Навыков: 6 342. Сортировка по числу звёзд.
Write the step-by-step runbook a computer-use or browser agent follows to finish a real online task, such as cancelling...
Execute tasks efficiently with minimal explanations. Deliver results first, explanations only when needed. Optimized for...
Write or revise a paper's Conclusion using recipes distilled from dissecting top ML researchers' papers. Use when drafti...
Write a sincere condolence or sympathy message when someone has died or a friend is grieving — warm, personal, and free...
Complete workflow for evaluating implementation plans before execution with quality checklist and structured feedback
Manage track lifecycle: archive, restore, delete, rename, and cleanup
Create a new track with specification and phased implementation plan
Initialize or resume Conductor project setup. This command creates foundational project documentation through interactiv...
Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help bu...
Sets up or edits the plugin configuration file interactively. Use on first-time setup, when config is missing, or when t...
Ask the user to confirm before taking a significant action. Use before containment, remediation, or other impactful oper...
Confluence Page Generator - Auto-activating skill for Enterprise Workflows.Triggers on: confluence page generator, confl...
Turn any Confluence Cloud instance into a private, searchable AI knowledge base on GitHub with access-tiered repos. Inte...
Scan all CDDs against the entity registry to detect cross-document inconsistencies. Works for both game and product CDDs...
Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.
Constitution Driven Development project governance — establishes, derives, updates, or amends governing principles at an...
Memory-bank governance audit — checks whether T0 laws/current state, T1 supporting context, T2 execution mirrors, adapte...
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on w...
生成ExecSpecMasterConstraints_L*.md权威约束文件，定义Phase/SubPlan/Round命名规范、目录结构、环境策略和质量门禁阈值。当需要创建 ExecSpec Master Plan 的约束文档、定义命名...
Drafts a new skill for a plugin in a marketplace repo, to its guidelines. Use when the user wants a skill written or a w...
Piaget's constructivism, schema theory, and cognitive development as practical tools for curriculum design. Covers assim...
Router skill for classifying Contabo tasks and delegating to the narrowest specialist for cost analysis, capacity planni...
Use when the task is FEA contact, penalty or Lagrange methods, contact stiffness, penetration, friction, stick-slip, mas...
Manage contact information by adding, updating, or validating entries. Use when adding new contacts or updating existing...
Answer questions, assist with planning, and help with design decisions for Mick's off-grid shipping container lake home...
Manage editorial content through 6 pipeline stages.
Automated content discovery workflow for scanning multiple data sources (ArXiv, GitHub, HuggingFace), applying AI-powere...
Move content between platforms, domains, or URL structures while preserving SEO equity, user bookmarks, and integrations...
Use when splitting content work between a raw drafting model/window, an editor-in-chief, and the user's final taste revi...
Log shipped content to the content log. Use when user says "I shipped", "I published", "just posted", or mentions comple...
Use when a user edits or criticizes generated copy and you need to extract durable writing-style rules instead of merely...
Plan sustainment under contested conditions. Use when designing resupply methods, pre-positioning, and distribution resi...
Use this skill to keep value-investing research runs token-efficient through routing, progressive disclosure, and contex...
Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, re...
Use when the user explicitly asks to audit, pack, or configure the context for a task or project, or asks to investigate...
Build the smallest, highest-signal context package for an AI coding task — goal, constraints, repo facts, boundaries, an...
Evaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows.
Teaches you how to break large tasks into stages, save your place between sessions, and recover smoothly when a task get...
Creates a project context map by interviewing the user, exploring connected data sources, and scaffolding project config...
Generate a map of all files relevant to a task before making changes. Works from a short or vague task description: expa...
Keep Claude Code sessions productive across resets with output filtering, session logging, and auto-resume. Use when sta...
Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Us...
Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already p...
Reconstruct where you were and what's next after an interruption, so a broken focus doesn't cost you the whole thread. U...
Continuation format reference for GSD sessions
Resume the last problem-solving session. Use when returning after a break or starting a new conversation.
Continue existing technical or general research from notes, files, URLs, papers, task IDs, or prior reports. Use when ve...