Improve and rewrite user prompts to reduce ambiguity and improve LLM output quality. Use when a user asks to optimize, refine, clarify, or rewrite a prompt for better results, or when the request is about prompt optimization or prompt rewriting.
Edits, rewrites, or improves text for clarity, tone, grammar, or style.
Extract voice patterns from transcripts - speaking style, phrases, vocabulary for authentic author profiles
Consolidate multiple deepresearch results into a single comprehensive report following best practices for iterative processing
Use when designing real-time data processing systems, choosing stream processing frameworks, or implementing event-driven architectures. Covers Kafka, Flink, and streaming patterns.
Review data handling for privacy and retention. Use when a senior developer needs governance validation.
Guidance for using the TiDB Cloud Serverless Driver (Beta) in Node.js, serverless, and edge environments. Use when connecting to TiDB Cloud Starter/Essential over HTTP with @tidbcloud/serverless, or when integrating with Prisma/Kysely/Drizzle serverless adapters in Vercel/Cloudflare/Netlify/Deno/Bun. Use this skill for serverless driver setup and edge runtime guidance.
PyTiDB (pytidb) setup and usage for TiDB from Python. Covers connecting, table modeling (TableModel), CRUD, raw SQL, transactions, vector/full-text/hybrid search, auto-embedding, custom embedding functions, and reference templates/snippets (vector/hybrid/image) plus agent-oriented examples (RAG/memory/text2sql).
Process and validate datasets for training. Use when setting up data pipelines.
Use when designing data pipelines, choosing between ETL and ELT approaches, or implementing data transformation patterns. Covers modern data pipeline architecture.
Use when designing database schemas, need to model domain entities and relationships clearly, building knowledge graphs or ontologies, creating API data models, defining system boundaries and invariants, migrating between data models, establishing taxonomies or hierarchies, user mentions "schema", "data model", "entities", "relationships", "ontology", "knowledge graph", or when scattered/inconsistent data structures need formalization.
Optimize Claude Code skills for token efficiency using progressive disclosure and content loading order. Use when optimizing skills, reducing token usage, restructuring skill content, improving skill performance, analyzing skill size, applying 500-line rule, implementing progressive disclosure, organizing reference files, optimizing YAML frontmatter, reducing context consumption, improving skill architecture, analyzing token costs, splitting large skills, or working with skill content loading. Covers Level 1 (metadata), Level 2 (instructions), Level 3 (resources) loading optimization.
Create meta prompts, meta agents, and meta skills that build other agentic components. Use when scaling agentic layer development, creating generators/templates, or implementing "build the system that builds the system" patterns.
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following January 2026 Anthropic best practices.
Audit current context composition and identify optimization opportunities. Use when context window is overloaded, agents are underperforming, or applying the R&D framework to optimize token usage.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
Template for creating new skills in gptme-contrib. Use this as a starting point when creating your own skills.
Expert guidance for Talon voice control development. Use when creating voice commands, defining actions, writing .talon files, testing Talon config, or debugging Talon issues.
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when editing MCP server files, working with tool/prompt/resource definitions, or discussing LLM tool integrations in Ruby.
Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Apply R&D framework to optimize prompts and context. Use when optimizing context window usage, reducing prompt size, delegating to specialized agents, or applying systematic context management.
Write prompts for orchestrator workflows with phases and aggregation. Use when designing multi-phase workflows, writing agent command prompts, or implementing result aggregation patterns.
