Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
windsurf-flows-automation
Create and manage Windsurf Flows for repetitive tasks. Activate when users mention
"windsurf flows", "task automation", "workflow automation", "repetitive tasks",
or "process automation". Handles Flow creation and management. Use when working with windsurf flows automation functionality. Trigger with phrases like "windsurf flows automation", "windsurf automation", "windsurf".
majiayu000/claude-skill-registry 163
-
using-jj
Use when working with Jujutsu (jj) version control for task management and change tracking - provides workflows for examine-commit-work-squash cycle, checkpointing progress, and managing working copies
majiayu000/claude-skill-registry 163
-
worker-cleanup
Remove completed or abandoned worker worktrees and their branches. Use to clean up after workers finish their tasks.
majiayu000/claude-skill-registry 163
-
oauth-automation
Use when OAuth tokens expire frequently, need automatic token refresh, YouTube/Google API integration, or when workflows fail due to expired credentials
majiayu000/claude-skill-registry 163
-
emotion-engine
Manage emotion detection, LED responses, and mood-based automations for Ezra. Use when working on emotional regulation features, smart home responses, or the Chaos Orb.
majiayu000/claude-skill-registry 163
-
triage-workflow
SOC II triage workflow for creating Linear tickets, branches, OpenSpec proposals, commits, and PRs. Use when asked to triage an issue, create a triage ticket, or start SOC II workflow.
majiayu000/claude-skill-registry 163
-
tasknotes
Manage tasks in Obsidian via TaskNotes plugin API. Use when user wants to create tasks, list tasks, query by status or project, update task status, delete tasks, or check what they need to do.
majiayu000/claude-skill-registry 163
-
run-experiment
Execute the complete experimental workflow - model optimization followed by evaluation - for all runs in a scaffolded experiment. Use after scaffold-experiment to submit jobs to SLURM.
majiayu000/claude-skill-registry 163
-
deep-research
Deep research with NotebookLM + web search. Iterative multi-source research with domain boost, source credibility, and post-research artifact generation (podcast, video, slides, quiz). Free alternative to Perplexity/Gemini Pro. Use when user says "/deep-research", "research this", "deep dive into", or "investigate".
majiayu000/claude-skill-registry 163
-
ralph
Autonomous agent for tackling big projects. Create PRDs with user stories, then run them via the CLI. Sessions persist across restarts with pause/resume and real-time monitoring.
majiayu000/claude-skill-registry 163
-
jira
Manages JIRA issues, projects, and workflows using Atlassian MCP. Use when asked to "create JIRA ticket", "search JIRA", "update JIRA issue", "transition issue", "sprint planning", or "epic management".
majiayu000/claude-skill-registry 163
-
performance-profiling
Instruments integration and performance analysis workflows for iOS apps. Use when profiling CPU usage, memory allocation, network activity, or energy consumption. Covers Time Profiler, Allocations, Leaks, Network instruments, and performance optimization strategies.
majiayu000/claude-skill-registry 163
-
implementing-from-task
测试中, 用户明确指定执行 implementing-from-task 时候才执行, 其余情况一律不执行
majiayu000/claude-skill-registry 163
-
agent-project-manager
Expert project manager specializing in project planning, execution, and delivery. Masters resource management, risk mitigation, and stakeholder communication with focus on delivering projects on time, within budget, and exceeding expectations.
majiayu000/claude-skill-registry 163
-
calendar-event-creator
Calendar Event Creator - Auto-activating skill for Business Automation.
Triggers on: calendar event creator, calendar event creator
Part of the Business Automation skill category.
majiayu000/claude-skill-registry 163
-
command-basic-patterns
基本実装パターン（シンプル指示/ステップバイステップ/条件分岐/ファイル参照）を整理し、パターン選定とテンプレート適用を支援するスキル。
選定基準、実装の骨格、検証手順を一貫して整理する。
Anchors:
• The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: コマンド設計 / 目的: 実践的な手順設計パターンの習得
Trigger:
Use when selecting or reviewing basic command patterns, or structuring workflows for simple/step/conditional/file-reference commands.
command basic patterns, simple command, step-by-step, conditional command, file reference
majiayu000/claude-skill-registry 163
-
skills-improve
Capture and apply continuous improvements to Codex CLI skills during regular work. Use when a user wants to refine a skill, add a new skill after repeating a workflow, or keep skills up to date based on recent tasks.
majiayu000/claude-skill-registry 163
-
Project Memory Store
Store project-specific insights and context into file-based memory. Use after completing tasks that reveal important details about THIS codebase. Use when user says "--project-store" or "--learn" (you decide which scope, may use both) or after discovering project-specific patterns. Skip for universal patterns (use coder-memory-store) or routine work.
majiayu000/claude-skill-registry 163
-
task-search
Provides fast, case-insensitive text search across task titles, descriptions, and tags with debounced input, relevance ranking, and highlighted matching text. Uses AND logic for multi-token queries and limits results to top 50 for performance.
majiayu000/claude-skill-registry 163
-
trello-cli-zenoxzx-trello-cli
majiayu000/claude-skill-registry 163
-
claude-workflow
majiayu000/claude-skill-registry 163
-
managing-jira
Creates and manages Jira work items via acli CLI. Use when creating Jira issues, updating tasks, transitioning statuses, adding comments, or querying JQL. For Confluence operations, use managing-confluence instead.
majiayu000/claude-skill-registry 163
-
managing-autonomous-development
Execute enables AI assistant to manage sugar's autonomous development workflows. it allows AI assistant to create tasks, view the status of the system, review pending tasks, and start autonomous execution mode. use this skill when the user asks to create a new develo... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
majiayu000/claude-skill-registry 163
-
workflow-executor-inline
Inline workflow executor for proxy providers (ZenMux, custom API providers).
Executes workflow steps directly in the main context WITHOUT spawning Task subagents.
Use this skill when:
- Running looplia workflows via ZenMux or other proxy providers
- Task subagents fail with "invalid_model" errors
- You need inline execution without context isolation
Architecture: Each workflow step is executed INLINE (no Task tool) - read skill, execute
mission, write output, then proceed to next step. All steps share the main context.
v0.6.6: Created for cross-provider compatibility with ZenMux.
majiayu000/claude-skill-registry 163