Recently Added
Fresh skills just added to the collection. Be the first to try them out!
share--markdown
by alankyshum
Generate a shareable URL for markdown content. Encodes markdown (with mermaid charts, mind maps, gantt charts, interactive tables, pie/bar/line charts, interactive multi-day maps, code blocks, GFM tables, task lists) into a short URL backed by Cloudflare KV (or URL fragment for offline use). The viewer is a Cloudflare Pages SPA with system light/dark theme, OG/Twitter card metadata for rich link previews on social media and Telegram, a floating "Add to LLM" selection menu, build-time lint, and edit-existing support. Use whenever the user wants to share markdown, send a markdown link, make markdown viewable or shareable, render markdown for someone else, create a shareable URL for markdown, publish or preview a markdown file/snippet, give someone a link to a README or notes, update an existing share, or turn markdown into a pretty viewable page. Auto-splits long markdown across multiple URLs when needed.
mbti-agent
by yungzyx
Adapt the coding agent's planning depth, autonomy level, check-in frequency, explanation style, feedback tone, option breadth, ambiguity handling, and closure style to the user's MBTI type. Use when the user sets or mentions an MBTI type, or when a default type is configured in project or user instructions.
slides-on
by T0nyMa
Build presentation slides, PPT, slide decks, 演示文稿, keynotes, 小红书图文, or image cards from any document. Use this whenever the user asks to create slides, 做PPT, 做演示文稿, 做slides, 帮我做个汇报, 整理成图文, 做成小红书, 生成图文, make a deck, generate a PPT, weekly report, pitch deck, 周报, 提案, 分享, or any document-to-slides task — even if they don't say "slides" explicitly (e.g. "帮我整理一下这个文档", "把这篇做成卡片"). One pipeline: content analysis → style decision → review → L0 validation → HTML rendering → L1 QA gate (18 groups) → repair loop → export. QA at every gate: BLOCKER (must fix) / WARN (should review) / INFO (suggestion).
a0_voqualizer
by neurocis
Real-time full-duplex WebSocket ASR/TTS bridge for Agent Zero. Use this skill when the user wants to talk to A0 with voice from browser, mobile, Twilio, Asterisk, or another PCM/VoIP client.
railrun
by ray306
Agent 经常自作主张调整复杂的流程。本 Skill 可通过向 Agent 渐进式披露每个步骤，让 Agent 只能逐步执行当前看到的步骤，以保证流程确定性。
truth-shield
by BAS-More
"Fact-verification layer v3 — catches hallucinations using 10 verification tiers, self-consistency sampling, isolated-context verification (CoVe), package existence checking (DepScope), and multi-judge arbitration. Cross-checks claims against local files, stored knowledge, live docs, web search, multi-model cross-check, and external fact-checkers. Every contradiction is persisted so the same lie is never repeated. MANDATORY TRIGGERS: 'verify this', 'truth-check this', 'fact-check this', 'shield this', 'truth shield', 'truth-shield', 'is this true', 'check your work'. STRONG TRIGGERS: 'are you sure', 'really?', 'source?', 'prove it', 'how do you know', 'is that right', 'double-check that'. PASSIVE MODE: 'shield on' / 'shield off'. Do NOT trigger on opinions, creative writing, brainstorming, or subjective preferences."
gstack
by jkkorn
Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
quoteable-smart-money-meme-scout
by V-SK
"OnchainOS-first quoteable meme scout for the OKX Agentic Wallet Trading Competition. It verifies fresh entry quotes and exit routes, enriches holder/risk evidence, classifies skip/watch/paper candidates, and records auditable paper-only reviews. Triggers: scan market, show candidates, paper trade top candidate, show risk report, show positions, explain decision."
WorldWideBridges.MVP-allmight
by StriveKS
Use sempre que o usuario iniciar, estruturar, desenvolver, validar, otimizar, publicar, vender, entregar ou escalar um projeto, MVP, automacao, site, landing page, conteudo, video, processo comercial ou fluxo operacional. Priorize ferramentas gratuitas, conexoes nativas, Google Drive, GitHub, Apps Script, planilhas, marketing, entrega, memoria operacional e orquestracao entre LLMs.
elephant-goldfish-workflow
by therealr2d2
Implements the Rensin "Elephant and Goldfish" methodology for intent-driven software engineering via persistent planning and zero-context execution.
peat-node
by defenseunicorns
Per-repo skill for the Peat sidecar node — Rust binary that exposes peat-protocol over Connect/gRPC/gRPC-Web for co-located applications, plus Helm/Zarf packaging.
peat-mesh
by defenseunicorns
Per-repo skill for the Peat mesh networking layer — pluggable transport, peer discovery, topology, routing, optional Automerge/Iroh CRDT sync, optional HTTP/WS broker.
skill-oracle
by Aleffsalmeida
Universal Dynamic Orchestrator for Skills, Agents, Plugins, and MCP servers. Single entry point that indexes the full Claude Code ecosystem (5000+ assets), routes user tasks to domain Master Agents, debates ambiguous matches, suggests related domains proactively, and falls back to find-skills when no local match exists. Use as the FIRST step before any non-trivial task; replaces the legacy local-only skill matcher.
moviemonk-ai
by mfscpayload-690
"Full build and safety test workflow for MovieMonk UX/Component changes. Validates that UI modifications maintain type safety, component consistency, responsive behavior, and test coverage before deployment. Runs linting, unit tests, integration tests, and regression checks with automated validation of component consistency patterns. WHEN: after making UI component changes, before deploying UX improvements, validating movie/show/person display consistency, ensuring responsive behavior is preserved, testing ambiguity modal or hero metadata changes."
claude-to-gemini
by rauls-kjarners
Offloads heavy, token-intensive reasoning and search tasks to Gemini via the Agent Client Protocol (MCP). MANDATORY delegation for grep, git diff, git log, large files, multi-file analysis.
kiri-friends-core
by Project-Kiri
Kiri Friends project-specific conventions. Use when implementing watchOS UI, CLIBridge communication, domain models, or iPhone companion features. Triggers on tasks involving the Kiri Friends codebase.
watchos-code-review
by Project-Kiri
Reviews watchOS code for app lifecycle, complications (ClockKit/WidgetKit), WatchConnectivity, and performance constraints. Use when reviewing code with import WatchKit, WKExtension, WKApplicationDelegate, WCSession, or watchOS-specific patterns.
watchos-design-guidelines
by Project-Kiri
Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.
watchOS
by Project-Kiri
watchOS development guidance including SwiftUI for Watch, Watch Connectivity, complications, and watch-specific UI patterns. Use for watchOS code review, best practices, or Watch app development.
coding-agent-workflow
by luosky
用 GitHub label 驱动本机 agent 处理 issue/PR，daemon 自动监听并派工。包含 setup（一次部署到某个项目）、status（查 daemon 状态）、disable（关闭某项目的 daemon）等命令
html-artifact-deliverable
by lzljim
Create a self-contained HTML artifact instead of Markdown when the user asks for a substantial report, plan, comparison, code review, PR writeup, architecture explanation, timeline, diagram-heavy document, visual prototype, slide-like walkthrough, or one-off editor/tool where layout, color, navigation, interaction, checkpoint tracking, or shareability materially improves the result. Use this for Chinese or English deliverables that need to be opened locally as a single .html file or published into a local Node.js artifact server for team viewing and state tracking. Stay in Markdown for short replies, code-only snippets, terminal instructions, durable git-reviewed docs, or content that is mainly plain text.
md-course-report-to-pdf
by Eason412
Convert Chinese Markdown course reports, class papers, or homework reports into polished LaTeX/PDF deliverables using Pandoc, ctexart, Tectonic, local images, Chinese/English font rules, cover pages, table of contents, chapter pagination, GB/T 7714-style references, and final PDF QA.
openclaw_ai_video_editor
by brajendrak00068
OpenClaw AI video editor for natural-language edits: viral clips, captions, vertical video, chroma key, audio cleanup, and MP4 export.
task-split-skill
by relunctance
AI Agent 任务拆解方法论 — 将模糊需求拆解为可执行、可追踪、可验证的工作计划，支持读取 PLAN.md 生成 milestone + subTask