AI & ML

clawrun-sh Bundle

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

clawrun-sh Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

astoreyai Bundle

Portfolio Forecasting Agent

van7171 Bundle

Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

flutterclaw Skill

Manage workspace files and agent configuration

astoreyai Bundle

Portfolio Analysis Agent

open-agent-craft Skill

Use this skill when you need a focused, repeatable workflow for a specific agent task. Replace this description with trigger words, scope, and boundaries.

ooshka Bundle

Development planner for deciding the next concrete implementation step, balancing feature delivery with hardening, spotting tech debt/refactor signals, and producing small agent-ready Case files under agent_docs/. Use only when the user explicitly asks for `$planner`, explicitly asks to use the planner skill by name, or explicitly asks for planner-driven Case generation in this workflow. Do not use for generic planning questions unless the user specifically invokes this skill.

ooshka Bundle

Spin up an isolated, sandboxed git worktree for a long-running/autonomous agent. Creates the worktree in a central tree (~/projects/worktrees/<repo>/<name>, never under a repo's .claude/) and seeds it with a .claude/settings.local.json that enables the OS sandbox so bash + git run hands-off, confined to the worktree. Use when the user wants to "spin up a worktree for an agent", run unattended/long-running work, or avoid babysitting bash permission prompts.

rloisell Skill

BC Government network security classification and zone model. Use when determining what security zone a workload belongs to, mapping ISCF data classification to DataClass labels, designing connectivity between zones, evaluating internet egress constraints, or planning Third Party Gateway (3PG) connections to external partners.

rloisell Skill

Zero Trust Architecture (ZTA) and SASE design — identity-first access, ZTNA, CASB, SWG, FWaaS, SSE/SASE frameworks, SD-WAN security integration, microsegmentation, policy engine design, and NIST SP 800-207 control mapping. Use when designing a ZTA, building a SASE deployment model, evaluating SD-WAN + security stack integration, or auditing implicit trust assumptions.

514-labs Bundle

One sentence describing when an agent should use this skill. Include trigger phrases users are likely to say.

514-labs Bundle

ALWAYS invoke this skill when the user wants to test, compare, optimize, or iterate on variants of a developer-facing artifact — a CLI, an MCP server, Claude/agent hooks, an install script, docs, or a schema — using axp experiments. Trigger phrases: "test variants of", "which version works better", "optimize my CLI/MCP/docs for agents", "run a build loop", "A/B test my tool descriptions", "iterate on this with axp". Do not hand-roll experiment YAMLs and one-off comparisons for these tasks; drive the full loop with this skill instead.

enkrateialucca Skill

Write a structured, timestamped handoff document that captures the current session's context (what was done, what changed, key learnings, next steps) so a fresh agent session can resume the work without replaying the prior conversation. Use when the user says "create a handoff", "save a handoff", "write a status.md", "end-of-session summary", "save session context", or wants to wrap up a working session so it can be picked up later.

enkrateialucca Skill

Resume work from a handoff document written by a previous agent session, with context analysis and drift validation before any work starts. Use when the user says "resume from the handoff", "pick up where we left off", "continue from yesterday's session", "resume handoff", or points at a file in a handoffs/ directory. Pairs with the create-handoff skill, which writes the documents this skill consumes.

driftingradiance Skill

在当前项目启用已注册的 MCP server

driftingradiance Skill

在当前项目停用 MCP server（保留定义，只切 disabled 列表）

driftingradiance Skill

列出所有注册的 MCP server 及当前项目 ON/OFF 状态

driftingradiance Skill

从 MCP_REPO 和所有项目配置中完全删除 MCP server

driftingradiance Skill

从 preset/npx/github 安装 MCP server 到 MCP_REPO（默认不启用）

uncertaintydeterminesyou4ndme Bundle

PowerShell and Windows Command Prompt (CMD/Batch) expert skill. Use whenever the user asks about PowerShell, pwsh, CMD.exe, batch files, Windows Terminal, Windows command line, Windows administration, Windows automation, registry edits, Windows services, event logs, scheduled tasks, WMI/CIM, Active Directory, UAC, execution policy, file permissions, PATH environment variables, or running Windows commands from an agent. Trigger especially on phrases like: "write a PowerShell script", "how do I do X in CMD", "Windows batch", "PowerShell error", "my CMD command failed", "list services", "query event logs", "registry key", "Windows admin", "automate Windows", "PowerShell vs CMD", "batch script", "elevated PowerShell", "execution policy".

onyxyno Skill

Security audit of an MCP (Model Context Protocol) server via the MCTS scanner (Model Context Threat Scanner, `mcp-mcts`). Produces a report with legacy + v2 scoring (8 risk dimensions, per-finding contributions, attack chains, baseline for regression detection). Distinguishes heuristic false positives from real risks and proposes pragmatic mitigations (confirmation tokens for destructive tools, local-path validation, read/egress isolation). Triggers (EN): "MCTS audit", "MCP security scan", "audit my MCP server", "MCTS score", "MCP threat scan", "check MCP risks", "run MCTS on", "mcp-mcts", "MCTS findings", "MCTS baseline", before publishing an MCP server (PyPI/npm). Triggers (FR): "audit MCTS", "scan sécurité MCP", "auditer mon serveur MCP", "score MCTS", "vérifier les risques de mon MCP", "passer MCTS sur", "mcts baseline", avant publication d'un serveur MCP.

minhngoc25a Skill

Use Tavily through the local MCP server for web search, URL extraction, site mapping, crawling, and research. Use this skill whenever the user wants to search the web, find articles, look something up online, extract content from a URL, read a webpage, map a website, crawl documentation, download or inspect multiple pages, or conduct in-depth research with citations. This skill routes requests to the right Tavily MCP tool and does not use the Tavily CLI.

minhngoc25a Skill

Discover and list URLs on a website through the local Tavily MCP server without extracting page content. Use this skill when the user wants to find a specific page on a large site, list pages, inspect site structure, locate docs, or says "map the site", "find the URL for", "what pages are on", "list all pages", or "site structure". Faster than crawling because it returns URLs only.

minhngoc25a Skill

Crawl websites and extract content from multiple pages through the local Tavily MCP server. Use this skill when the user wants to crawl a site, inspect or download documentation, extract an entire docs section, bulk-extract pages, get all pages under a path, or says "crawl", "get all the pages", "download the docs", "extract everything under /docs", or "bulk extract". Supports depth and breadth limits, path/domain filtering, semantic instructions, and markdown or text extraction.

minhngoc25a Skill

Search the web with LLM-optimized results through the local Tavily MCP server. Use this skill when the user wants to search the web, find articles, look up current information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", or "find articles about". Returns relevant results with snippets, scores, metadata, and optional raw content or images.

minhngoc25a Skill

Extract clean markdown or text content from specific URLs through the local Tavily MCP server. Use this skill when the user provides one or more URLs and wants their content, says "extract", "grab the content from", "pull the text from", "get the page at", "read this webpage", or needs clean text from web pages. Supports advanced extraction for JavaScript-heavy pages and query-focused extraction.

minhngoc25a Skill

Conduct comprehensive AI-powered research with citations through the local Tavily MCP server. Use this skill when the user wants deep research, a detailed report, comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", or "what does the market look like for". Produces synthesized analysis grounded in web sources. For quick fact-finding, use tavily-mcp-search instead.

the-notorious-avengers Bundle

Reference for the tawk.to REST API v1.1.0 (https://api.tawk.to/v1). Covers authentication (API key Basic Auth + OAuth2), every endpoint group (Property, Widgets, Members, Chats, Tickets, Tabs, Knowledge-Base, Webhook, Metrics, Contacts), scopes, error shapes, and pagination. Has deep coverage of the Knowledge-Base content-block model and a workflow for turning markdown files plus image links into KB articles (host images on Cloudflare R2 or DigitalOcean Spaces, then reference by URL). Use when integrating tawk.to, calling its API, programmatically creating or syncing knowledge base articles, categories, or sites, or converting markdown content into tawk articles.

frank-oll Bundle

端到端制作竖屏 AI 妙招短视频(默认 3 镜 × 5 秒 = 15 秒,9:16)。题材通用:三农园艺、阳台种菜、美食、家居清洁收纳、宠物、育儿等都行,开场先问用户选题方向,不预设。工作流:方向确认 → 热门检索/对标视频拆解 → 双锚定(视觉一致 + 叙事承接)→ 全中文分镜 prompt → 一致性生图(火山 Seedream)→ 图生视频 + 原生 AI 配音(火山 Seedance 1.5 pro)→ ffmpeg 自动拼接成片。单网关单 key(火山 ARK,ark- 开头)。支持标准/快速/托管三档确认模式,生成物 agent 先做多模态自检再交付。当用户说"做 AI 视频""做一条妙招短视频""三农/阳台种菜/园艺短视频""美食/清洁/收纳妙招视频""复刻这种短视频""按这个对标拍一条",或上传带"内容由 AI 生成"标识的妙招类短视频做对标时,触发这个 skill。不要跟 script-washing(洗稿)、prompt-polish(单条提示词打磨)混用——这个是从选题到成片的端到端视频生产。

rloisell Bundle

Self-learning agent that monitors development sessions and evolves the agent skill library — surfaces past relevant knowledge before sessions begin (pre-session retrieval), appends causal discoveries to *_KNOWLEDGE sections, identifies candidate shared skills from recurring patterns across sessions, flags oversized agents needing references/ splits, and records all updates in the evolution log. Use at session start for retrieval and at session end to grow the team's shared intelligence.

mdadul Bundle

Create and maintain custom subagent definition files for any AI agent platform, with strong descriptions, tight tool scope, and explicit handoff contracts. Use when the user asks to create, improve, or standardize a subagent.

mdadul Bundle

Teach and apply the Composite pattern to model tree structures where leaves and containers share a common interface and can be handled uniformly. Use when users ask about Composite or Object Tree, recursive aggregation, uniform leaf/container operations, or comparing Composite with Decorator, Visitor, or Iterator.

chris0214 Bundle

Use when Codex needs to write or modify MMD/MME shader files such as .fx or .fxsub, including model shaders, post effects, render-target chains, controller-driven effects, or ray-mmd/sdPBR/ExcellentShadow-compatible effect code.

chris0214 Bundle

Use when Codex must decide whether an MMD/MME visual effect can be implemented, whether it should be standalone or framework-based, and what shader model, render target, controller, hardware, or compatibility risks apply.

mozartinos Bundle

Companion skill for the MiroFish multi-agent simulation engine. Use when planning or running MiroFish simulations, writing source material or simulation requirements, debugging graph/entity/profile/config/runtime/report stages, evaluating run quality, validating model or proxy routes, interpreting generated artifacts, or maintaining a repository of MiroFish best practices.