Skill rating

Use when building, auditing, or simplifying an AI coding-agent harness, especially when the current runtime has unclear config precedence, weak tool permissions, hidden product-only behavior, or poor

Safely assess and purchase TLMNT Mini App Doctor evidence for a public Farcaster Mini App URL. Use when an agent must diagnose manifest or embed issues, obtain a 0.75 USDC Static Evidence Dossier, or

Audit an unfamiliar codebase and map architecture, user-facing features, maturity, and risks. Use when the user asks to inspect a repo, summarize the stack, explain structure, list implemented feature

学术论文润色修改全流程SOP。从审稿意见解析、论文全息诊断、可视化批注生成、分级改写执行到终审自检的完整闭环。当用户需要根据期刊审稿意见修改论文、需要论文润色、需要去AI味、需要学术写作规范检查时触发。典型触发："修改这篇论文""根据审稿意见润色""去AI味""按期刊要求压缩字数""帮我看看这篇论文能不能通过"。

Local STT with selectable backends - Parakeet (best accuracy) or Whisper (fastest, multilingual).

中国专利技能：挖掘专利点与编写交底书（发明/实用/外观），把已有交底改写成申请文件四件套，也可按材料交底申请一起做，按著录字段检索公布公告，通俗解读专利，对照审查口径出政策简报，辅助审查答复。| China patents skill: mine patent points and draft disclosures, rewrite an existing disclosure into app

Auto-route tasks to the cheapest z.ai (GLM) model that works correctly. Three-tier progression: Flash → Standard → Plus/32B. Classify before responding. FLASH (default): factual Q&A, greetings, remind

Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new f

The Noveum AI reliability & QA engineer for LLM, agent, and voice apps — sets up and operates Noveum.ai end to end in a codebase, integrating the noveum-trace SDK (LangChain, LangGraph, CrewAI, LiveKi

Connect to and explore databases (PostgreSQL, MySQL, SQLite, MongoDB, Redis). Run queries, inspect schemas, export data. Use when user wants to query a database, explore schema, check data, export res

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions — Claude Code remembers previous context within the same workdir. Use when the user asks

Extract flood extent from SAR backscatter imagery. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.

Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release

Wakapi coding stats (summaries, projects, today status, totals) via a small Python CLI. Requires WAKAPI_URL. WAKAPI_API_KEY is HTTP Basic (Authorization Basic base64(key)) for all calls except health,

Identify vegetation encroachment, rapid growth, and tree fall risks along powerline corridors. Generate prioritized inspection points. Use when screening vegetation near powerlines, assessing tree fal

Review a Java Maven project delivered as a ZIP archive or a GitLab repository URL for code规范, naming, module boundaries, maintainability problems, duplicated logic, structure issues, and整改建议. Use when

Use when implementing or reviewing frontend server-state flows: typed queries, request caching, invalidation, mutations, optimistic updates, infinite queries, prefetch, SSR hydration, or API-layer int

Identify potential debris-flow gullies, integrate terrain, material source, rainfall trigger, and downstream exposure to produce basin-level hazard screening and risk assessment.

检索并导出 SVN 和 Git 仓库中指定人员的提交记录及修改点信息。支持按作者、时间范围、项目路径过滤，可导出为 Markdown、CSV、JSON、Detailed 等格式。Detailed 格式包含完整提交日志。当用户说"导出某人的提交记录"、"查看提交历史"、"生成提交日志"、"导出代码提交记录"、"查看 SVN 提交"、"导出 Git 历史"、"查看提交备注"等类似请求时触发此 Skil

Generate EIP-681 Ethereum payment links and QR codes for any EVM chain. Zero configuration, instant setup for receiving ETH and ERC-20 payments. Use when you need to create payment requests, invoices,

A local missing person assistance tool for organizing cases, managing clues, generating notices, and providing search guidance.

Debug through a structured root-cause process instead of guesswork. Use when commands fail, tools behave unexpectedly, automations break, integrations only partially work, or the real cause is unclear

Multi-temporal shoreline change rate analysis. Generates transects, computes Endpoint Rate (EPR) and Linear Regression Rate (LRR), and identifies erosion hotspots. Use when monitoring coastline retrea

Manage whitelisted git repositories from chat. Status, log, diff, pull, push with security controls — only approved repos, write commands need confirmation. Repo list configurable via ~/.config/git-sy

三个能干活的 AI 分身协作系统。用 Claude Code 启动三个不同人设的 coding agent，共享同一个工作目录，多轮协作直到达成共识。适用于代码审查、方案评审、重构任务等需要多视角协作的场景。

A cat clone with syntax highlighting, line numbers, and Git integration - a modern replacement for cat.

Safely migrates OpenClaw memory from LanceDB Pro, official LanceDB list captures, QMD, or Markdown into memory-core. Use when an owner asks to migrate, audit, deduplicate, benchmark, cut over, or roll

观势专家集群 — 数据分析专家。负责数据清洗/统计推断/财务建模/可视化/情景模拟，将原始数据转化为分析洞察。Use when 被观势 Chief 调度执行数据处理、统计分析、ROI测算、敏感性分析、数据可视化、情景推演。不适用于原始数据获取（→情报获取专家）、纯定性分析。

Detect and quantify urban expansion from multi-temporal built-up rasters. Use when the user wants to analyze changes, compare multi-temporal rasters, compute indices, or generate assessment reports.

Fallback image viewer when vision models are unavailable. Converts images to ASCII art via ffmpeg + Python for brightness distribution, texture analysis, edge detection, and color sampling — without a

Turn a product idea into a manual-first process you can start delivering today. Use when you have an idea and want to figure out how to deliver value by hand before writing any code.

New and fucking improved with more cursing. Install, run, recover, or explain the standalone ClawPatch queue supervisor when someone needs a whole repair queue, exact stopped-finding recovery, or real

Integrate Self (self.xyz) — a privacy-first identity protocol using zero-knowledge proofs to verify passports and ID cards. Use when the user mentions Self protocol, Self identity, self.xyz, passport

Fast lightweight verification pass for recent work. Use proactively after medium or large tasks, coding passes, app changes, or long replies when you need a quick check for missed asks, partial comple

Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

Identifies acquaintances in videos or images through face photo comparison. Supports database enrollment, and the recognition results tell you who is at which location. Suitable for identity verificat

Variflight Global Flight Fares searches one-way flight fares from the Variflight ticket API by departure IATA city code, arrival IATA city code, and departure date.

Spec-first execution workflow for OpenClaw that turns large, vague, or messy project requests into phased, verifiable implementation plans. Helps build, rescue, refactor, redesign, organize, and finis

Java 代码审查报告生成器。用于审查 Java 代码变更，生成结构化审查报告。 触发场景： (1) 审查 git diff 或代码变更 (2) 审查 Java 源文件 (3) 代码质量检查 (4) PR/CR 审查 (5) 检查代码是否符合 Google Java Style、阿里 Java 开发手册、Clean Code 规范 支持输入：git diff 输出、Java 源文件、需求/设计文档

Unified configuration manager for AI coding assistants. Manage profiles, install skills/agents/commands, and switch configurations across Claude Code, OpenCode, Goose, and Amp.

Use Camofox/Camoufox as an opt-in anti-detection browser server for agent workflows that need cloaked browsing. Covers npm/npx startup, OpenClaw plugin tools, REST API commands, session/tab workflow,

Detect forest disturbance from multi-temporal NDVI. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.

Parallel multi-agent coding sprints using git worktree isolation. Unlike naive parallel agents that silently overwrite each other's work, Swarm gives each agent its own private copy of the repo (a git

Scrape Product Hunt daily/weekly/monthly/yearly leaderboard launches with full product details, maker profiles, and website contact info. Use when user mentions Product Hunt, producthunt, PH scraper,

Generate structured summaries of recent git commit activity. Use when the user asks for a commit summary, changelog draft, standup notes from git, or to understand what changed in a repo over a time r

You are a frontend development specialist with deep expertise in modern web technologies and frameworks. Use when: react, vue.js, angular, svelte, state management, typescript and modern javascript, c

Create, edit, and package new AgentSkills. Use when asked to create a skill, build a skill, author a skill, or when需要对技能进行创建、打包或审核。Triggers on phrases like "create a skill", "author a skill", "build a

Scan/clean Maya scene malware on Windows. Use for Maya杀毒, Maya病毒扫描, Maya病毒查杀, 清理Maya病毒, 病毒查杀, Maya antivirus, Maya virus scan/removal; not general antivirus.

Generate slides, audio overviews, and documents from sources using Google NotebookLM via browser automation. Use when the user wants to (1) create presentation slides from topics or sources, (2) gener

Retrieve Amazon product data including pricing, reviews, sales estimates, stock levels, search results, deals, and more via the Canopy API REST endpoints using Python.