В каталоге 182 820 навыков в 14 категориях.
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent...
Audit CLAUDE.md/AGENTS.md for context bloat, duplication, and misplaced guidance. Use when agent docs feel too long, red...
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a `conductor/` di...
Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts,...
Treat project context as a managed artifact alongside code. Use structured context documents (product.md, tech-stack.md,...
Filter and transform tool results before they reach the model — prevent context bloat from large outputs
Autonomous context extraction and structuring for converting unstructured information from multiple sources into AI-inte...
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belie...
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent qua...
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use...
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxe...
This skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowle...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale cont...
Context management engine for AI coding agents. Use when building agent memory systems, optimizing context windows, allo...
Context window optimizer — analyze, audit, and optimize your agent's context utilization. Know exactly where your tokens...
Context engineering and prompt patterns for AI agents
Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200...
Optimize Claude Code context usage through monitoring, reduction strategies, progressive disclosure, planning/execution...
Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to c...
Context engineering knowledge base — context stack architecture (8-layer model), memory engineering (taxonomy, CRUD, con...
Guidance for designing, auditing, and improving context supplied to LLM agents, prompts, tools, RAG/MCP servers, and mul...
Context Engineering — Institutional capability and runbook for context-engineering.
Manages context window for cost, performance, and quality in Claude API workflows and agent sessions. Use when building...
Manage filesystem context for large data offloading, cross-session state persistence, and token optimization. Use when m...
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversati...
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking...
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversa...
Advanced 2026 context curation patterns (Nvidia Eureka, Context Hygiene, RLMF) for autonomous agents.
Use when an agent works in an unfamiliar or information-heavy project, context is limited, or outputs miss local convent...
Workflow for context packets, context audits, compaction, handoffs, session memory, and deciding what AI-agent context t...
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimiz...
Use when managing what an LLM sees. Covers context-window budgeting, retrieval and compaction, memory across turns, tool...
Optimize context windows and token usage for LLM efficiency.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction s...
Master context engineering for AI agents - token optimization, degradation patterns, compression, memory systems, multi-...
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reli...
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent syst...
Optimize context windows, manage token budgets, compress context, and create effective handoff documents for long-runnin...
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting...
Advanced context engineering management system that provides comprehensive context architecture design, memory managemen...
Writes meaningful ai_context values in Crowdin JSONL files for strings that need translator context. Use when extracting...
Specifies rules for managing context files, including the master project context and supplementary files, emphasizing st...
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architecture...
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architect...
Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or wh...
Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding e...
Save working state before compaction or session end for reliable recovery
Creates context handoff documents for session continuity. Use when ending sessions, switching tasks, or handing off work...
Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports,...
Use Context Hub (chub) for curated, versioned API/SDK docs and agent skills. Keep OpenAI tasks on official docs first.
Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixi...
Keep sessions focused and efficient — prune stale outputs, preserve active state, recommend compaction
Nightly context trim for ACTIVE_PRIORITIES and the dated SESSION_LOG schema. Archives before removal, uses content-hash...
Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. U...
Report how much of the session's context window remains. Use when the user asks "how much context is left", "check the c...
Explains how SpecWeave achieves context efficiency through Claude's native progressive disclosure and sub-agent parallel...
ALWAYS activate this skill at the start of every task. Load project context from .claude/ directory including coding rul...
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only...
Manage project context effectively. Use when onboarding, context switching, or maintaining project knowledge. Covers con...
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Features pr...
Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation,...
Use when working with context management context save
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and in...
Audit and manage the full project context landscape: CLAUDE.md memory hierarchy, project documentation, markdown footpri...
Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based mo...
Expert in managing the "Memory" of AI systems. Specializes in Vector Databases (RAG), Short/Long-term memory architectur...
Generates a compressed project context map to avoid expensive Read/Grep calls. Use at session start or before implementi...
Universal context management and planning system. PROACTIVELY activate for: (1) ANY complex task requiring planning, (2)...
Long-term context retention, cross-session memory, and user preference learning
Entry point to the Context Mate toolkit - skills, agents, and commands that work with Claude Code's natural flow. Projec...
Invoke when deciding what to load into context, what to persist across turns or sessions, and what to drop — reads only...
Activate output filtering, session logging, and auto-resume to keep Claude Code sessions running for hours without conte...
Monitors context token usage and warns when approaching limits. Automatically activates when context usage exceeds thres...
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance,...
Optimize context window via MECW principles, memory tiering, and subagent coordination.
Apply compaction, masking, and caching strategies to optimize context windows. Use when reducing token usage or improvin...
Use when managing context window usage, compressing long sessions, or optimizing token usage. Triggers on keywords like...
> [IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. Th...
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency",...
Context optimization extends the effective capacity of limited context windows through strategic compression, masking, c...
Apply compaction, masking, and caching strategies
Strategies for managing Claude Code's context window efficiently: token budgeting, progressive disclosure, reference fil...
Reduce active-session context bloat without losing decisions, errors, evidence, or verification state. Use when tool out...
Use this skill when context is growing quickly or cache consistency drops.
Context Optimization - Orchestrate RPI workflow TODO generation with interactive scoping
Second-pass context optimization that analyzes user prompts and removes irrelevant specs, agents, and skills from loaded...
上下文优化专家。专注于长对话中的上下文管理、token 效率和性能优化。解决 lost-in-middle、context poisoning 等问题，提升 AI 代理在复杂任务中的表现。
Automatically optimizes context window usage when filling up (>70%). Uses hierarchical summarization, selective file loa...
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of...
Parallel historical context gathering using G-4 CONTEXT. Deploy 6 probes to gather all relevant context before complex w...
Solve context fragmentation across Claude sessions. Use when users mention re-explaining themselves, losing conversation...
Proactively preserve critical information before automatic context pruning destroys it.
Generate structured handoff summaries between workflow phases. Use when transitioning between RQPIV phases.
Use when context passes ~60%, a context-percentage alert arrives, or a compaction/respawn decision is needed. PDs above...
Retrieve full pre-compaction conversation history from saved transcript files when the compact summary is insufficient o...
Query past decisions, bets, learnings, and documents by topic
Automatically recover working context after session compaction or when continuation is implied but context is missing. W...
Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recove...