rlcoach
AI coaching for Rocket League using local replay analysis. Use when the user asks about their Rocket League performance, replays, improvement, or coaching. Covers analysis, comparison, weakness detection, and practice recommendations.
github-insights
|
release-reports
|
pr-writer
|
code-reviewer
|
git-commit
Create git commits with appropriate commit messages. Use when the user asks to commit, create a commit, write a commit message, or mentions "commit" in the context of saving changes to git.
git-worktree
Manage git worktrees and branches. Use when the user asks to create a worktree, new worktree, create a branch, new branch, switch branches, or work on a new feature.
github-pr
Create GitHub pull requests using gh CLI with automatic stacked PR detection. Use when the user asks to create a PR, open a pull request, make a PR, or mentions creating/opening a pull request on GitHub.
test-async-guardian
Flutter/Dart 測試異步資源管理守護者。用於：(1) 診斷測試卡住問題，(2) 審查測試代碼中的異步資源清理，(3) 提供 tearDown 最佳實踐，(4) 掃描潛在的資源洩漏風險。觸發場景：測試卡住、撰寫新測試、Code Review 測試代碼、執行 flutter test 前自動掃描。
ticket-create
Interactive Atomic Ticket design and creation tool following Single Responsibility Principle. Use when: (1) Creating new tickets for development tasks, (2) Breaking down complex requirements into atomic tickets, (3) Creating tickets from test failures, (4) Batch creating multiple tickets from requirements description. Each ticket must have exactly one Action + one Target.
lsp-first
LSP 優先開發策略工具。用於：(1) 查詢 LSP 操作指令, (2) 配置新語言 LSP 插件, (3) LSP vs MCP 工具選擇決策, (4) 自建 LSP 插件指南
version-release
版本發布整合工具，處理 worklog 檢查、文件更新、合併推送等完整流程。三步驟流程：Pre-flight 檢查 → Document Updates → Git Operations。支援 check / update-docs / release 子命令，包含 --dry-run 預覽模式。
ticket-track
Frontmatter-based Ticket tracking system. Provides two core capabilities: (1) READ operations for querying ticket info without loading full files - use query/list/summary commands, (2) UPDATE operations for agents to track progress without reporting back - use claim/complete/release commands. Eliminates need for agents to report progress to main thread.
tech-debt-capture
Automated Phase 4 technical debt capture and Ticket creation. Parses work-log evaluation reports, extracts TD (Technical Debt) items, and creates Atomic Tickets using Single Responsibility Principle. Use: Extract technical debts from Phase 4 evaluation → Auto-map to target versions → Create tickets → Update todolist.
mermaid-generator
根据用户描述智能选择最合适的图表类型并生成 Mermaid 代码。支持流程图、时序图、类图、ER图、甘特图、状态图等全部类型，配色鲜艳美观。
confidence-check
Pre-implementation gate to validate readiness before coding. Use when starting features, fixes, refactors, or making architecture decisions. Triggers on "before implementing", "verify readiness", "should I proceed", "am I ready".
codereview
Deep code review skill for Go code focusing on performance, security, concurrency safety, and readability. Supports reviewing local uncommitted code, recent commits, or specified commits/branches/tags.
technical-content-optimizer
Polish technical blog posts to be more professional, logical, and search-optimized, removing "AI flavor" and ensuring idiomatic code.
prompt-executor
Execute prompts from ./prompts/ directory with various AI models. Use when user asks to run a prompt, execute a task, delegate work to an AI model, run prompts in worktrees/tmux, or run prompts with verification loops.
config-reader
Read and manage daplug configuration from CLAUDE.md using <daplug_config> blocks, with legacy fallback and migration support.
ai-usage
Check AI CLI usage/quota for Claude Code, OpenAI Codex, Google Gemini CLI, and Z.AI. Use when user asks about remaining quota, usage limits, rate limits, or wants to check how much capacity is left.
tmux-manager
Manage tmux sessions for background tasks. Use when user asks about background processes, wants to monitor running tasks, attach to sessions, list active sessions, or kill stuck processes.
worktree
Manage git worktrees for isolated development. Use when user asks to create isolated workspaces, work on multiple branches simultaneously, set up parallel development environments, or clean up old worktrees.
prompt-finder
Find and resolve prompt files in ./prompts/ directory. Use when user asks to find a prompt, list available prompts, locate prompt by number or name, or check what prompts exist.
code-review
Perform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase.
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
design-postgres-tables
Comprehensive PostgreSQL-specific table design reference covering data types, indexing, constraints, performance patterns, and advanced features
commit-push
Commit and push changes with gitmoji-style messages. Triggers on '/commit-push' or phrases like 'commit and push', 'save my changes', 'push this'.
explaining-code
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
sentry
Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.
improve-skill
Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
fal-ai
|
exploring-knowledge-graph
Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.
using-forgetful-memory
Guidance for using Forgetful semantic memory effectively. Applies Zettelkasten atomic memory principles. Use when deciding whether to query or create memories, structuring memory content, or understanding memory importance scoring.
curating-memories
Guidance for maintaining memory quality through curation. Covers updating outdated memories, marking obsolete content, and linking related knowledge. Use when memories need modification, when new information supersedes old, or when building knowledge graph connections.
collaboration
Team collaboration - remote, fetch, pull, push, clone, and team workflows
advanced-git
Advanced Git - interactive rebase, cherry-pick, bisect, reflog, and power user operations
branching
Git branching strategies - create, switch, merge, rebase, and workflows
github-features
GitHub platform features - PRs, issues, actions, projects, and automation
basic-workflow
Daily Git workflow - add, commit, push, pull cycle for everyday development
git-basics
Git fundamentals - init, add, commit, status, log, and core concepts
git-intro
Introduction to Git version control - what, why, and first steps
security-testing
Comprehensive security testing automation for AI/ML systems with CI/CD integration
vulnerability-discovery
Systematic vulnerability finding, threat modeling, and attack surface analysis for AI/LLM security assessments
adversarial-examples
Generate adversarial inputs, edge cases, and boundary test payloads for stress-testing LLM robustness
automated-testing
CI/CD integration and automation frameworks for continuous AI security testing
certifications-training
Professional certifications, CTF competitions, and training resources for AI security practitioners
rag-exploitation
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
benchmark-datasets
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
Page 347 of 409 · 20429 results
