Skill rating

Quantum Circuit Builder with Proof: Use this product when a quantum circuit needs verifiable evidence, not just. Use when an agent needs quantum circuit builder with proof, formally verified quantum c

数学教师的测评设计：用双向细目表把"凭感觉出数学卷"变成可诊断的命题。仅在老师提出明确的数学命题任务时建议激活，例如"给八年级数学出一份单元测评""做一张数学双向细目表""算这次数学测评的逐题 P/D"；泛泛聊数学、问某题怎么解、问学生近况都不激活。只做四件事：命题蓝图与双向细目表、题目选编与版权标注、题目统计（逐题 P/D 与信度）、经老师逐条确认后的写回。不做：错因归类与个体诊断（转 xiao

Enhanced Tavily search with intelligent intent recognition, source preferences, critical source validation, and offline report generation.

Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions. Detects 63+ known bug patterns.

Video analysis: object detection, scene classification, activity recognition, and summarization.

Audit a Shopify Article, research content and E-E-A-T gaps, generate a reviewable HTML candidate, and produce one audit-plus-storefront-preview report before any approved update. Use when a merchant g

免费 AI 网站一键上线助手（内部标识：vibecoding-deployment-auditor）：适合国内用户与零基础小白，无需 Git、服务器、域名或复杂部署配置；面向 VibeCoding 生成的纯静态网站，适用于官方 Sites/ChatGPT Sites 上线不成功或不适用时，通过私有 ZIP 链路完成上线并验证公开 HTTPS 地址。支持 H5 小游戏、个人作品集、企业官网、活动落地

Spawn multiple perspectives to evaluate a problem before converging on a solution.

亚马逊市场关键词竞争度的SIF概览分析。当用户提到关键词竞争度、供需比、竞品数量、关键词搜索量估算、市场竞争力评估、关键词热度排名、广告竞争分析、某个关键词下的商品数量、keyword competition, supply-demand ratio, competitor count, search popularity, market competition analysis, SIF, ke

Implement the 5-file agent memory architecture for durable continuity across sessions. Covers SOUL.md (identity), IDENTITY.md, USER.md, AGENTS.md (operating manual), MEMORY.md (long-term memory), dail

MPSTATS Ozon 俄罗斯站按卖家 ID 下钻商品列表。返回该卖家下全部 SKU 的销量、销售额、价格、评分、库存、周转、损失销售额等完整指标，支持多维数值筛选、排序、货币换算。用于店铺结构分析、卖家爆款拆解、竞争对手店铺对标。当用户提到 Ozon 卖家商品、Ozon 店铺分析、Ozon 卖家下钻、Ozon 卖家 SKU、Ozon 店铺爆款、Ozon 竞争店铺、MPSTATS seller,

Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turns, failed approaches, and scope drift by su

Batch sentiment and intent analysis for up to 500 texts. Flat $3.00 USDC via x402.

把班级成绩表变成可执行的教学调整。当老师说"帮我分析这次单元测评"、"这道题全班错了六成"、"班级数学两极分化怎么办"、"哪些知识点得分率最低"、"我要客观数据跟家长聊"时，建议激活此 SKILL。工作流：导入逐题分数 → 班级画像 → 知识点热力图 → 分层 → 教学调整建议。本 SKILL 不出卷、不写教案、不排复习计划：命题与讲评设计转 xiaozhi-teach-exam-designer

虾评Skill平台评测模板生成工具。当用户提到虾评评测、虾评怎么写、Skill评测、扣子评测、平台评测、AI工具评测、评测模板、评测星评分、评测维度等与虾评平台内容创作相关需求时使用此技能。

Verify the serving stack with a user-specified target model. Runs twice: first with FlagGems/FlagCX disabled (isolate model-specific errors), then with full multi-chip stack enabled. Diffs the two run

Identify, categorize, and prioritize technical debt across a codebase — analyze TODOs, complexity hotspots, dependency age, test coverage gaps, and code duplication.

Developed by a senior office director with a PhD who taught himself coding: 38 document types, template-guided Q&A, reviewer profiling, no fabrication (〔待补〕), GB/T 9704. Wanna know how Chinese officia

合同规则审阅助手 - 上传本地合同文件到 AnyShare 并调用规则审阅技能进行自动化审阅，支持保存结果和生成分享链接

Take webcam snapshots with path validation, safe resource handling, and flexible output options.

基于面部和手部特征的趣味性格分析。结合传统面相学/手相学 + 行为经济学 + 行为心理学，提供深度的性格画像和实用建议。

Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detection are enforced every turn via the persisten

Search Yelp businesses and reviews, compare local options, and audit listing quality with official APIs, public pages, and safe action boundaries.

Build or review frontend UI for clean, restrained, human-designed interfaces without generic AI visual patterns.

Analyze product images: identify items, extract specs, compare features, generate descriptions.

The Consensus and Arbitration Primitive. A multi-agent deliberation framework designed to resolve complex disputes and validate truth claims through probabilistic reasoning.

Batch detect and mask PII across up to 500 text inputs. Flat $6.00 USDC via x402.

Identify duplicate company records by domain and name, export audit CSVs for review, and guide merging. API for discovery, third-party tools or manual UI for merging (HubSpot has no bulk merge API).

MPSTATS Ozon 俄罗斯站按品牌下钻商品列表。按 Ozon 品牌展示名（俄语/拉丁）返回该品牌下全部商品的销量、销售额、价格、评分、库存、周转、损失销售额等完整指标，支持多维数值筛选、排序、货币换算。用于品牌对标、竞品分析、品牌商品结构研究、ASIN 级（productId 级）爆款拆解。当用户提到 Ozon 品牌下钻、Ozon 品牌商品、Ozon 竞品品牌分析、品牌结构、品牌 SKU、品

Using a fixed camera in the living room (aimed at the sofa and TV area), the system analyzes the elderly person's continuous sitting time while watching TV, detecting whether the body remains in a sea

专业级AI合同审查专家 - 智能风险识别、条款自动修改、模板生成、法律合规检查，企业级合同管理工具

Exact detection thresholds for identifying malicious network patterns including port scans, DoS attacks, and beaconing behavior.

金蝶云星空经营数据分析技能。仅当用户明确要求分析金蝶云星空或 K3 Cloud 的库存、采购订单、销售出库、开票、结算等经营数据时使用；可读取 kingdee-data-exporter 导出的 Excel，也可自动调用同级导出技能实时取数，并生成 HTML 报告、全量明细 Excel 和结构化 JSON。

小红书笔记分析、爆文拆解、关键词挖掘、竞品监控。适合内容创作者、品牌运营、电商卖家。

亚马逊爆款评论分析 Skill：采集热销竞品评论，拆解爆款卖点、差评短板与买家真实需求， 输出选品验证、竞品调研与 Listing 打磨建议，附星级/趋势/关键词图表。 本包同时提供 ARI 完整评论分析能力：订阅 ASIN 并采集评论、浏览与筛选评论、 查看星级/关键词/趋势与雷达图表、生成 VOC 与深度洞察等分析报告、 运行商品运营工作流、商品变化监控（watch）、差评预警与差评工作台、

基于FastMoss数据搜索和筛选TikTok全球电商商品，支持关键词搜索、多维度筛选（类目、店铺类型、佣金率、销量、达人数等）和排序。当用户提到TikTok选品、TikTok商品搜索、TikTok产品数据、TikTok达人带货、TikTok佣金率、TikTok爆款追踪、TikTok GMV分析、TikTok product search, TikTok product research, Tik

Analyze staged changes and generate semantic commit messages automatically. Reads git diff --staged, analyzes code changes, generates conventional commit messages.

Validate data formats including JSON, email, URL, file paths, IP addresses, and phone numbers with detailed error reporting and batch processing.

Read-only Api3 feed discovery, readiness, coverage, and purchase-planning skill for downstream agent projects. Use when an agent needs to discover or verify decentralized data feeds, inspect funding/r

Security auditing skill for scanning CVE vulnerabilities across npm, Python, Go, and Rust projects using osv-ui. Opens a visual browser dashboard for human review, then applies fixes with explicit con

Runtime-neutral skill operations suite. Input a skill directory, slug, marketplace goal, or release plan; output quality checks, safety boundaries, naming/summary improvements, install-conversion diag

Interface for EvolutionNet Collective Intelligence. Allows agents to register, share verified experiences (anonymized), and participate in discussion threads to evolve together.

B2B企业数字化诊断——通过3道选择题判定企业专注类型（能力/行业/问题/混合），给出官网架构、短视频策略、小程序定位等数字化落地建议，并生成PDF诊断报告。适用制造业、工程服务商、工业软件等B2B企业。关键词：数字化、官网、短视频、B2B营销、企业专注、工业品推广、制造业营销。

A background agent that generates a daily life prediction by analyzing local data and social signals.

Analyzes and optimizes pricing strategy using proven frameworks

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

UX 启发式评估专家。基于 Nielsen Norman 10 条可用性原则检查用户体验问题。当用户说「review UX」「检查用户体验」「UX 评估」「可用性检查」「启发式评估」时触发。

Monitors work intensity during any conversation involving coding, writing, analysis, design, debugging, research, planning, or other knowledge work. Tracks user activity timestamps and inserts natural

Use for PostHog project-token runtime capture, event batching, and remote feature-flag evaluation with caller-owned tokens, local previews, and explicit confirmation before any provider request.

All-in-one JSON toolkit — format, validate, query, minify, and extract data from JSON. Built-in JMESPath query, JSONPath support, syntax highlighting. 适合API调试、数据处理、前端开发。JSON beautifier, parser, valida