Loading...
Loading...
Found 1,366 Skills
Self-evolving AI agent system with 26 tools, three-layer memory, MCP plugins, and 24/7 self-repair in pure Python.
Expert knowledge for Azure App Testing development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Azure Load Testing with VNets/private endpoints, JMeter/Locust/Playwright, CI/CD pipelines, or Playwright Workspaces, and other Azure App Testing related development tasks. Not for Azure Test Plans (use azure-test-plans), Playwright Workspaces (use azure-playwright-workspaces), Azure DevOps (use azure-devops), Azure App Service (use azure-app-service).
Design and implement lead routing and assignment rules — round-robin, territory-based, score-based, and account-based models. Use when designing how leads get assigned to reps, building routing rules in your CRM, optimizing speed-to-lead, setting up territory assignments, configuring lead queues, or scaling assignment as your team grows. Do NOT use for lead scoring model design (use /sales-lead-score), CRM platform configuration (use /sales-apollo or /sales-salesloft), or marketing-to-sales handoff process (use /revops).
Effectue des revues de code complètes des merge requests GitLab, analysant la qualité du code, la sécurité, les performances et les bonnes pratiques. À utiliser quand l'utilisateur dit « review » ou « code review » ou demande de revoir des merge requests ou d'analyser les changements d'une branche avant fusion.
Open a private GitHub repo to external clients or contractors without making it public. Accepts a mixed list of GitHub usernames and/or email addresses, resolves each to a GitHub account (falling back to an email invitation when the user has no discoverable account yet), and invites them as collaborators with a chosen permission level (default: read-only, sufficient for pulling code and filing issues / PRs). Also supports revoking access and listing current collaborators. Use when the user says "给客户开权限", "share private repo", "invite collaborator", "邀请外部协作者", "grant repo access", "客户要看代码", "revoke access", "撤销访问", "list collaborators", or similar.
Use when Wildix API tokens are needed for x-bees, x-hoppers, or Collaboration 7 — or when tokens are missing, expired, or the user asks to log in, log out, sign out, revoke access, or remove authorization from a Wildix app
Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include "read this aloud", "generate voice for ...", "create a narration of ...", "tts this", "把这段念出来", "做个配音", "合成语音", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys.
Opinionated, evolving constraints to guide agents when building interfaces. Useful for keeping output coherent across many small UI pieces.
Build autonomous self-evolving AI agents with vision-grounded memory that operate computers through a perceive-reason-act cycle
A curated collection of research papers and resources on agentic reasoning for Large Language Models, organized by planning, tool use, search, self-evolution, and multi-agent systems.
Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint.
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.