verification-before-completion
Low Risk 66Verify Before Claiming Completion
by ZhanlinCui
This skill prevents AI agents from making false completion claims by requiring actual verification evidence before reporting success. It ensures tests pass, builds succeed, and work is genuinely complete.
using-superpowers
Safe 73Always Invoke Skills Before Responding
by ZhanlinCui
This meta-skill establishes critical workflow discipline by requiring Claude Code to check for and invoke relevant skills before any response or action, preventing missed opportunities and rationalization.
subagent-driven-development
Safe 70Execute Plans with Subagents and Two-Stage Review
by ZhanlinCui
AI agents often struggle with complex multi-task implementations. This skill solves that by dispatching fresh subagents for each task with mandatory spec compliance and code quality reviews.
slack-gif-creator
Safe 70Create Slack GIFs with PIL
by ZhanlinCui
Create animated GIFs optimized for Slack using Python PIL. Generate custom animations with easing functions and automatic file size optimization for emoji and message contexts.
skill-creator
Safe 80Create custom skills for Claude
by ZhanlinCui
Building effective AI skills requires understanding context management, progressive disclosure, and reusable resource design. This skill provides a complete framework for creating modular skills that extend Claude's capabilities without wasting context window space.
receiving-code-review
Safe 71Handle code review feedback with technical verification
by ZhanlinCui
Code review requires technical evaluation, not emotional performance. This skill provides a structured pattern for verifying review feedback before implementation, ensuring technical correctness over social comfort.
pptx
Safe 75Create and Edit PowerPoint Presentations
by ZhanlinCui
This skill enables AI assistants to create, edit, and analyze PowerPoint presentations by converting HTML to slides, manipulating OOXML directly, and using Python automation scripts for batch operations.
planning-with-files
Safe 80Plan Complex Tasks with Files
by ZhanlinCui
AI agents lose track of goals during long tasks. This skill uses persistent markdown files as external memory so agents can handle complex multi-step projects without losing context.
obsidian-helper
Safe 77Build an Obsidian Note-Taking Assistant
by ZhanlinCui
Manage your Obsidian knowledge base efficiently with automated daily journaling, intelligent knowledge capture, and periodic review generation. Integrates seamlessly with Obsidian MCP for hands-free note management.
obsidian-bases
Safe 70Create and Manage Obsidian Bases
by ZhanlinCui
Organize your Obsidian notes with dynamic database-like views. This skill enables you to create .base files with table, card, list, and map views, complete with filters, formulas, and custom summaries.
notebooklm
Low Risk 72Query NotebookLM Notebooks from Claude
by ZhanlinCui
This skill enables Claude to query Google NotebookLM notebooks directly, providing source-grounded answers from Gemini that cite your uploaded documents, drastically reducing AI hallucinations.
google-official-seo-guide
Safe 71Google Official SEO Guide
by ZhanlinCui
Users struggle to optimize their websites for Google Search without authoritative guidance. This skill provides comprehensive SEO assistance based on official Google documentation, covering crawling, indexing, structured data, and technical SEO best practices.
finishing-a-development-branch
Safe 67Complete a Development Branch
by ZhanlinCui
This skill helps Claude guide developers through finishing a feature branch by verifying tests pass, presenting clear merge/PR/cleanup options, and executing the chosen workflow safely.
executing-plans
Safe 69Execute Implementation Plans with Review Checkpoints
by ZhanlinCui
Transforms written plans into structured execution with built-in review points. Ensures quality through batch processing and architect feedback loops.
dispatching-parallel-agents
Safe 69Dispatch tasks to parallel agents for concurrent execution
by ZhanlinCui
Stop investigating multiple independent problems sequentially and wasting time. This skill teaches you to dispatch one agent per problem domain so investigations happen concurrently.
chat-compactor
Safe 71Generate Session Summaries for AI Continuity
by ZhanlinCui
Lose critical context when sessions end. This skill produces structured handoff documents that preserve decisions, dead ends, and next steps for seamless AI agent continuity.
brainstorming
Safe 72Collaborative Brainstorming for Design
by ZhanlinCui
This skill helps AI assistants turn vague ideas into concrete designs through structured dialogue, ensuring requirements are clear before implementation begins.
ChatCrystal Task Writeback
Safe 69Capture Task Knowledge Automatically
by ZengLiangYi
Lose valuable insights from debugging and implementation sessions. This skill automatically preserves reusable fixes, patterns, and decisions into ChatCrystal memory for future reference.
chatcrystal-task-recall
Safe 73Recall Project Context Before Coding
by ZengLiangYi
Avoid repeating mistakes and forgetting past decisions. This skill automatically recalls relevant project memories, patterns, and pitfalls before you make substantial changes to your codebase.
agent-email-cli
Safe 71Manage Disposable Email Inboxes from Terminal
by zaddy6
Agents need temporary email addresses for verification workflows and testing. This skill provides safe, documented access to the agent-email CLI for creating disposable inboxes, polling for messages, and extracting verification codes.