Loading...
Loading...
Found 9,243 Skills
执行完整的 7 阶段深度研究流程。接收结构化研究任务，自动部署多个并行研究智能体，生成带完整引用的综合研究报告。当用户有结构化的研究提示词时使用此技能。
Register and manage AI agent identities on Avalanche C-Chain using ERC-8004 (Trustless Agents). Use this skill when the user wants to register an AI agent on-chain, give or read reputation feedback, request validation, or interact with ERC-8004 identity/reputation/validation registries on Avalanche mainnet or Fuji testnet.
Use when syncing contacts or lists to HubSpot CRM. Automatically uses HUBSPOT_API_TOKEN from environment.
ABP Framework cross-cutting patterns including authorization, background jobs, distributed events, multi-tenancy, and module configuration. Use when: (1) defining permissions, (2) creating background jobs, (3) publishing/handling distributed events, (4) configuring modules.
ADHD-optimized task state machine with abandonment detection and interventions. Use when: (1) user initiates any task, (2) providing solutions to problems, (3) detecting context switches, (4) user says "done", "completed", "finished", (5) session ends with pending tasks, (6) >30 minutes since solution provided. Tracks complexity, clarity, domain (BUSINESS/MICHAEL/FAMILY/PERSONAL), and triggers interventions.
Apply Better Stimulus best practices for writing maintainable, reusable StimulusJS controllers following SOLID principles
Kanban methodology including boards, WIP limits, flow metrics, and continuous delivery. Activate for Kanban boards, workflow visualization, and lean project management.
Use when creating interactive maps in Obsidian using LeafletJS plugin - covers real-world maps, image maps, markers from notes, overlays, GeoJSON, GPX tracks, and common issues with bounds/zoom levels
Configures ExDoc for Elixir projects including mix.exs setup, extras, groups, cheatsheets, and livebooks. Use when setting up or modifying ExDoc documentation generation.
Intelligent recommendation system analysis tool that provides implementations of multiple recommendation algorithms, evaluation frameworks, and visual analysis. It requires user behavior data, product information, or rating data for use, supports recommendation algorithms such as collaborative filtering and matrix factorization, and generates personalized recommendation results and evaluation reports.
Debugs the Buttercup CRS (Cyber Reasoning System) running on Kubernetes. Use when diagnosing pod crashes, restart loops, Redis failures, resource pressure, disk saturation, DinD issues, or any service misbehavior in the crs namespace. Covers triage, log analysis, queue inspection, and common failure patterns for: redis, fuzzer-bot, coverage-bot, seed-gen, patcher, build-bot, scheduler, task-server, task-downloader, program-model, litellm, dind, tracer-bot, merger-bot, competition-api, pov-reproducer, scratch-cleaner, registry-cache, image-preloader, ui.
Activate when the user clearly has a skill issue. Generates chaotic, barely-functional code with maximum confidence and sarcastic commentary. Guarantees an infinite loop of attempted fixes that never quite land.