llm-doc-writer
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
Discover Blockchain skills, compare source repositories and read the instructions for each workflow.
Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.
Create, use, and manage Agent Skills for Claude. Use when working with Skills, creating custom capabilities, or understanding how Skills extend Claude's functionality. Covers Skill architecture, file structure,...
Generate growth strategies and ready-to-publish marketing content for product growth. Use when planning launches, assessing product-market fit, creating marketing content, designing experiments, optimizing acti...
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
Maintains SnowTower project documentation, README, and Claude configuration. Use when updating documentation, auditing .claude folder contents, syncing README with actual project state, or reviewing agent/patte...
Generate short video scripts for oral broadcast from article content. Automatically analyzes content and outputs scripts in one of three template types. Outputs style analysis report, system instruction, and re...
実装方針・作業内容の吟味・修正を、ユーザーとAIの会話で行う。ユーザーからの指示があるまでは、勝手にコーディング作業に取りかからない
Generate game assets (sprites, UI icons, backgrounds, tilesets) using DALL-E 3 from a YAML specification file. Use when user asks to create game art, generate sprites, or make game graphics.
A specialized guide for managing Qdrant Cloud collections, optimizing vector schemas for RAG, and executing precise semantic search queries in Python.
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved streaming UX with granular progress updates and source attribution.
Creates new skill YAML definitions in the canonical format. Use when the user wants to create a new skill, command, or workflow for the AI config transpiler.
Design AI characters and personas with structured definitions. Use when creating chatbot personalities, AI assistants, or roleplay characters.
Provides MLflow documentation covering Tracking, Projects, Models, and Registry. Use when the user asks about MLflow features, APIs, implementation, or debugging.
Process audiobooks from the inbox: transcribe to text and organize audio for voice training.
Manage database schema changes with version control. Use when modifying DB schema, adding tables/columns, or setting up new projects. Covers Prisma, Drizzle, and migration best practices.
PostgreSQL database schema, table structures, relationships, and migration rules. Use this skill when working with SQLAlchemy models, Alembic migrations, or database design.
Prepare context for compaction. Run before /compact to ensure critical state survives.
Execute plan in batches with review checkpoints. Use when partner provides a complete implementation plan to execute with controlled batches and architect review between batches.
Resume spec implementation from checkpoint. Use when continuing task-dispatch after context limit or session break.
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
MongoDB database exploration, querying, and debugging using MCP tools. Use when writing aggregation pipelines, analyzing schemas, debugging data issues, or exploring collections in ShipitSmarter databases.
A specialized guide for Serverless Postgres development, enforcing connection pooling, schema-as-code, and MCP-driven database inspection.
Used for resolving schema conflicts by keeping the more recent timestamp
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.