ra-video-wash-pipeline
End-to-end Chinese video washing pipeline. Use when the user provides a Bilibili, Douyin, Xiaohongshu, YouTube, web video URL, or local video file and asks for…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-15 00:13
All skills
253,499 results
logfire-coding-agents
Connect Claude Code or Codex itself to Logfire telemetry, or route a coding agent's model requests through Pydantic AI Gateway. Use for coding-session…
agent-orchestrator-parallel-coding
Orchestrate parallel AI coding agents across git worktrees for autonomous CI fixes, code reviews, and PR management
page-agent-web-automation
Control web interfaces with natural language using Page Agent, a JavaScript in-page GUI agent for browser automation
pixel-agents-vscode
Visualize and manage Claude Code AI agents as pixel art characters in a VS Code extension office interface
codex-hygiene-skill
Audit and tune Codex Desktop context surfaces, tool availability, and token usage through telemetry measurement
harness-update
SELF-MAINTAIN the overstack framework on the user's machine (self-maintain) — migrate the old llmwiki to the harness (case B) or update to the new version (case C). ONE command…
chat
Write correct Sarvam AI chat-completion code (Sarvam-105B, Sarvam-30B) — OpenAI-compatible API, streaming, reasoning mode, and the content=None gotcha. Use…
youtube-marketing
Plan, write, and publish for YouTube and YouTube Shorts. Use when the user wants high-CTR video titles, an SEO description with chapters and links, a…
business-model-auditor
Stress-tests business models to identify scale limitations, bottlenecks, and unit economics gaps using Hormozi frameworks. Triggers when a user asks "can this…
rules-capture
Detects user preferences and workflow rules in conversation and records them in .agents/memory/captured-rules.md for promotion. Use on always/never or…
vee-validate-skilld
Use when writing, reviewing, or debugging Vue.js forms that import vee-validate (useForm, defineField, useField, useFieldArray, Form, Field, FieldArray,…
dws
Manage DingTalk product capabilities (AI tables/calendar/contacts/documents/bots/to-dos/email/AI Minutes/AI apps/approvals/logs/DingTalk Drive, etc.). Use when users need to operate table data, manage schedules and meetings, query contacts, send message notifications, handle approval processes, view AI Minutes summaries, create apps/systems/admin backends/business tools, view daily and weekly reports, or manage DingTalk Drive files.
mobile-security
Mobile application security testing (Android + iOS) mapped to OWASP MASVS/MASTG — static reversing (Flutter AOT, Unity IL2CPP, React Native/Hermes, native…
system
System exploitation testing - Active Directory attacks, privilege escalation (Linux/Windows), and exploit development.
twilio-verify-send-otp
Send and verify one-time passcodes (OTPs) via Twilio Verify over SMS (auto-upgraded to RCS where supported), voice, email, or WhatsApp. Covers creating a…
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js…
agentlens-tracing-instrument
Add Forge AgentLens tracing to Python or TypeScript agents. Use when asked to trace agent turns, model calls, tools, or subagents with Forge or AgentLens.
chemistry-skills
9 chemistry skills. Trigger: chemical structure analysis, reaction prediction, molecular modeling. Design: computational chemistry tools and cheminformatics…
trading_halt_resume_tracker_skill
Track the causes, progress, potential impact, and post-resumption observation framework for trading suspension, temporary suspension, and resumption events. It is suitable for scenarios such as encountering suspension and resumption events, judging the nature of the information, and assessing the risks and opportunities of post-resumption price movements.
clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
jimeng_mcp_skill
Use jimeng-mcp-server for AI image and video generation. Use this skill when the user requests generating images from text, compositing multiple images, creating videos from text descriptions, or animating static images. Supports four core capabilities: text-to-image, image composition, text-to-video, image-to-video. Requires jimeng-mcp-server to be running locally or accessible via SSE/HTTP.
xgent-app-release
Used to publish or troubleshoot XGENT portal releases from the App repository: frontend dist, backend image, manifest, or first-time onboarding. Submit proposals via release-cli and a release token, and handle CI, pending review, and post-release incidents.
zeabur-variables
Use for ALL Zeabur environment variable operations — create, list, update, delete, or troubleshoot. Use when user says "set env var", "add variable", "create…