“improve”的搜索结果

Audit, improve, and compress every skill in the repo using live research. Load when the user asks to improve skills, audit the skill library, upgrade existing skills, refresh with new research, do a skill health check, or says "improve all skills", "update the skill library", "skill audit", or "run an improvement pass". Applies live domain research, fixes structural gaps, checks for skill linking opportunities, then rewrites and resizes each skill. Supports TARGETED mode (`TARGET=<skill> [SKIP_RESEARCH=true]`) for single-skill fixes, including learn-from-chat restructure escalations. All skills are in scope including meta skills.

中文简介正在准备中。当前显示原文说明。

将智能体工作中实际遇到、也会影响其他任务的障碍整理为具体改进建议，记录到Paperclip，在不中断主要任务的情况下共享。

• 报告工具行为不一致
• 反馈缺少说明或上下文
• 改进反复出现的审批步骤

根据读者和页面目的，审核、改进或新写Storybook的/docs文档。既可调整结构和示例、统一格式，也可讨论页面定位与文档规划。

• 改进说明页面的结构和示例
• 起草新功能文档
• 讨论页面类型和目录

将重复使用的工作流程整理为技能，通过测试请求和反馈持续改进。支持创建或修改技能，对比启用前后的结果，并调整说明，使其在合适的请求中被调用。

• 将常规工作流程整理为技能
• 根据反馈改进现有技能
• 对比启用技能前后的输出

Compare ruflo and HAL systems for running the GAIA benchmark, an AI evaluation. Examine differences in code execution, browsing, file handling, memory, and model selection to prioritize improvements by expected impact and effort.

中文简介正在准备中。当前显示英语简介。

• Plan the next round of GAIA improvements
• Compare code execution and browser capabilities
• Weigh improvement priorities against implementation effort

Create reusable agent skills or improve existing ones through test prompts and user feedback. Compare output quality, execution time, and token usage against a baseline, then refine instructions and descriptions so the skill is invoked in appropriate situations.

中文简介正在准备中。当前显示英语简介。

• Turn a recurring workflow into a reusable skill
• Improve an existing skill using test results
• Compare quality, runtime, and token usage across versions

Improve existing code structure while preserving its behavior, using Martin Fowler's refactoring approach. Assess tests, identify structural problems, agree on a phased plan, and make small, tested changes with reversible commits and before-and-after comparisons.

中文简介正在准备中。当前显示英语简介。

• Splitting long functions into clearer responsibilities
• Removing duplicate or unused code
• Planning gradual improvements to legacy code

Review AI prompts for harmful output risks, bias, privacy concerns, security weaknesses, and clarity. Receive an assessment, a revised prompt, and suggested tests with explanations of the principles behind each improvement.

中文简介正在准备中。当前显示英语简介。

• Review a prompt before putting it into use
• Check wording for stereotypes and bias
• Assess data exposure and prompt injection risks

Improve code through repeated experiments against a measurable target, such as execution time or memory use. After defining scope and constraints, the agent tests changes, keeps improvements, reverts unsuccessful attempts, and logs results.

中文简介正在准备中。当前显示英语简介。

• Reduce execution time through measured code experiments
• Optimize memory use or bundle size
• Compare changes using benchmark results

Run repeated change-and-evaluation cycles for one predefined improvement mission within an explicit runtime limit. Save each evaluation as JSON and each decision in readable Markdown logs, with support for periodic reruns through Claude Code native cron.

中文简介正在准备中。当前显示英语简介。

• Repeating improvements under a fixed evaluation method
• Keeping evaluation results and decision logs
• Running experiments within a time limit

Guide a structured review after a security incident, using timelines and response data to identify root causes and process gaps. Produce review notes, response metrics, and practical improvements with named owners and deadlines.

中文简介正在准备中。当前显示英语简介。

• Reviewing response after a ransomware incident
• Turning exercise findings into process improvements
• Updating incident response playbooks

Improve an existing skill by checking its structure and category requirements, proposing focused fixes, and testing again. Compare failure and warning counts to decide whether to keep changes or restore the previous content.

中文简介正在准备中。当前显示英语简介。

• Fix missing fields and instructions in a skill
• Address findings from category checks
• Compare check results before and after edits

Improve code, prompts, skills, or agent definitions through repeated changes and evaluation. Measure numerical targets such as latency or size, or use an LLM to judge pass-or-fail criteria, keeping changes that improve the result.

中文简介正在准备中。当前显示英语简介。

• Improving page load performance
• Reducing build output size
• Refining prompts against evaluation criteria

Build repeatable DeepEval tests for AI agents, chatbots, and applications that retrieve documents to answer questions. Reuse or generate evaluation datasets, inspect failures, and improve prompts, tools, or retrieval through repeated evaluation runs.

中文简介正在准备中。当前显示英语简介。

• Add repeatable quality tests for an AI agent
• Evaluate chatbot behavior across multiple conversation turns
• Generate evaluation datasets from documentation

Review past dsh agent sessions to identify recurring tasks and test proposed skill or memory improvements. This skill guides preview runs, validation on reserved tasks, staged proposals, adoption with backups, and scheduled nightly cycles.

中文简介正在准备中。当前显示英语简介。

• Extract recurring tasks from past agent sessions
• Test proposed skill and memory improvements
• Review staged changes before adopting them

Audit existing SKILL.md files for clear activation conditions, usable instructions, and defined outputs. Get prioritized findings and specific improvements, with changes applied only when requested and the author's intent preserved.

中文简介正在准备中。当前显示英语简介。

• Audit existing skills for quality issues
• Clarify when a skill should activate
• Move lengthy examples into supporting files

Run repeated Ouroboros execution and improvement cycles as a background job, starting from a Seed specification or continuing an existing lineage. The loop stops on a quality check pass, convergence, cancellation, or the generation limit, and reports the outcome.

中文简介正在准备中。当前显示英语简介。

• Starting repeated improvement from a Seed specification
• Continuing an existing improvement lineage
• Following meaningful background progress

Audit a React codebase using React Doctor scan results and code inspection. It ranks issues by impact and effort, then writes detailed implementation plans that another agent can execute, while leaving source code unchanged during the audit.

中文简介正在准备中。当前显示英语简介。

• Create a prioritized React improvement roadmap
• Audit performance across an application
• Review accessibility and security issues

Review recent issues, pull requests, and recurring operational problems to choose a concrete repository improvement. Check for duplicate work, implement a suitable change, or document a plan and follow-up when implementation is blocked.

中文简介正在准备中。当前显示英语简介。

• Find recurring problems in contributor workflows
• Update outdated documentation and agent instructions
• Reduce repeated manual work in operations

Write Google Ads headlines, descriptions, and responsive search ad components. Create alternative messages for A/B testing, which compares ad versions, and develop copy ideas aimed at improving the click-through rate of existing ads.

中文简介正在准备中。当前显示英语简介。

• Draft headlines and descriptions for a new ad group
• Create components for responsive search ads
• Compare different advertising messages with A/B tests

Guided journey from a shipped app that works but feels rough to a product that fits the job, flows without friction, reads clearly, and persuades honestly. Orchestrates nine skills phase by phase - jobs-to-be-done, ux-heuristics, design-everyday-things, refactoring-ui, microinteractions, made-to-stick, influence-psychology, high-perf-browser, steve-jobs-design-review - asking the user questions at every decision point and recording results in the project docs/ folder (CUSTOMER.md, DESIGN.md, POSITIONING.md, IMPROVE-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to fix a clunky product, cut UX friction, sharpen in-app copy, or says 'the app works but feels rough'. Not for code, tests, or hardening - use improve-code-quality (fresh prototype) or remove-technical-debt (aged); no app yet, create-app; needs growth loops, grow-app; marketing-site friction, improve-website; one leaking flow, conversion-optimization. For one framework in isolation, invoke that skill directly.

中文简介正在准备中。当前显示原文说明。

Agent Performance Optimization Workflow workflow skill. Use this skill when the user needs Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

中文简介正在准备中。当前显示原文说明。

Optimize existing blog posts and web content for GEO (Generative Engine Optimization) — AI search visibility on ChatGPT, Perplexity, Claude, and Google AI Overviews. Use whenever a user provides a blog URL or pastes existing content and asks to optimize it for AI search, rewrite for LLM visibility, improve GEO score, make content answer-first, add FAQ sections, restructure headings for AI retrieval, improve citation potential, or audit content for AI readiness. Also triggers on "GEO optimize this", "make this AI-search ready", "rewrite for Perplexity", "optimize for ChatGPT", "optimize for Google AI Overviews", "improve AI visibility", "reformat for AI search", "make this content citation-worthy", "content isn't showing up in AI search", "why isn't my blog cited by AI", "GEO audit", "answer-first rewrite", "restructure for AI", "make my blog AI-friendly", "improve LLM citability". Do NOT trigger for writing new content from scratch — use geo-content for that.

中文简介正在准备中。当前显示原文说明。

Skill Optimization: Auto Research. Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.

中文简介正在准备中。当前显示原文说明。