自动化
工作流自动化与调度
unsloth-hf-jobs
svngoku
Fine-tune LLMs and VLMs using Unsloth on HF Jobs (Hugging Face on-demand cloud GPUs). Use when users want to fine-tune language models, train VLMs (Vision Language Models), do continued pretraining, domain adaptation, or run UV scripts on HF Jobs. Triggers on requests involving Unsloth training, HF Jobs GPU training, Qwen3-VL fine-tuning, Gemma VLM training, or LoRA fine-tuning on cloud GPUs.
web3-forge
sablier-labs
Write Foundry-based tests and scripts. Trigger phrases - foundry testing, write test, fuzz test, fork test, invariant test, deploy script, gas benchmark, coverage, or when working in tests/ or scripts/ directories.
docx
ImGoodBai
"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
good-TTvideo2text
ImGoodBai
"Extract audio from short videos (Douyin/TikTok) and transcribe to text with timestamps. Use when user provides video URL and needs audio transcription."
shortcuts-generator
drewocarr
Generate macOS/iOS Shortcuts by creating plist files. Use when asked to create shortcuts, automate workflows, build .shortcut files, or generate Shortcuts plists. Covers 1,155 actions (427 WF*Actions + 728 AppIntents), variable references, and control flow.
conductor-methodology
rbarcante
Use this skill when the user asks about Conductor concepts, workflow patterns, track lifecycle, plan structures, or context-driven development principles. Also activate when working with conductor/ directory files or when implementing tasks following TDD and verification protocols.
property-based-testing
lv416e
Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing tests, reviewing code with serialization/validation/parsing patterns, designing features, or when property-based testing would provide stronger coverage than example-based tests.
executing-plans
lv416e
"Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches パートナーが完全な実装計画を提供し、レビューチェックポイント付きで制御されたバッチで実行する際に使用 - 計画を読み込み、批判的にレビューし、タスクをバッチで実行し、バッチ間でレビュー報告"
convex
bntvllnt
Build and operate Convex backends: functions (queries/mutations/actions/http actions), schemas, auth patterns, scheduling (cron/scheduled/workflows), file storage, testing, and debugging. Triggers: "convex", "query", "mutation", "action", "httpAction", "schema", "validator", "cron", "schedule", "workflow", "workpool", "ctx.db", "ctx.auth", "convex dev".
prompt-improver
dazuck
Transform any rough prompt, task description, or job into an optimized AI instruction prompt. Use when users ask to "improve this prompt", "make this better for an AI", "optimize this for Claude/GPT", or provide raw instructions that need refinement into a well-structured prompt following best practices.
beads
michalvavra
Persistent task tracking with dependency graphs via bd CLI. Use for multi session work that must survive compaction.
design-frontend
ravnhq
Visual design system patterns for web UIs — layout, responsive, Tailwind
daily-next
BenjaminG
Pick up the next task from today's daily task list and gather full context for working on it. This skill should be used when Benjamin says "next", "next task", "what's next", "pick up task", "start task", or wants context for a specific task ID or Jira key.
team-coordination
duyet
Spawn and coordinate team-agents and orchestration patterns for parallel execution. Use for complex multi-component work.
competing-hypotheses
shhac
Debug problems by investigating multiple hypotheses in parallel. Use when you have a bug, unexpected behaviour, or mystery where the root cause is unclear. Spawns parallel investigator agents each pursuing a different theory, then compares evidence to identify the most likely cause and fix.
task-loop
duyet
Iterative execution methodology. Small steps, verify each, adapt based on results.
claude-prompting
duyet
Prompt engineering guidance for Claude (Anthropic) model. Use when crafting prompts for Claude to leverage XML-style tags, long-context capabilities, extended thinking, and strong instruction following.
orchestration
duyet
Orchestrate complex work through parallel agent coordination. Decompose requests into task graphs, spawn background workers, and synthesize results elegantly. Use for multi-component features, large investigations, or any work benefiting from parallelization.
daily-done
BenjaminG
Mark the current or specified task as done in today's daily task list and show progress. This skill should be used when Benjamin says "done", "task complete", "finished", "mark done", or wants to mark a task as completed.
daily-unblock
BenjaminG
Unblock a task on standby and bring it back to active status. This skill should be used when Benjamin says "unblock", "resume", "unpause", "pick back up", or when a blocked task's dependency has been resolved.
task-decomposition
duyet
Break down complex tasks into parallel workstreams for efficient execution. Use when planning multi-component features, large refactors, or any work that benefits from parallelization.
daily-standby
BenjaminG
Put a task on standby when it's blocked or waiting on someone. This skill should be used when Benjamin says "standby", "waiting on", "put on hold", "blocked", "can't proceed", or needs to park a task that requires external input.
quality-gate
BenjaminG
Run parallel quality reviews (React, SOLID, Security, Simplification, Slop) on branch changes and auto-fix issues
ralph-loop
BenjaminG
Create autonomous iterative loops (Ralph Wiggum pattern) for multi-step tasks. Use when setting up automated workflows that iterate over a backlog of tasks with clear acceptance criteria. Triggers on requests like "create a ralph loop", "set up an iterative agent", "automate this migration", or "create an autonomous loop".