Search
Context engineering
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 193 | 193.Docs Guide Fetch and explain official documentation for any library, framework, API, or service using an llms.txt-first strategy — triggers on "How do I…", "What is…", "How does X work", "Best practice for…"… | fivetaku/ | 128 | — | ~3.5k | Automated safety check: Pass | MIT | 1 mo ago |
| 194 | Memory is the cornerstone of intelligent agents. An agent skill from davila7/claude-code-templates. | davila7/ | 33k | 2 repos | ~577 | Automated safety check: Pass | MIT | today |
| 195 | Implement persistent memory patterns for AI agents using AgentDB. | aiskillstore/ | 433 | 6 repos | ~2.2k | Automated safety check: Pass | No licence | today |
| 196 | 196.Reorient Use mid-task when the working thread is lost — after a context compaction, a long agent run, or coming back to a feature unsure of the role, the current checkpoint, or the next action. | swingerman/ | 154 | — | ~1.5k | Automated safety check: Pass | MIT | 17 days ago |
| 197 | Context window monitoring and budget management. An agent skill from a5c-ai/babysitter. | a5c-ai/ | 1.8k | — | ~1.8k | Automated safety check: Notes | MIT | 23 days ago |
| 198 | 198.Slm Compress Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slmcompress(content, mode, reversible, ttlseconds) to shrink content… | qualixar/ | 230 | — | ~1.6k | Automated safety check: Notes | AGPL-3.0 | today |
| 199 | Configure and optimize .geminiignore files for AI context window efficiency and token cost reduction (FinOps). | sickn33/ | 47k | 1 repo | ~1.4k | Automated safety check: Notes | MIT | yesterday |
| 200 | 当系统提示词需要设计 token 预算分配、上下文压缩策略、延迟加载机制、记忆持久化方案时调用此 Skill。适用于长对话 AI 助手、代码编辑器集成、研究型 Agent、多会话系统等需要精细管理上下文窗口的场景。不适用于:单轮交互系统(无上下文管理需求)、纯无状态 API(无对话历史)、简单的 prompt 模板设计。当需求聚焦于"如何搜索外部信息"而非"如何管理已有信息"时,应该用… | kangarooking/ | 208 | — | ~834 | Automated safety check: Pass | MIT | 5 mo ago |
| 201 | 201.Context Budget エージェント、スキル、MCPサーバー、ルールにわたってClaude Codeのコンテキストウィンドウ消費を監査します。肥大化、冗長なコンポーネントを特定し、優先順位付けされたトークン節約の推奨事項を生成します。 | affaan-m/ | 276k | — | ~981 | Automated safety check: Pass | MIT | today |
| 202 | 202.Evaluation Build evaluation frameworks for agent systems. An agent skill from aiskillstore/marketplace. | aiskillstore/ | 433 | 5 repos | ~2.8k | Automated safety check: Pass | No licence | today |
| 203 | A skill your agent uses when the user asks to "optimize CLAUDE.md", "create a new skill", "write a custom agent", "configure hooks", "manage context window", "set up MCP servers", "scaffold a skill… | borghei/ | 891 | — | ~1.9k | Automated safety check: Pass | MIT | 3 days ago |
| 204 | A skill your agent uses when working with context management context save | aiskillstore/ | 433 | 7 repos | ~1.5k | Automated safety check: Pass | No licence | today |
| 205 | 205.Context Manager Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. | aiskillstore/ | 433 | 7 repos | ~2.1k | Automated safety check: Pass | No licence | today |
| 206 | 206.Board Meeting Multi-agent board meeting protocol for strategic decisions. An agent skill from alirezarezvani/claude-skills. | alirezarezvani/ | 28k | — | ~1.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 207 | This skill should be used when designing prompts, system prompts, or context windows for Claude. | closedloop-ai/ | 122 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | today |
| 208 | 208.Agent Evaluation Evaluate and improve Claude Code commands, skills, and agents. | NeoLabHQ/ | 1.8k | — | ~14k | Automated safety check: Pass | GPL-3.0 | 1 mo ago |
| 209 | Context is the complete state available to a language model at inference time. | aiskillstore/ | 433 | 6 repos | ~3.1k | Automated safety check: Pass | No licence | today |
| 210 | 210.Session Guard A skill your agent uses when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts ignoring rules it followed earlier, when conventions drift… | wshobson/ | 40k | — | ~993 | Automated safety check: Pass | MIT | 5 days ago |
| 211 | 211.Context Surfing Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. | pskoett/ | 315 | — | ~4.7k | Automated safety check: Pass | No licence | 5 days ago |
| 212 | 212.API Error Report Produce a detailed report on APIError events from Agent Monitor data — counts over time, which sessions and models are affected, and the likely root cause (rate limits, overload/529, or… | hoangsonww/ | 1.1k | — | ~750 | Automated safety check: Pass | MIT | today |
| 213 | Configures and verifies an expanded, model-aware context window for OpenAI Codex CLI and Desktop. | daymade/ | 1.4k | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 214 | Decide how to split skill content between SKILL.md and reference files for context efficiency and reliable triggering. | samber/ | 227 | — | ~4.3k | Automated safety check: Pass | MIT | 9 days ago |
| 215 | 215.Agent Workflow A skill your agent uses when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture… | sharpdeveye/ | 591 | — | ~2.1k | Automated safety check: Pass | MIT | 5 mo ago |
| 216 | Manages attention and evidence in long agent sessions. An agent skill from jamditis/claude-skills-journalism. | jamditis/ | 416 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 217 | Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. | mattgierhart/ | 180 | — | ~4.3k | Automated safety check: Notes | MIT | 1 mo ago |
| 218 | Sets up and maintains isolated Claude Code CLI profiles to run Kimi, MiniMax, DeepSeek, GLM, StepFun or Anthropic in separate terminal windows. | daymade/ | 1.4k | — | ~11k | Automated safety check: Pass | MIT | today |
| 219 | Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions. | opsmill/ | 534 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | today |
| 220 | A skill your agent uses when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. | cwinvestments/ | 423 | — | ~1.4k | Automated safety check: Pass | Proprietary | 13 days ago |
| 221 | [omh] Context window or token budget at risk: plan compact context, token/cost budgets, summarization checkpoints, and overflow recovery before long agent work. | rlaope/ | 3.2k | — | ~2k | Automated safety check: Pass | MIT | today |
| 222 | Memory is the cornerstone of intelligent agents. An agent skill from benjaminasterA/antigravity-awesome-skills. | benjaminasterA/ | 375 | 1 repo | ~531 | Automated safety check: Pass | MIT | yesterday |
| 223 | 223.Team Dispatch A skill your agent uses when a request requires multi-agent workflow orchestration (task decomposition + dependency/DAG + parallel execution), needs durable task tracking across context compaction… | LeoYeAI/ | 2.2k | — | ~3.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 224 | 224.Mnemos Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies | alinaqi/ | 707 | — | ~1.8k | Automated safety check: Pass | MIT | 16 days ago |
| 225 | Keeping a design system in an LLM's context: loading tokens compactly, persisting design decisions across sessions, handling multiple variants, and budgeting the context window. | HermeticOrmus/ | 112 | — | ~5k | Automated safety check: Pass | MIT | 5 days ago |
| 226 | 226.Context Surfing Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. | pskoett/ | 315 | — | ~5.8k | Automated safety check: Pass | No licence | 5 days ago |
| 227 | 227.Pi Provider Inspect BB Pi provider support for message editing and context compaction. | get-bb/ | 4.2k | — | ~130 | Automated safety check: Pass | MIT | today |
| 228 | 228.Add Compact Add /compact command for manual context compaction. An agent skill from sbusso/claudeclaw. | sbusso/ | 194 | — | ~1.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 229 | 229.Memory Kit Persistent context management for Claude Code sessions. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~890 | Automated safety check: Pass | MIT | today |
| 230 | 230.Agent Experience A skill your agent uses when writing or changing a model-facing tool definition (name, description, parameter schema, or its system-prompt section), and when designing skills, context loading, or… | singula-ai/ | 109 | 1 repo | ~531 | Automated safety check: Pass | MIT | 11 days ago |
| 231 | Understand the components, mechanics, and constraints of context in agent systems. | NeoLabHQ/ | 1.8k | — | ~13k | Automated safety check: Pass | GPL-3.0 | 1 mo ago |
| 232 | Context optimization extends the effective capacity of limited context windows through strategic compression, masking, caching, and partitioning. | aiskillstore/ | 433 | 3 repos | ~2.2k | Automated safety check: Pass | No licence | today |
| 233 | Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot | aiskillstore/ | 433 | 3 repos | ~2.4k | Automated safety check: Pass | No licence | today |
| 234 | 234.PDF Ingestion Get a PDF into the model without blowing the context window or losing structure. | Archive228/ | 755 | — | ~969 | Automated safety check: Pass | MIT | 2 mo ago |
| 235 | 235.Ghm Self Install Install the PRD-Driven Context Engineering methodology into a fresh OR existing repository — the subscription-native alternative to forking the whole repo. | mattgierhart/ | 180 | — | ~1k | Automated safety check: Notes | MIT | 1 mo ago |
| 236 | 236.Init Seed a fresh (greenfield) repository with the PRD-Driven Context Engineering scaffold — PRD.md, SoT/ knowledge files, EPIC templates, domain-profile config, and agent MEMORY starters. | mattgierhart/ | 180 | — | ~1.2k | Automated safety check: Notes | MIT | 1 mo ago |
| 237 | 237.Daily Task Prep Morning preparation. An agent skill from inbrainfun/inbrain. | inbrainfun/ | 142 | 1 repo | ~399 | Automated safety check: Pass | Unknown | 2 mo ago |
| 238 | Analyze markdown files for token efficiency and reduce context-window bloat. | Azure/ | 134 | — | ~494 | Automated safety check: Pass | MIT | today |
| 239 | A skill your agent uses when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the docadpa Core context, loading a DPACC-compiled DPA app image (docadpaapp), creating DPA… | NVIDIA/ | 3.6k | — | ~5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 240 | 240.Agent Memory 当智能体涉及"memory"与"Context"的操作时触发skill;智能体底层记忆基础设施,完整实现Context Engineering五大核心能力:选择(噪声过滤+相关性筛选)、压缩(因果结构提取+工具结果压缩)、检索(结果重排序+多样性保证)、状态(任务进度追踪+目标对齐)、记忆(冲突检测+跨会话关联);认知模型层支持认知模型构建、因果链提取、知识缺口识别、检索时机决策、质量评估、状态… | LeoYeAI/ | 2.2k | — | ~4.1k | Automated safety check: Pass | MIT | 2 mo ago |