.
中文简介正在准备中。当前显示英语简介。
Design how an AI agent trims long conversations and large tool outputs while retaining decisions, constraints, failed approaches, and sources. Compare summarization strategies, choose compression triggers, and consider separate subagents to keep intermediate information out of the main conversation.
中文简介正在准备中。当前显示英语简介。
Organize the instructions, conversation history, and tool information an agent receives. Use the skill to clarify business rules, structure SKILL.md files for loading when needed, and distinguish external source material from instructions to reduce prompt injection risks.
中文简介正在准备中。当前显示英语简介。
Turn verified facts and calculation results from the shared conversation into a finished draft. Follow the requested language, audience, structure, and length while retaining necessary sources and qualifications without inventing citations or numbers.
中文简介正在准备中。当前显示英语简介。
Design agents that operate desktop or browser software through screenshots, mouse actions, and keyboard input. Compare ways to locate interface elements, diagnose coordinate errors, handle changing screens, and evaluate task completion, operating speed, and safety boundaries.
中文简介正在准备中。当前显示英语简介。
Design and improve retrieval for RAG, which supplies external knowledge to AI answers. Cover document splitting, semantic and keyword search, combined result ranking, and quality measurements to identify where relevant information is being missed.
中文简介正在准备中。当前显示英语简介。
Design evaluation tasks that check whether agents actually complete work. Define requests, simulated user behavior, starting conditions, and verifiable success criteria, then plan difficulty levels, training-data leakage checks, and ongoing maintenance.
中文简介正在准备中。当前显示英语简介。
Design knowledge systems that preserve document structure and connections across sources. Choose retrieval methods, organize conversation memory, and plan evidence-based updates, review workflows, and access controls for information that scattered text searches cannot adequately cover.
中文简介正在准备中。当前显示英语简介。
Turn agent failure records into training examples by locating the first incorrect decision and pairing preferred actions with rejected ones. Assess whether training is appropriate, then check both targeted improvements and preservation of correct behavior.
中文简介正在准备中。当前显示英语简介。
Break complex requests into research, calculation, coding, and writing stages. Clarify goals, dependencies, and completion criteria, then coordinate the next specialist skill while keeping the conversation history available across transitions.
中文简介正在准备中。当前显示英语简介。
Design recovery paths for AI agents that loop, lose streamed responses, or hit service limits. Classify failures, choose retries or backup models, and set stopping rules to keep recovery attempts from causing further failures.
中文简介正在准备中。当前显示英语简介。
Build an evaluation process for AI agents using success, reliability, cost, and latency measures. Define scoring criteria, repeatable environments, failure analysis, and regression tests that check for recurring problems to support model selection and system improvements.
中文简介正在准备中。当前显示英语简介。
Design rewards for reinforcement learning, where feedback guides model behavior. Choose how to score outcomes and intermediate actions, check for scoring loopholes, and use independent tests to detect incomplete work presented as finished.
中文简介正在准备中。当前显示英语简介。
Design and evaluate how an AI agent remembers user preferences and history across conversations. Compare storage formats and memory frameworks, plan updates and compression, and distinguish personal memory from shared document retrieval while addressing sensitive information.
中文简介正在准备中。当前显示英语简介。
Design the operating layer around a coding agent so it can read and edit code, run checks, and correct errors. Define completion criteria, permission boundaries, feedback, and recovery methods, and assess which tasks suit autonomous execution.
中文简介正在准备中。当前显示英语简介。
Plan how to add external capabilities to an AI agent using MCP, a connection protocol, or Skill Hub distribution. Compare integration methods, design tools and data access, and review context costs, credentials, and third-party security risks.
中文简介正在准备中。当前显示英语简介。
Review and rewrite Chinese product announcements, articles, emails, and README text using eleven style checks. Identify repetitive phrasing, overloaded sentences, vague openings, and decorative language, then revise them into clearer statements suited to each type of writing.
中文简介正在准备中。当前显示英语简介。
Design a running status summary that keeps an agent aware of tasks, tool call counts, time, errors, and its environment. The skill covers updating that summary and balancing cache reuse against the buildup of outdated information.
中文简介正在准备中。当前显示英语简介。
Plan and review systems where several AI agents work together. Assess whether multiple agents are useful, choose roles and communication methods, and define shared files, verification, and resource limits to address conflicts, spreading errors, and uncontrolled execution.
中文简介正在准备中。当前显示英语简介。
Turn papers, articles, or outlines into an 8–12 slide PowerPoint presentation. The skill organizes background, methods, findings, and conclusions, extracts concise bullet points, and generates a .pptx file using its bundled script.
中文简介正在准备中。当前显示英语简介。
Design how an AI agent finds and loads tools as needed. Compare discovery approaches, organize large tool collections, and assess tool selection accuracy, token costs, and cache reuse without placing every tool definition in the initial context.
中文简介正在准备中。当前显示英语简介。
Write small, reproducible Python scripts and run them in a sandbox using execute_python. Check the script's logic and output, then report the actual results or errors while clearly distinguishing executed results from code that has not been run.
中文简介正在准备中。当前显示英语简介。
Plan further training for AI agent models by diagnosing gaps in knowledge, output consistency, or decision making. Compare continued pretraining, supervised fine-tuning, reinforcement learning, and distillation, then design training data, feedback environments, and evaluation checks.
中文简介正在准备中。当前显示英语简介。