Meta

A sophisticated meta-skill that enables AI agents to autonomously improve their own capabilities through documentation updates and system extensions based on real-world usage patterns.

Extracts and analyzes agent session transcripts to improve or create MCP skills. Provides scripts to locate Claude Code, Pi, and Codex session files and generates structured prompts for skill refinement in fresh sessions. Focuses on identifying confusion patterns and missing documentation from actual usage.

Provides structured guidance for creating Claude Skills with emphasis on context efficiency. Covers skill anatomy, progressive disclosure patterns, and resource organization. Focuses on practical file structure decisions and when to include scripts vs references.

A skill for orchestrating multi-agent workflows by decomposing complex tasks into parallel activities. It generates structured prompts with FOCUS/EXCLUDE templates, validates agent outputs, and manages retry strategies. Useful for coordinating specialist agents and preventing file collisions.

This skill sets a behavioral expectation for Claude to provide direct, unfiltered feedback during code reviews and technical discussions. It explicitly requests blunt honesty when users are wrong, preventing overly polite or non-critical responses. The skill functions as a meta-instruction rather than a tool.

This skill provides a structured framework for managing long-running, multi-step AI agent tasks. It enforces evidence-based delivery with mandatory QAS review gates, clear escalation paths, and checkpoint patterns for state preservation. It's designed to prevent common agent workflow failures like skipping validation or losing context.

Applies test-driven development principles to Claude skill creation. Provides concrete methodology: run scenarios without skill (RED), observe failures, write skill (GREEN), close loopholes (REFACTOR). Includes pressure scenarios, rationalization tables, and bulletproofing techniques.

A meta-skill that applies TDD methodology to skill documentation creation, providing systematic guidance for writing effective, discoverable skills that resist rationalization.

This skill enforces mandatory workflows for AI agents to discover and use other skills before starting any task. It requires checking for relevant skills, announcing usage, and following skill instructions exactly. The skill prevents rationalization and skipping established processes.

A well-structured integration guide that standardizes detective skill usage across plugins, enforcing indexed memory patterns and providing clear role-to-skill mappings for consistent code investigation workflows.

This skill automates the extraction of patterns from Claude session learnings and converts them into reusable artifacts like rules, skills, hooks, or agent updates. It provides a structured 8-step process with frequency thresholds, artifact type decision logic, and concrete file creation templates.

This skill provides a structured framework for developing product positioning strategies. It guides users through category selection, competitive analysis, differentiation identification, and positioning statement creation with clear templates and validation steps. It enforces prerequisite market analysis and includes anti-rationalization patterns to prevent common mistakes.