Best context engineering skills, page 6

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/openclaw-master-skills

Design a scoped multi-agent harness for a requested long-running AI workflow.

AnastasiyaW/codex-claude-code-config

Secret safety for AWS Secrets Manager, secret management, credentials, API keys, tokens, and passwords.

aws/agent-toolkit-for-aws

Add /compact command for manual context compaction. An agent skill from sbusso/claudeclaw.

sbusso/claudeclaw

Builds semantic code indexes, maps dependency graphs, and performs intelligent code search across large codebases.

proffesor-for-testing/agentic-qe

Writes educational Teams channel posts about Claude Code features and best practices, using templates emphasizing concrete examples and underlying principles (e.g.

daymade/claude-code-skills

Run Spec Kitty charter interview, generation, context loading, and synchronization workflows.

spec-kitty/spec-kitty

Inspect Claude Code session JSONL files at ~/.claude/projects/ to extract real conversation telemetry: token counts (input/output/cache reads/cache writes), assistant turn counts, human prompt…

swyxio/skills

Compress tool outputs, logs, and JSON before they enter the context window — structural compression via a deterministic stdlib script (schema + samples + stats instead of 300 raw rows), no API, no…

mohitagw15856/pm-claude-skills

Multi-agent board meeting protocol for strategic decisions. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

Save a compact continuation checkpoint so current work survives context compaction or a later session.

flonat/flonat-research

Handle sensitive data with Claude — PII redaction, conversation management, Use when working with data-handling patterns.

jeremylongshore/tons-of-skills-marketplace

Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy.

jeremylongshore/tons-of-skills-marketplace

Optimize context window usage for OpenRouter models to reduce cost and improve quality.

jeremylongshore/tons-of-skills-marketplace

Understand the components, mechanics, and constraints of context in agent systems.

NeoLabHQ/context-engineering-kit

Context management engine for AI coding agents. An agent skill from borghei/Claude-Skills.

borghei/Claude-Skills

This skill should be used when the user asks about "writing conventions", "codebase context", "HARNESS.md context section", "convention documentation", "how to write enforceable rules", or needs…

Habitat-Thinking/ai-literacy-superpowers

This skill should be used when the user asks about "harness engineering", "what is a harness", "harness framework", "AI code quality", "context engineering", "architectural constraints", "garbage…

Habitat-Thinking/ai-literacy-superpowers

Generate structured session summaries optimized for future AI agent consumption.

aiskillstore/marketplace

MANDATORY agent discovery system for token-efficient agent loading.

sundial-org/awesome-openclaw-skills

Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved questions.

majiayu000/claude-skill-registry

Interactive chat workflows with Gemini CLI including context management, multimodal conversations, and session persistence.

majiayu000/claude-skill-registry

Operational framework for the DAAF orchestrator. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

brycewang-stanford/Auto-Empirical-Research-Skills

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

NeoLabHQ/context-engineering-kit

Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state, context management, verification, recovery, and bounded autonomous loops.

magnus919/agent-skills

建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。

xu-xiang/everything-claude-code-zh

Run and resume the CatGo md-orchestration poll loop — delegate each poll to a subagent (keep main context lean), verify convergence by force, auto-advance each converged species per-species…

Hello-QM/catgo-LRG

Guidance on how to use Claude Code effectively — covering context management, verification strategies, the explore-plan-implement workflow, prompting techniques, session management, parallel…

aiskillstore/marketplace

A skill your agent uses when implementing managing AI conversation context.

thedaviddias/ux-patterns-for-developers

Proactive session capacity monitoring and management for OpenClaw.

LeoYeAI/openclaw-master-skills

Keep the agent's context lean so accuracy doesn't collapse. An agent skill from Archive228/loopkit.

Archive228/loopkit

Designing what information goes into the context window and in what order.

Owl-Listener/ai-design-skills

Compress conversation context — summarize the current session, extract key decisions and facts, then compact history to free up context window.

AlexAI-MCP/hermes-CCC

Debug complex Claude API issues including context window overflow, tool use failures, streaming corruption, and response quality problems.

jeremylongshore/tons-of-skills-marketplace

Manage Cascade context window and memory for complex projects.

jeremylongshore/tons-of-skills-marketplace

Audit token consumption across agents, skills, MCP servers, and rules.

coco-research/coco

Memory is the cornerstone of intelligent agents. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Plan a session's context window like the budget it is — what loads up front, what gets linked instead, what stays fetch-on-demand, and how to keep the stable prefix cache-friendly so repeated turns…

mohitagw15856/pm-claude-skills

Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.

mohitagw15856/pm-claude-skills

Set up or update the agent-first engineering harness for any repository.

pproenca/dot-skills

A skill your agent uses when splitting extracted text into chunks for LLM context windows or RAG ingestion.

hashgraph-online/awesome-codex-plugins

Design or audit what an agent tool returns: shape and trim payloads, paginate, report partial success, reference files and media, and add next-step hints.

hashgraph-online/awesome-codex-plugins

Guide for maintaining the MassGen model and backend registry.

Microck/ordinary-claude-skills

Fetch trending programming models from OpenRouter rankings. An agent skill from MadAppGang/claude-code.

MadAppGang/claude-code

Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window.

sundial-org/awesome-openclaw-skills

A skill your agent uses when a long-horizon task is filling the context window and you must decide what to keep, offload, drop, or hand off to a fresh window — when to compact, what the summary must…

ericrisco/rsc-harness

Optimizes context window via MECW principles and memory tiering.

athola/claude-night-market

覆盖项目级 MEMORY.md 索引、主题文件、MemoryRead/MemoryWrite 工具和压缩后启发式巩固. An agent skill from echoVic/blade-code.

echoVic/blade-code