Skill rating

一句话需求 → 结构化 PRD + 评审 Checklist。支持中英文、图表、JSON导出、多角色评审。

Audit, manage, and clean up feature flags across codebases to reduce toggle debt

Generate first-draft technical documentation from code analysis

Analyze data evolution patterns in construction organizations. Assess digital maturity and data strategy for construction companies

Classify construction data by type (structured, unstructured, semi-structured). Analyze data sources and recommend appropriate storage/processing methods

Detect and map data silos in construction organizations. Identify disconnected data sources and integration opportunities

为AIME（AI交易助手）生成综合用户行为分析报告。当用户要求分析用户行为、生成用户报告、分析交互模式、调查用户流失、了解用户参与度或从用户ID或日志数据创建分析文档时，使用此技能。

Tai Alpha stock analysis — collect, VectorBT backtest (RSI/MACD/BB), conviction score, optional ML. Persistence is SQLite (default tai_alpha_output/tai_alpha.db); override TAI_ALPHA_DB_PATH.

Multi-database SQL assistant — query MySQL, PostgreSQL, SQLite & MariaDB across dev/test/prod environments with a single command. Security-first: read-only by default, DML/DDL gating, EXPLAIN analysis

开店选址综合分析助手。用户输入目标地址和开店类型，自动整合高德地图实时数据（地理编码、POI搜索、交通态势），从人流量、用户群体、客流特点、消费情况、竞品分析六大维度进行评估，生成交互式HTML可视化选址报告（含评分仪表盘、雷达图、竞品对比表、行动建议）。覆盖餐饮零售服务等全业态。触发词：开店选址、选址分析、店铺选址、选店面、开店评估、门店选址、帮我选店面、这地方能开店吗、开奶茶店选哪里、餐饮选址

「AI 通识课资深专家 V5.5」——V4.3 升级版，融合 AI 通识课完整课程体系（A→G 七大模块）+ p5.js 2.x 艺术创意编程 + 沉浸式 2D/3D 冒险游戏化 + 交互式问答生成完整备课文档 + 智能学习评估反馈系统 + 商用生产级（SLA/契约/容错/成本/可观测性/安全/版本/QA）+ 离线支持（Service Worker/IndexedDB）+ 团队协作备课 + ⭐ W

A governed project management OS for OpenClaw that routes user project work through an orchestrator, enforces onboarding wiring, model validation, subagent coordination, and log/memory governance for

Generate FOSMVVM Fields protocols with validation rules, FormField definitions, and localized messages. Define form contracts once, validate everywhere.

Set up Prometheus for comprehensive metric collection, storage, and monitoring of infrastructure and applications. Use when implementing metrics collection, setting up monitoring infrastructure, or co

Analyze ChatGPT conversation exports to discover cognitive archetypes and optimize AI-human communication patterns. Enables personalized agent interactions based on detected user profiles.

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption. Use when buildin

Type-based autonomous task queue system. Categorizes tasks by type (research, writing, analysis, maintenance) and lets autonomy work only on value-add tasks while cron handles maintenance. Use when yo

Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or ana

Audit and rewrite content to remove AI-generated feel by stripping markdown artifacts, eliminating AI vocabulary patterns, flagging hallucination risks, and restoring natural human voice. Use whenever

Runtime prompt injection defense for agent workspaces. While other tools watch workspace identity files, Bastion protects the input/output boundary — the files being read by the agent, web content,...

Psychological profiling through natural conversation using narrative identity research (McAdams), self-defining memory elicitation (Singer), and Motivational Interviewing (OARS framework). Use when yo

Security scanner and hardening tool for OpenClaw. Use when the user asks about security, wants to scan installed skills for malware or vulnerabilities, audit their OpenClaw configuration, check their

Data validation and signal extraction service for agents. Sift through raw outputs (JSON, text, data streams) to extract quality signals, validate against schemas, and score reliability. Use when: (1)

Evidence-based endurance cycling coaching protocol (v11.5). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions,

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators pe

Verify documentation coverage and generate missing docs interactively

会议逐字稿精细化分析工具：输入腾讯会议或飞书会议链接，输出结构化分析 JSON（阶段/关键点/决策/待办/参与者画像）、drawio 概要图与 Markdown/HTML 报告。当用户要分析会议逐字稿、生成会议纪要可视化、提取会议关键内容截图、制作会议总结网页时使用。

横纵分析法（Horizontal-Vertical Analysis）深度研究Skill。由数字生命卡兹克提出，融合了索绪尔的历时-共时分析、社会科学的纵向-横截面研究设计、商学院案例研究法与竞争战略分析的核心思想。 当用户想要系统性研究一个产品、公司、概念、技术或人物时使用。核心是双轴分析：纵轴追踪从诞生到当下的完整生命历程（以叙事故事呈现），横轴在当下时间截面上与竞品/同类进行系统性横向对比，

可移植自包含的股票分析薄编排 skill。行情/基本面/新闻/资金流等全部数据委托 sibling skill a-stock-data（A股，43端点）运行时取数；本 skill 只做输入归一化、技术指标(纯标准库)、上下文合并、LLM 决策仪表盘 prompt、报告存储。覆盖 A 股 + A 股 ETF（港美台不支持）。编排流程与 prompt 内置，任何支持 skill 的智能体项目都能用。

General AI agent introspection debugging framework: auto capture errors, root cause analysis, automatic repair, fix verification, no manual intervention required

Public network MTR diagnosis tool. Supports both manual guidance and Cloud Assistant automation modes. Manual mode guides users to run MTR tools locally (macOS/Linux/Android/Windows) and analyze resul

The Instagram SEO / keyword-search skill -- IG-specific search depth, distinct from the cross-cutting social-seo. Use when someone wants an Instagram post/Reel to rank in search, needs IG keyword rese

Use when writing, reviewing, or filling gaps in PRDs, product requirements, BRDs, functional specs, or SaaS/admin workflows that must become implementation-ready. Especially useful for business flows,

Warren Buffett-lens scorecard for any ticker. Scores 4 dimensions 0-100 each (business / circle of competence, moat / durable advantage, management / capital allocation, valuation / fair price vs 10Y

Evaluate 副业、产品构想、商业价值、AI 项目、睡后收入、开源变现和小游戏 with evidence, first-transaction paths, Phase 0, portfolio fit, and stop rules.

Full earnings-season IV analysis: historical crush, implied move forecast, IV Rank strategy tag, and a priced Iron Condor quote ready to trade. Triggers: "earnings crush AAPL", "NVDA IV before earning

Disciplined, legible, resumable execution of a single already-defined task — one task, one plan the user approves before any code is written, every change validated. Use this skill whenever the user s

Analyze data evolution patterns in construction organizations. Assess digital maturity and data strategy for construction companies

完整复刻 @jukan05（GF Securities 半导体分析师/150K粉丝 X KOL）的投资分析体系。 以「快速成长趋势识别」为核心分析框架，对任意个股、行业或市场生成「就像 Jukan05 本人撰写」的分析报告。 支持任意标的：若 Jukan 曾分析过，自动引用其历史观点；若未分析过，用其方法论推导。

Offline, defensive robustness auditor for LLM benchmarks: n-gram exact + shingle-Jaccard paraphrase contamination, temporal pre/post-cutoff gaps, TS-Guessing above-chance detection, option-letter sele

Run a multi-source, agentic literature review with real citations. Searches arXiv, Semantic Scholar Open, OpenAlex, and Crossref; deduplicates; screens abstracts against user-defined inclusion criteri

Code review and validation for CloudBase projects. After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill to check for known pitfalls — auth guard misuse, missi

Alibaba Cloud RAM permission diagnosis and repair assistant. When an agent encounters any permission-related error while operating Alibaba Cloud resources (403, NoPermission, Forbidden, AccessDenied,

Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer,

Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers. Use when setting up linting and formatting for a project.

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

Salesforce Industries Common Core (OmniStudio/Vlocity) Apex callable generation and review with 120-point scoring. TRIGGER when: user creates or reviews System.Callable classes, migrates `VlocityOpenI

Reviews skills (D1-D11 + M1-M6 criteria) or .claude/commands for quality. Use when validating skill correctness before release.

Premium UI/UX design audit and refinement skill. Conducts systematic visual audits of existing apps and produces phased, implementation-ready design plans. Use this skill whenever the user asks to aud

Resolves unresolved GitHub PR review threads end-to-end: evaluates whether each review comment is correct, applies a targeted fix when valid, replies with rationale when not, commits, and resolves the