Automation
Task automation and scripting
executing-plans
by derKlinke
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Scheduling
by andrueandersoncs
This skill should be used when the user asks about "Effect Schedule", "retry schedules", "repetition", "Schedule.exponential", "Schedule.spaced", "Schedule.recurs", "cron scheduling", "backoff strategy", "schedule combinators", "Effect.repeat", "Effect.retry", "polling", or needs to understand how Effect handles scheduled operations and retry policies.
building-subagents
by memyselfandm
Systematically creates production-ready Claude Code subagents with research, drafting, and refinement phases. Use when you need a new specialized agent for a specific domain or task pattern.
ios-background-processing-diag
by derKlinke
Use for symptom-based background task troubleshooting: task never runs, terminates early, delegate not called, dev/prod mismatch, inconsistent scheduling, launch crash, duplicate runs.
spawn-planning-agents
by eveld
Use when creating implementation plans to research codebase patterns and gather context for planning.
cn-holiday
by deusyu
中国节假日/调休查询 — 查某天是工作日还是休息日、是否调休补班、全年假期安排。 触发词: 节假日, 调休, 补班, 放假, 上班, holiday, workday, 今天上班吗, 明天放假吗, 春节放几天, 国庆放假, 下个工作日, 或任何 "[日期] 是否放假/上班" 格式的输入。
executing-work-items
by memyselfandm
Executes specific work items ad-hoc using AI agents with intelligent dependency analysis and parallelization. Use when you need to implement one or more specific items outside of a formal sprint, or when testing implementation of individual features.
nl2ledger
by deusyu
Natural language bookkeeping — parse Chinese/English expense descriptions and append to QianJi CSV. Trigger phrases: 记账, 记一笔, add expense, spent, 花了, 买了, lunch, dinner, 打车, 咖啡, or any input that looks like "[item] [amount]" or "[amount] [item]".
ios-background-processing-ref
by derKlinke
Complete background task API reference - BGTaskScheduler, BGAppRefreshTask, BGProcessingTask, BGContinuedProcessingTask (iOS 26), beginBackgroundTask, background URLSession, with all WWDC code examples
breaking-down-work
by memyselfandm
Breaks down epics into features and tasks optimized for AI agent execution. Includes structure preparation, parallel codebase analysis, feature sizing, task generation, and dependency mapping. Use when an epic is ready for sprint planning or when a large work item needs decomposition into actionable pieces.
before-spawning-task
by eveld
Use BEFORE using the Task tool. Ensures you select the correct specialized subagent_type instead of generic agents.
ios-background-processing
by derKlinke
Use when implementing BGTaskScheduler, debugging background tasks that never run, understanding why tasks terminate early, or testing background execution - systematic task lifecycle management with proper registration, expiration handling, and Swift 6 cancellation patterns
spawn-research-agents
by eveld
Use when conducting codebase research to orchestrate specialized agents in parallel for comprehensive investigation.
spacy
by G1Joshi
spaCy NLP library with pipelines. Use for text processing.
app-store-reviews
by onatcipli
App Store review analysis, competitor intelligence, and automated response generation for iOS/macOS apps. Use this skill when working with Apple App Store reviews for any of these tasks: (1) Fetching and analyzing customer reviews for your own apps via the App Store Connect API, (2) Fetching competitor app reviews via the public RSS feed or iTunes Search API, (3) Performing sentiment analysis, theme extraction, or bug/feature-request categorization on reviews, (4) Generating context-aware developer replies to customer reviews, (5) Comparing ratings, review sentiment, or feature gaps across competing apps, (6) Tracking rating trends and review volume over time, (7) Producing executive summaries or actionable insight reports from review data, (8) Searching the App Store for apps by name or category, (9) Setting up app-specific reply configurations through an interactive onboarding interview that auto-detects patterns from existing responses.
interface-design
by derKlinke
This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).
task-decomposition
by hieutrtr
Decompose high-level objectives into atomic implementation tasks for Python/React projects. Use when breaking down large features, multi-file changes, or tasks requiring more than 3 steps. Produces independently-verifiable tasks with done-conditions, file paths, complexity estimates, and explicit ordering. Creates persistent task files (task_plan.md, progress.md) to track state across context windows. Does NOT cover high-level planning (use project-planner) or architecture decisions (use system-architecture).
refactor:pytorch
by SnakeO
Refactor PyTorch code to improve maintainability, readability, and adherence to best practices. Identifies and fixes DRY violations, long functions, deep nesting, SRP violations, and opportunities for modular components. Applies PyTorch 2.x patterns including torch.compile optimization, Automatic Mixed Precision (AMP), optimized DataLoader configuration, modular nn.Module design, gradient checkpointing, CUDA memory management, PyTorch Lightning integration, custom Dataset classes, model factory patterns, weight initialization, and reproducibility patterns.
ios-assume-isolated
by derKlinke
Use when needing synchronous actor access in tests, legacy delegate callbacks, or performance-critical code. Covers MainActor.assumeIsolated, @preconcurrency protocol conformances, crash behavior, Task vs assumeIsolated.
cellxgene-census
by hxk622
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
liftosaur-program-creator
by pbantolas
Creates and edits Liftosaur workout programs using Liftoscript. Use for program authoring, exercise/set changes, progression setup (lp/dp/sum/custom), advanced custom progression logic, custom progress/update script debugging, and reuse/template refactors.
deeptools
by hxk622
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
using-superpowers
by hxk622
"开始任何对话时使用 - 确立如何查找和使用技能。在任何响应之前（包括澄清问题）都需要调用 Skill 工具。Use when starting any conversation - establishes how to find and use skills. If a skill might apply (even 1% chance), you MUST invoke it."
scvi-tools
by hxk622
Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.