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。
- Building an initial agent evaluation process
- Comparing models on actual work tasks
- Investigating a drop in evaluation scores
bojieli/ai-agent-book☆ 5.5万2026年10月9日 更新
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 The skill covers updating that summary and balancing cache reuse against the buildup of outdated information.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。
- Addressing repeated tool calls and retry loops
- Keeping TODO progress and original goals visible
- Choosing how to update runtime status messages
bojieli/ai-agent-book☆ 5.5万2026年10月9日 更新
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。
- Revising formulaic Chinese product announcements
- Reviewing repetitive phrasing in Chinese articles
- Shortening overloaded sentences in Chinese emails
bojieli/ai-agent-book☆ 5.5万2026年10月9日 更新
Design agents that respond to incoming emails, external notifications, and timers. Plan how they handle interruptions, prioritize new requests, track concurrent tasks, and deliver results while longer operations continue in the background.
中文简介正在准备中。当前显示英语简介。
- Connecting agents to incoming emails and external notifications
- Scheduling reports and recurring checks
- Handling interruptions and changes during long tasks
bojieli/ai-agent-book☆ 5.5万2026年10月9日 更新
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。
- Diagnosing the first incorrect decision in an agent failure
- Building preference pairs from failure records
- Choosing between system fixes and model training
bojieli/ai-agent-book☆ 5.5万2026年10月9日 更新
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。
- Checking a Python script's logic
- Confirming actual output from a short script
- Reproducing an error with minimal code
bojieli/ai-agent-book☆ 5.5万2026年10月9日 更新