AI & ML

kukucaicndy Skill

Converts Pencil MCP .pen design files to WeChat Mini Program code (WXML+WXSS+JS) with precise 1:1 visual replication. Invoke when user needs to implement a page from a Pencil design稿.

kurone-kito Bundle

Semantic audit of the IDD instruction corpus for leaked session context, cross-file contradictions, fresh-memory completability gaps, automation blockers, and restatement-discipline drift. Use on request to audit .github/instructions, the issue-authoring skill bundle, and the installed agent entry files (CLAUDE.md, AGENTS.md, GEMINI.md, .github/copilot-instructions.md). Read-only — never edits files or mutates issues.

langgraph4j Bundle

This agent return commit description evaluating the updates for the provided file path required input are: * commit file path

langgraph4j Skill

payment agent, this is the agent that provides payment service. required data are: * Product name * Product price * Product currency * the International Bank Account Number (IBAN) - optional

langgraph4j Skill

marketplace agent, ask for information about products. This is agent that provides the information on the product marketplace. required data are: * product name

lollipopkit Bundle

Create concise, evidence-based handoff notes for another AI coding agent. Use when the user asks for a handoff, continuity note, next-agent summary, progress transfer, "告诉别的 agent", "handoff skill", "交接", or wants the current state, completed work, remaining plan items, risks, and next steps captured for another agent without writing a verbose work log.

lollipopkit Bundle

Maintain an evolving linked documentation library for project wikis, ADRs, design notes, research notes, release notes, and decision logs. Use when asked to create, grow, repair, reorganize, or verify a wiki/ADR knowledge base with Markdown pages, YAML frontmatter, Obsidian-style [[wikilinks]], source-backed citations, llmwiki/llm-wiki-compiler projects, or a durable project memory that should compound over time instead of being rewritten from scratch.

abdullahmalik17 Bundle

Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).

agentscope-ai-hiclaw Skill

Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.

agentscope-ai-hiclaw Bundle

Discover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.

outlinedriven Bundle

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

mjunaidca Bundle

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

aquariuscook Skill

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

clawdsolana Bundle

Control Claude Code via MCP protocol. Trigger with "plan" to write a precise execution plan then feed it to Claude Code. Also supports direct commands, persistent sessions, agent teams, and advanced tool control.

lifangda Bundle

Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, QA, summarization, translation, and image tasks. (plugin:scientific-packages@claude-scientific-skills)

caizongyuan Bundle

This skill should be used when users need to work with AgentScope, a multi-agent platform for building AI-powered applications. It provides comprehensive guidance on agents, tools, memory management, models, RAG, workflows, evaluation, and development operations.

caizongyuan Bundle

This skill should be used when users need to work with AgentScope Runtime for deploying, managing, and operating AI agent applications. It provides comprehensive guidance on AgentApp deployment, service architecture (State, Memory, Session, Sandbox), API integration, CLI workflows, deployment strategies, tools and skills management, and advanced features including real-time processing and training environments.

drolu Skill

Create or update Pi prompt templates and Agent skills from a short user brief. Produces minimal, well-structured SKILL.md or prompt files that follow Agent Skills best practices.

englandtong Bundle

Execute an authorized software goal through low-context, bounded-autonomous AI coding loops with persistent state, proactive repair, automatic and functional evidence, layered stage review, independent final acceptance, safe workspace boundaries, and resumable handoffs. Use when a target and acceptance criteria are clear and the user asks to implement, debug, verify, continue autonomously, follow Controller-Developer-QC cycles, resume after context loss, or reduce repeated context and documentation. Typical triggers include keep going, continue where we left off, run it autonomously and fix what breaks, 接着跑 / 继续做 / 自动修 / 断点续跑 / 别再问我每一步, we are stuck on the same failure, 卡在同一个错误上, resume after compaction, 上下文快满了, stop burning tokens on repeated context, run the regression after this repair, and make a flaky test deterministic. Also use for bounded-autopilot, single-writer loop state, failure-signature stop rules, delivery-class-aware evidence, and anti-doc-bloat execution. For vague goals, legacy-state conflic

forgeyclap Skill

Produces the standard end-of-task Forge report — project adaptation, agent ledger, memory update. Use when delivering the result of any non-trivial /forge build, fix, or review.

moonweave-systems Bundle

A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate directions, cheaply score each by that fitness, and pick the winner by the number — not by taste, and not by polish. Lightweight and inline: it is a discipline, not a multi-agent engine. Manually triggered via `/anneal` only — never auto-invoked. Use when the user types `/anneal`, typically at a fork where the best approach is not obvious.

openly-useful Bundle

Show truthful, low-overhead live progress for any agent, skill, test, workflow, or automation run. Use for a portable RunGlance HUD, workflow/skill/agent accounting, context and quota visibility when hosts report it, explicit lock state, one-second local status watching, host hook normalization, verification commands, and concise or verified final run receipts. Works without model calls, network access, API keys, or the optional read-only RunGlance MCP companion.

openly-useful Bundle

Inspect, validate, generate, and maintain evidence-backed project readiness. Use for weighted readiness, blockers, active and deferred effort, unknown estimates, provenance checks, one-shot live monitoring, dashboard plan/apply/check workflows, repository attachment for Codex and Claude, or local Project Status plugin packaging and verification. Use the separate RunGlance skill for live agent, workflow, test, usage, lock, HUD, and run-receipt tracking.

paldom Bundle

Authors or improves one Agent Skill via the eval-first workflow - scope a single purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for infrastructure work - hooks, CI, the validator, or docs.

skillmedev Skill

Drafts specific, observable, kind workplace feedback using the SBI model - Situation, Behavior, Impact - for both praise and correction. Use when someone asks "help me give feedback to a teammate", "how do I tell my report they keep missing deadlines", "make this feedback less vague", or wants to reinforce a good behavior specifically. Do NOT use for formal performance review documents - use performance-review-writer instead; for feedback on student work, use student-feedback-writer; for mediating an active interpersonal dispute, use conflict-resolution.

theakshits Bundle

Get input from a different AI model (GPT-5, Gemini, Claude variants, or any model reachable via opencode/cursor-agent/kiro-cli) on a question, plan, or piece of code. Trigger this whenever the user wants another model's take, opinion, or judgment — "what would GPT-5/Gemini/another model say/think", "is this safe/right, get another opinion", "ask another model to check/review/weigh in", wants to delegate or run a prompt through cursor/opencode/kiro, wants to pick the best model for a task and run it, or wants to switch/set the default external-model CLI. Applies even without naming a CLI or model, and even when the ask is implicit ("before I ship this", "am I sure about this approach") rather than an explicit request for a "second opinion." Not for — re-running the user's own code/tests, asking Claude itself to reconsider, or general questions about what a CLI tool is/does.

abracadabra50 Bundle

Grocery automation across nine retailers in five countries — UK, Netherlands, Belgium, Spain and the US. Search, compare, basket, delivery slots and checkout, plus Open Food Facts nutrition and allergen enrichment. Available as CLI, MCP server, or agent skill.

alexgreensh Bundle

Cross-agent self-inspection of your AI-agent stack. Audits skills, MCP servers, hooks, plugins, commands, credentials, and memory files across Claude Code, Codex, OpenClaw, and NanoClaw. Produces a structured inventory and narrative briefing with cross-ecosystem risk analysis. Use when the user asks to audit their own setup, check what they have installed, review their agent stack security posture, or understand cross-tool interactions. Use when a user has accumulated skills/plugins/MCP servers over time and wants visibility into their attack surface. Use after installing new skills or plugins. Do NOT use for vetting external code before install (that is repo-forensics). Do NOT use for incident response during active attacks. Do NOT use for fixing or patching vulnerabilities (forensify is read-only).

alexgreensh Bundle

Security forensics for git repos, AI skills, and MCP servers. Audits dependencies, detects prompt injection, credential theft, runtime dynamism, manifest drift, known CVEs, CISA KEV (actively exploited) vulns, and 2026 attack patterns. Not for fixing vulnerabilities or pentesting.

alextiannus Skill

中文长篇小说全流程创作技能（v1.0.0）。当用户想写小说、创作故事、续写章节、构思剧情、搭建世界观、设计人物关系、提取写作风格、仿写其他小说时，必须使用本技能。覆盖从模糊想法到300万字成品的完整链路：脑洞引导、知识图谱构建、大纲管理、分镜写作、质量门禁、跨Agent审核、风格校准、中途改纲级联更新。即使用户只是说"帮我写个故事"或"我有个小说的想法"，也应触发本技能。

alignbase Skill

Use when testing MCP servers -- e2e tests with the sunpeak inspector, visual regression testing, live testing against real ChatGPT, multi-model evals, Playwright configuration, or scaffolding test infrastructure with "sunpeak test init". Works with any MCP server (Python, Go, TypeScript, etc.), not just sunpeak projects.

alphamao1 Bundle

全自动生成前沿技术领域的全景图谱。适用于以技术为核心的赛道（如量子计算、核聚变、AI Agent 等），通过双向挖掘（正向追踪学术源头 + 逆向溯源独角兽创始团队）构建学术→开源→商业化的完整脉络。触发词：「技术mapping」「技术全景图」「technology map」「赛道图谱」。

alphamao1 Bundle

构建和维护可累积的研究认知模型。适用于持续投资研究、行业/公司/技术主题研究、独立 Research dossier、Current Model 状态恢复、材料吸收、并行搜索、模型更新、范围拆分合并、promote 到 Obsidian 主知识库前审计，以及用户要求“研究一下/更新模型/现在我们知道什么/把重要成果入库”时使用。

withcoral Bundle

Query live sources through Coral MCP. Use when the task needs GitHub, Jira, Slack, Linear, Datadog, Sentry, files, or connected data.

withcoral Bundle

Create or update a Coral source spec YAML for a custom HTTP API or local dataset. Use when authoring a standalone source for `coral source add --file`, or when adapting that spec into a Coral repo source under `sources/core` or `sources/community`.

wunamesst Bundle

将自然语言接口描述、接口文档、参数表格或支持的后端代码转换为标准 OpenAPI 3.0.3 JSON， 并在需要时生成 Postman Collection 等平台兼容产物，供 Postman / Apifox / ApiPost 导入后形成可调试接口。 Use when the user asks to generate, export, convert, or validate Swagger/OpenAPI/importable API documentation from existing API descriptions, docs, tables, or code. Do not use merely to implement, call, debug, or review API code. Directly writing/importing into external platforms is outside this skill and belongs to a separate MCP such as api-publish.