Skills · category
AI & agents skills and plugins
Public Claude skills and plugins for ai & agents, each with Waxell's security verdict and the findings behind it.
- 10,124 reviewed
- 8,025 no issues
- 1,676 to review
- 380 high risk
1,845 resultsAI & agents
compare-showsarcmiraUse Arcmira to compare two YouTube channels or podcasts on YouTube: size, latest episode, topics, overlap and shared sponsors. For rival… Review findingsAI & agentsImages, video & audio33
find-quotesarcmiraUse Arcmira to find exact quotes on YouTube, podcasts included: the line, often who said it, the date, and a timestamped link with clip… Review findingsAI & agentsImages, video & audio33
person-researcharcmiraUse Arcmira to research a person from what they said on YouTube: appearances, their own words with timestamps, who discusses them. For… Review findingsAI & agentsResearch33
podcast-transcript-searcharcmiraUse Arcmira to search podcast transcripts on YouTube for a topic, guest or phrase: which episodes covered it, what was said, and a… Review findingsAI & agentsImages, video & audio33
what-did-they-sayarcmiraUse Arcmira when asked what someone said about something: a person's or company's own words from YouTube, with the show, the date and a… Review findingsAI & agents33
youtube-clip-finderarcmiraUse Arcmira to find the clip: search YouTube transcripts for a moment, get a watch link at the second, start and end seconds, and an embed… Review findingsAI & agentsImages, video & audio33
agent-hooksstarchild-ai-agentManage shell hooks: user scripts that run at agent lifecycle points to block, rewrite, or warn on actions, via the /hooks command. High riskAI & agents33
cli-bridgestarchild-ai-agentManage short-code bundles that authorize the local starchild CLI to talk to this agent, including the agent-shell local-exec channel and… High riskAI & agentsEngineering33
wpsstarchild-ai-agent金山文档(WPS / Kdocs):新建、读取、编辑、搜索、分享、整理在线文档与知识库。 当用户处理在线文档时使用(例如:写周报、网页剪藏到文档、PDF 拆分、AI 生成 PPT、表格美化、接龙转表格)。 High riskAI & agentsDocuments33
ai-podcast101-skillsGenerate multi-person talking head podcast videos from scratch using AI, character creation, TTS, avatar animation, and video stitching.… Review findingsAI & agentsImages, video & audio30
character-design-sheet101-skillsCharacter consistency across AI-generated images with reference sheets and LoRA techniques. Covers turnaround views, expression sheets,… Review findingsAI & agentsDesign30
product-photography101-skillsAI product photography with studio lighting, lifestyle shots, and packshot conventions. Covers angles, backgrounds, shadow types, hero… Review findingsAI & agentsImages, video & audio30
python-sdk101-skillsPython SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh).… High riskAI & agentsEngineering30
inference-sh101-skillsAI agent skills for models via inference.sh CLI - generate images with FLUX, create videos with Veo, call LLMs, search the web, and more High riskAI & agentsImages, video & audio30
academic-research101-skillsSearch and fetch academic papers and archives via inference.sh CLI. Apps: arXiv Search, arXiv Paper, bioRxiv Search, bioRxiv Paper,… Review findingsAI & agentsResearch30
ai-rag-pipeline101-skillsBuild RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT,… Review findingsAI & agentsResearch30
agent-browser101-skillsBrowser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record… Review findingsAI & agentsResearch30
heygen101-skillsHeyGen avatar videos, photo animation, lipsync, video translation, TTS and voice cloning via inference.sh CLI. Apps: heygen/avatar-video… Review findingsAI & agentsImages, video & audio30
image-to-video101-skillsStill-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.7 i2v, Seedance 2.5, Kling v4, Grok… Review findingsAI & agentsImages, video & audio30
agent-ui101-skillsBatteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and… Review findingsAI & agentsDesign30
tools-ui101-skillsTool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results.… Review findingsAI & agentsDesign30
assistant-uiassistant-uiSkills for building AI chat interfaces with the assistant-ui React library Review findingsAI & agentsDesign29
setupassistant-uiInstalls and configures assistant-ui with the `assistant-ui` CLI (`create`, `init`, `add`, `update`, `upgrade`, `codemod`, `doctor`,… Review findingsAI & agentsEngineering29
agentic-workflow-guideaktsmmDesign, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before… High riskAI & agentsProductivity27
ascii-banneraktsmmGenerate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー,… Review findingsAI & agentsDesign27
azure-env-builderaktsmm[Alpha] Experimental Azure environment builder for infrastructure and deployment design. Use when building Azure infrastructure,… High riskAI & agentsDesign27
azure-screenshot-maskaktsmmMosaic environment-sensitive areas (tenant name, user avatar, subscription name / ID, resource group, internal hostnames) on Azure Portal… Review findingsAI & agentsDocuments27
azure-update-customer-pptxaktsmmBuild a customer-facing Azure Update PowerPoint from Azure Updates MCP results, including customer classification, Japan region stamps,… High riskAI & agentsDocuments27
book-writing-workspaceaktsmmOperate a reusable technical book manuscript workspace with writing structure, reader persona SSOT, review rules, and optional Markdown to… Review findingsAI & agentsWriting & content27
customer-workspaceaktsmmSet up dedicated customer workspaces and coordinate meeting notes, actions, and workstreams for ongoing customer accounts. Use for… High riskAI & agentsProductivity27
duck-criticaktsmmRun a Duck Critic producer-critic loop: you (main) keep producing the plan/code/tests and gate your own work at checkpoints with a… Review findingsAI & agentsEngineering27
humanize-writingaktsmmRemove AI-generated tone and make writing sound more human in Japanese and English. Use when reviewing drafts for AIっぽさ, humanizing… Review findingsAI & agentsWriting & content27
opportunity-factoryaktsmmRun a reusable opportunity-to-artifact workflow: discover unmet needs, set up workspace factories, schedule recurring… High riskAI & agentsProductivity27
powerpoint-automationaktsmmCreate a new PPTX from a manuscript, outline, or content.json; convert articles into slides, translate or rebuild a deck, or edit an open… High riskAI & agentsDocuments27
refactor-contextaktsmm指定した instruction / agent / skill の重複・矛盾・冗長性と配置を整理する。単一ファイルや workspace / user 横断のコンテキスト最適化に使い、新規 workflow の設計・構築は扱わない Review findingsAI & agentsEngineering27
refine-product-100aktsmmプロダクトを反復実行で最高品質へ近づける。前回サマリーを読み、重複観点を避けて自律的に改善軸を選び、各回で具体改善・検証・記録まで行う。明示 release mode では品質 gate 後に配布と公開状態確認まで進める Review findingsAI & agents27
retro-private-skillsaktsmmReflect reusable learnings into a private Agent Skills repository, align affected skills' frontmatter with their workflows, keep the… Review findingsAI & agentsEngineering27
retro-useraktsmmReflect verified incident or session learnings into personal Copilot or Codex instructions and configuration. Invoke explicitly for Retro… Review findingsAI & agentsSales & marketing27
retro-workspaceaktsmmReflect reusable learnings into the selected workspace's authorized instructions and automation assets, such as AGENTS.md,… Review findingsAI & agentsProductivity27
review-workflow-runtimeaktsmmワークフロー定義と参照 scripts/hooks/validators を横断し、実行時ロジック・I/O・冪等性・冗長処理・検証ゲートをレビューし、低リスク修正まで行う Review findingsAI & agentsProductivity27
review-workflow-structureaktsmmワークフロー設計資産としての agent / instruction / skill / AGENTS を横断レビューし、SSOT・整合性・構造の問題を検出する Review findingsAI & agentsProductivity27
schedule-managementaktsmmPlan, create, update, and verify personal calendar events across Outlook, Google Calendar, and TimeTree, and propose meeting time windows… Review findingsAI & agentsProductivity27
skill-creator-plusaktsmmCreate or review a reusable skill (SKILL.md) that packages a workflow, and decide whether the request should be a skill instead of a… High riskAI & agentsProductivity27
sync-copilot-customizationsaktsmm~/.copilot の instructions、手動参照メモ、agents を、公開 repo(Agent-Customization)の .github へ安全に同期する。syncToGlobal の分類と機密監査を通し、公開前に差分を提示して承認を取る。skill… Review findingsAI & agentsEngineering27
sync-public-skillsaktsmmSynchronize curated Agent Skills across approved repositories with policy checks and verification. Use when publishing or updating managed… Review findingsAI & agentsEngineering27
tweet-x-csa-microsoftaktsmmX 投稿文(ポスト案・ツイート文)を、日本マイクロソフト CSA の視点でフォーマルに作る。Microsoft / Azure / VS Code / GitHub Copilot の話題向け。ニュース起点は generate-news-x-posts、短文リライトは… Review findingsAI & agentsEngineering27
video-watchaktsmmPrepare video URLs or local video files for GitHub Copilot analysis by extracting captions, sampled frames, contact sheets, and a prompt… Review findingsAI & agentsImages, video & audio27
vscode-extension-guideaktsmmGuide for creating VS Code extensions and plugins from scratch through Marketplace publication. Use when developing a VS Code… High riskAI & agentsDesign27
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF