「AI 与智能体」分类共 1707 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。
LB623/no-negative-echo897Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs. Use after corrections or discarded proposals. Not for ordinary deletion, deprecation, migration, or exclusions materially required for safety, accuracy, compatibility, audit, quotation, or requested comparison.
instavm/coderunner893Image processing skill for cropping images to 50% from center and rotating them 90 degrees clockwise. This skill should be used when users request image cropping to center, image rotation, or both operations combined on image files.
alirezarezvani/claude-code-skill-factory880Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
alirezarezvani/claude-code-skill-factory880Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
alirezarezvani/claude-code-skill-factory880Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.
alirezarezvani/claude-code-skill-factory880Comprehensive Scrum Master assistant for sprint planning, backlog grooming, retrospectives, capacity planning, and daily standups with intelligent context-aware reporting
alirezarezvani/claude-code-skill-factory880Analyzes social media campaign performance across platforms with engagement metrics, ROI calculations, and audience insights for data-driven marketing decisions
laolaoshiren/claude-code-skills-zh879依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时；区分“生成测试”和“执行请求”的授权，不猜测状态码、响应结构或 SLA，不在未确认环境中发送写请求。
laolaoshiren/claude-code-skills-zh879数据库迁移助手 - Schema 对比、迁移脚本生成
laolaoshiren/claude-code-skills-zh879审计 Node.js、Python、Go、Rust、JVM、Ruby 项目的依赖漏洞、版本健康度与许可证事实；当用户要求检查 package.json、lockfile、requirements、go.mod、Cargo.toml、pom.xml、Gemfile.lock，或生成不改依赖的中文审计报告时使用
laolaoshiren/claude-code-skills-zh879项目目录结构地图 - 生成带说明的可视化目录树，快速理解任意代码库
laolaoshiren/claude-code-skills-zh879环境变量管理器：扫描、校验、同步 .env 文件，生成安全配置模板
laolaoshiren/claude-code-skills-zh879国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译
laolaoshiren/claude-code-skills-zh879日志分析助手 — 智能解析日志文件，识别异常模式，定位问题根因
laolaoshiren/claude-code-skills-zh879基于可复现基线和 profiler 证据分析性能问题。用于用户要求定位慢接口、慢任务、慢查询、内存或网络瓶颈，制定优化方案，或验证优化收益时；区分实测结论与静态推断，不虚构耗时和提升比例，生产环境操作需明确授权。
laolaoshiren/claude-code-skills-zh879中文代码审查专家 - 生成详细的中文代码审查报告
laolaoshiren/claude-code-skills-zh879中文文档生成器 - 从代码库自动生成中文技术文档
laolaoshiren/claude-code-skills-zh879中文 README 生成器 - 先分析项目，再生成面向中文开发者的高质量 README
komako-workshop/digital-oracle873Answer prediction questions using market trading data, not opinions. Use when the user asks probability questions about geopolitics, economics, markets, industries, or any topic where real money is being traded on the outcome. Examples: 'What's the probability of WW3?', 'Will there be a recession?', 'Is AI in a bubble?', 'When will the Russia-Ukraine war end?', 'Is it a good time to buy gold?', 'Will SPY drop 5% this month?', 'Is NVDA options premium overpriced?'. The skill reads prices from prediction markets, commodities, equities, options chains, derivatives, yield curves, and currencies, then cross-validates multiple signals to produce a structured probability report.
karanb192/itr-wala871File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27. Use when the user wants to file their ITR, compute or verify Indian income tax, compare the old vs new tax regime, read a Form 16, AIS, TIS or Form 26AS, reconcile TDS, handle capital gains from Zerodha/Groww/Upstox statements, check their tax refund, or asks about ITR-1/ITR-2/ITR-3/ITR-4, sections 80C/80D/87A/111A/112A, crypto tax, advance tax, or the income-tax e-filing portal - even if they just say "help me with my taxes" in an Indian context.
agentscope-ai/OpenJudge868Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.
agentscope-ai/OpenJudge868Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.
agentscope-ai/OpenJudge868Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
agentscope-ai/OpenJudge868Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use when the user mentions calibration, TPR/TNR, judge validation, inter-rater agreement, Cohen's kappa, bias detection, or "is my automatic evaluation trustworthy." Merges the calibrate and align functions into one skill.