Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

Apply context-driven testing principles where practices are chosen based on project context, not universal 'best practices'. Use when making testing decisions, questioning dogma, or adapting approaches to specific project needs.

Advanced context engineering management system that provides comprehensive context architecture design, memory management, knowledge engineering, and workflow orchestration through expert collaboration and intelligent tool integration.

Current state of Claude's memory, context, and Skills architecture as of late 2025. LOAD THIS when discussing context engineering, Skills, userMemories, memory management, context portability across surfaces, or troubleshooting why context isn't loading. Contains experimental findings and observed behaviors NOT in training data.

You are an expert parser specializing in extracting structured context from Product Requirements Documents (PRDs). You excel at parsing markdown tables and converting them into machine-readable JSON f

Generate standardized context documentation files (.ctx.md) for systems, APIs, features, and infrastructure. Use when documenting codebases, creating developer context, or when the user mentions documentation, context files, or needs to explain how a system works.

Specifies rules for managing context files, including the master project context and supplementary files, emphasizing stability and change management.

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

Create concise handover summary for seamless continuation in new chat session

Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports, implementing just-in-time context loading, or designing priming hierarchies for agents.

Scan project folder structure, validate organization, clone GitHub repository, and generate an inventory of available materials. First step of writer workflow. Use when starting a new manuscript project.

Explains how SpecWeave achieves context efficiency through Claude's native progressive disclosure and sub-agent parallelization. Use when asking about token usage, context management, or how SpecWeave scales with large projects. Leverages Claude's built-in mechanisms without custom caching.

Universal context management and planning system. PROACTIVELY activate for: (1) ANY complex task requiring planning, (2) Multi-file projects/websites/apps, (3) Architecture decisions, (4) Research tasks, (5) Refactoring, (6) Long coding sessions, (7) Tasks with 3+ sequential steps. Provides: optimal file creation order, context-efficient workflows, extended thinking delegation (23x context efficiency), passive deep analysis architecture, progressive task decomposition, and prevents redundant work. Saves 62% context on average. Essential for maintaining session performance and analytical depth.

Advanced token optimization and context management strategies.

This Skill provides instant orientation for developers using Spec Kit + CCGC integration pipelines. It replaces the need to manually check multiple files (active_context.md, tasks_plan.md, git status)

Bootstrap, maintain, and evolve context networks across their full lifecycle. Use when starting a new project, when existing documentation feels scattered, or when agent effectiveness degrades due to missing context.

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.

Format and structure data files for optimal Claude reasoning and extraction. Use when: (1) Preparing documents/data for Claude analysis, (2) User asks to 'optimize context' or 'format for Claude', (3) Structuring multi-document corpora, (4) Improving LLM retrieval/reasoning over files, (5) Converting data between formats for Claude consumption, (6) User mentions 'lost in the middle' or context window issues. Supports XML, JSON, YAML, CSV, and markdown.

Maintain user and project context across Claude sessions via a structured GitHub-hosted document.

Generate structured handoff summaries between workflow phases.

Automatically save and restore development context to minimize cognitive load when resuming work. Use when switching tasks, taking breaks, or returning after interruptions. Captures mental state, file locations, and next steps. Designed for ADHD developers with high context-switching costs.

Analyze agent-user interaction transcripts to identify context network maintenance needs and guidance improvements. Use after significant agent interactions or to improve context networks.

Review CLAUDE.md files for quality, efficiency, and structure. Use when auditing LLM context files, checking documentation organization, preparing for context optimization, or ensuring lean imperative instructions.

Generate comprehensive context-setting markdown files for coding tasks by intelligently exploring codebase and structuring work with ROLE, CONSTRAINTS, STYLE, file reading order, and structured tasks. Use proactively when the user is starting a complex dev task requiring multiple steps or file reads.

Checks current context window usage and provides recommendations. Use when sessions feel slow, responses seem degraded, or before starting complex work.

Token-efficient context gathering and synthesis from multiple sources (memory, docs, web). Orchestrates MCP tools to build comprehensive context before analysis or interviews. Use when starting discovery, research, or analysis tasks.

context-testing-infrastructure

Update CLAUDE.md files to improve efficiency and structure. Use when optimizing LLM context files, implementing review recommendations, splitting large files, or adding design doc pointers.

Validate CLAUDE.md structure, formatting, and quality. Use when checking context files for compliance, ensuring proper structure, or verifying before commits.

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

Use the local Context7 CLI in this repo to search libraries and fetch Context7 context for skills or documentation tasks. Trigger when you need to run `c7 search`/`c7 context`, resolve library IDs, or retrieve text/json outputs from Context7 via the CLI.

This skill enables fetching up-to-date, version-specific documentation directly from official sources.

Fetch the latest, docs-grounded API details and best practices for a library/framework using Context7 MCP tools `resolve-library-id` and `get-library-docs`. Use when a user asks for “最新用法/最新寫法/最佳實務/latest usage/current best practice/latest API” of a package, or asks how to implement a feature with a library and wants the newest docs-based guidance.

Always use Context7 MCP to fetch up-to-date library/API documentation before generating code that depends on external libraries or config. Use when the user asks for setup steps, configuration, or code involving third-party libraries. Prefer Context7 docs over memory. Include citations to the retrieved docs when possible.

Automatically generates skills from Context7 MCP documentation responses

Access up-to-date, version-specific documentation and code examples from Context7. Use this skill to verify library and framework details.

Contextual Retrieval implementation for RAG - chunks clinical notes with LLM-generated context prepended to each chunk before embedding. Improves citation accuracy by 49% per Anthropic research.

Review pull requests for code quality, security vulnerabilities, best practices, and potential issues. Use when reviewing PRs, examining diffs, or providing code review feedback.

Expert in Continental tradition from Kant through phenomenology, existentialism, structuralism, and post-structuralism

Continuation format reference for GSD sessions

Respond to CEU or professional credit inquiries. Use when a learner asks whether a course qualifies for continuing education credits.

Create or update continuity ledger for state preservation across clears

Apply Google's continuous fuzzing methodology using OSS-Fuzz and ClusterFuzz. Emphasizes coverage-guided fuzzing, automated bug triage, and integration into CI/CD. Use when building robust testing infrastructure or finding security vulnerabilities at scale.

After completing a task, briefly reflect and capture learnings.

Contract review and legal analysis

Review contracts to identify key terms, risks, obligations, and negotiation opportunities

Generate legal contracts from templates with variable substitution and clause management

Author OpenAPI/AsyncAPI specs, contracts, and mocks.

Design and manage API contracts before implementation using OpenAPI and AsyncAPI specifications for contract-first development

Use when asked to generate legal contracts, agreements, or documents from templates with variable substitution and formatting.