В каталоге 183 730 навыков в 14 категориях.
Manage Discussion entities — structured, multi-turn conversations that explore questions and produce decisions. Use when...
Select and configure a structured discussion protocol matched to the purpose, topic, and group readiness. Use when plann...
Disease-Drug Landscape Analysis - Map the drug landscape for a disease: OpenTargets disease drugs, FDA indications, and...
Disease Knowledge Graph - Build disease knowledge graph: OpenTargets targets, drugs, publications, and phenotypes. Use t...
Skill for populating the `classifications` top-level block of a dismech Disease entry. Covers Harrison's Part assignment...
Use ENCODE functional genomics data for disease mechanism research. Use when the user wants to connect GWAS variants to...
Mine Disease Trajectories (DT/DisTraj) outputs for comorbidity/trajectory candidates, including parsing DT JSON/TSV, ext...
Diseñar las pantallas del producto con Google Stitch (por MCP o pegando el prompt): armar el brief desde la ficha del Ce...
Orienta cualquier trabajo sobre la interfaz de AguaVigía — pantallas, componentes, estilos, animaciones, prototipos o el...
El rol de tester: a partir de una Historia con su Gherkin, armar el plan de pruebas de aceptación: qué Escenarios se aut...
Genera maquetas de alta fidelidad para aplicaciones móviles y web. Traduce requisitos de usuario en wireframes y esquema...
Conjunto de herramientas de diseño experimental que ayuda a investigadores y analistas a planificar estudios proporciona...
Úsalo al definir el holdout de una campaña, al formular su hipótesis, y al interpretar resultados de lift (get_campaign_...
disk reference tool
Mac 智能磁盘清理助手，基于 Mole (https://github.com/tw93/Mole) 的用户友好包装器
扫描磁盘空间占用，找出可安全删除的缓存、编译产物、安装包等，交互式清理释放空间
Scan and clean macOS caches, package-manager data, crash dumps, and app caches to reclaim disk space. Deterministic — a...
Use when df says disk is above 80% full or the user wants to reclaim storage space on a VM.
Analyze disk images and file systems for forensic investigation. Use when investigating data theft, insider threats, mal...
Permanent-delete grooming for leftover Docker builds, agent worktrees, and .next caches. Use when creating or finishing...
Analyze disk space and find cleanable files. Use when user wants to clean disk, free up space, find large files, analyze...
Analyze disk usage across directories, identify large/old directories, and generate storage reports. Use when you need t...
Ante disco lleno (ENOSPC, no space left on device), audita espacio en modo seguro, propone liberación por GRUPOS (origen...
Audit disk usage holistically, explain where storage is going, and rank cleanup candidates by size, reversibility, recen...
Fast utility scanning file resources.
Use when working on the DiskRipper Rust workspace.
Instructions for reviewing a dismech PR, in particular PRs relating to disorder curation, either creating new dismech en...
Conocimiento de fondo sobre los aplazamientos conscientes del MVP y sus disparadores de reapertura (ADR-0015). Cuando la...
Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions
Use when an approved plan exists (plan.md + tasks.md) and you need to execute it. Dispatches subagents per task with two...
Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code. Say 'check with codex' or 'ask gemini fo...
Build queue triage and Codex dispatch. Reads UNIFIED-BUILD-QUEUE.md, triages items into Codex-safe vs Opus-only, writes...
Dispatch agents to GKE Autopilot K8s Jobs or local worktrees for GitHub issues. Use when the user says 'dispatch', 'spaw...
Orchestrate parallel agent dispatch as a manager — not a micromanager. Use when coordinating 2+ independent workers, run...
Use when multiple tasks are ready and you want to assign them to parallel workers
Multi-model CLI orchestrator. Routes tasks to locally-installed AI CLIs (claude, codex, gemini, qwen). Zero Claude token...
Routes hockey analytics requests to the right 2-3 skills. Load this FIRST when a hockey data or analytics request comes...
open issue から自走できるものを選び、対応するセッションを起こす。定期の発火から呼ばれる。
Hand stories from the plan to their lane agents, one per lane, every free lane at once. Picks the ready stories, checks...
多助手协作底座。把活派给其他助手、外部模型会话，或开了后台命令之后用： 管怎么登记、到点怎么查、接单／收到成果／验收完成怎么分开记、没人接怎么办、 开工收工怎么点名、放行后立刻叫开工；只有验收完成或授权取消才退出未完清单。不用于：收回来的东...
Write the structured handoff from a planning session to a coding agent: a dispatch with a header, Gate 0 checks, scope,...
Use in a session with Dispatch tools whenever a design conversation with a person starts: brainstorming or /brainstormin...
Use in any session with Dispatch tools, before planning, filing an issue, asking a human, posting a finding, or starting...
Read the current Round's recommended deployable set, pick the top-priority open package not already in flight, and route...
Use when a task splits into independent sub-parts (several stacks to review, several files to migrate, several leads to...
Dispatch queue pattern for tracking pending tasks across sessions. Use when managing task continuity, understanding pend...
尚书省任务派发规则与调度策略，定义六部派发原则、跨部门协作与并行串行策略
Walks you through pairing your phone with Cowork and sending your first remote task — so you can control your desktop fr...
派發策略檢討工具. Use for: (1) 失敗數超預期 30% 時的策略檢討, (2) 重複分派失敗的分析, (3) 代理人選擇錯誤的修正
Route complex multi-step tasks, multi-skill orchestration, post-execution checklist
Single entry point for all AEM 6.5 LTS Dispatcher skills. Covers config authoring, technical advisory, incident response...
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidat...
Single entry point for all AEM as a Cloud Service Dispatcher skills. Covers config authoring, technical advisory, incide...
Use when implementing features or adding functionality - dispatches incremental-tdd-agent that enforces ONE test at a ti...
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Custom agents built for GH copilot
Launch parallel subagents for independent Godot work — use when 2 or more tasks have no shared files or sequential depen...
The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatch...
Use when deciding whether to dispatch subagents, when to stay in main context, when facing 2+ independent parallel tasks...
This skill should be used when managing "concurrent agent execution", "parallel task processing", "load balancing across...
You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, yo...
Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multip...
Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential depe...
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Dispatch one...
Orquestrar trabalho paralelo com multiplos sub-agents quando ha 2+ tarefas independentes. Usar automaticamente quando de...
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用
Use multiple Claude agents to investigate and fix independent problems concurrently
Use when ≥2 independent tasks exist. Dispatch all in a single message with multiple Agent calls.
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multi...
Enables concurrent subagent workflows for parallel processing
Identify independent failures and spawn concurrent agents. Turns sequential N×time into 1×time.
Use when multiple independent tasks can run simultaneously. Enables efficient parallel work execution with specialized a...
Splits a coding task into independent parallel agent workstreams with disjoint write sets, explicit inputs and outputs,...
Partition and coordinate two or more independent workstreams without duplicating work, leaking expected conclusions, or...
Use when facing 2+ independent investigations that can proceed without shared state - parallel literature survey, multi-...
Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and...
Use when encountering bugs, test failures, unexpected behavior, errors, or performance problems - dispatches systematic-...
Publishes HTML or Markdown as display.dev URLs with public, company, or private access. Supports signup, claiming, shari...
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI to...
Change a Mac's main display resolution in one command: real pixels instead of 4K HiDPI so remote desktop (AnyDesk), scre...
Build display experiences for Meta Ray-Ban Display, choosing between native DAT display integration and standalone Weara...
Displays 0-based collection indices as 1-based numbers in WPF Slider controls. Use when showing user-friendly slice/page...
Displaying charts, dataframes, and metrics in Streamlit. Use when visualizing data, configuring dataframe columns, or ad...
Displays chronological events and activity through timelines, activity feeds, Gantt charts, and calendar interfaces. Use...
Use AgentPMT external API to run the Disposable Email Address tool with wallet signatures, credits purchase, or credits...
Stage a medieval scholastic disputatio over a contested philosophical/textual claim — real combat, not a summary of one....
Locates a live construction dispute on the escalation ladder of the contract in force, names the next required step, the...
Write a letter to dispute an incorrect charge, bill, or record. Use when asked to dispute a credit-card charge, contest...
Generate FCRA-compliant credit dispute letters. Use when Rick says write a dispute letter, dispute this item, or generat...
Prepare and explicitly file an evidence-bound payment dispute response using native receipt proof, approval, provider ex...
Handles disqualified and near-miss inbound leads gracefully. Drafts polite rejection emails, referral requests (right co...
Reverse-engineer any online video into a reusable Markdown blueprint for making new videos in the same format. Takes lin...
Evidence-driven dissection of an existing service, written plan, or codebase area. Interrogates every entity (table, fie...
Reverse-engineer any online video into a reusable, frame-accurate blueprint for making new videos in the same format, an...
Reverse engineering unknown memory blocks and structs using Cheat Engine Structure Dissect, identifying vtables, pointer...
Analyzes bootkit and rootkit samples by identifying boot-process tampering (MBR/VBR/ UEFI), kernel-mode components, and...