One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
nek1987Skillnek1987/auto-agent-harness/.claude/skills/container-management/SKILL.md
Create, manage, and optimize LXC containers in Proxmox. Control container lifecycle, manage resources, and coordinate container deployments across nodes.
nek1987Skillnek1987/auto-agent-harness/.claude/skills/context-compression/SKILL.md
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Often used withbdi-mental-statesmemory-systemhosted-agents
nek1987Skillnek1987/auto-agent-harness/.claude/skills/context-degradation/SKILL.md
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
Often used withbdi-mental-statesadvanced-evaluationhosted-agents
nek1987Skillnek1987/auto-agent-harness/.claude/skills/context-engineering/SKILL.md
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
Often used withusing-agent-skillsconstraint-driven-developmentdeprecation-and-migration
nek1987Skillnek1987/auto-agent-harness/.claude/skills/context-fundamentals/SKILL.md
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
Often used withlong-horizon-promptingbdi-mental-statesadvanced-evaluation
nek1987Skillnek1987/auto-agent-harness/.claude/skills/context-optimization/SKILL.md
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
Often used withlong-horizon-promptingbdi-mental-statesadvanced-evaluation
nek1987Skillnek1987/auto-agent-harness/.claude/skills/contributing-guide-creator/SKILL.md
Create contributing guide creator operations. Auto-activating skill for Technical Documentation. Triggers on: contributing guide creator, contributing guide creator Part of the Technical Documentation skill category. Use when working with contributing guide creator functionality. Trigger with phrases like "contributing guide creator", "contributing creator", "contributing".
nek1987Skillnek1987/auto-agent-harness/.claude/skills/conversation-analyzer/SKILL.md
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
nek1987Reads credentialsSkillnek1987/auto-agent-harness/.claude/skills/cookbook-audit/SKILL.md
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
nek1987Skillnek1987/auto-agent-harness/.claude/skills/cpu-profiler-config/SKILL.md
Configure cpu profiler config operations. Auto-activating skill for Performance Testing. Triggers on: cpu profiler config, cpu profiler config Part of the Performance Testing skill category. Use when configuring systems or services. Trigger with phrases like "cpu profiler config", "cpu config", "cpu".
nek1987Skillnek1987/auto-agent-harness/.claude/skills/crawl4ai/SKILL.md
功能强大的开源网页抓取和数据处理工具，支持6种工作模式，包括截图、PDF导出和智能爬取
nek1987Skillnek1987/auto-agent-harness/.claude/skills/creating-claude-agents/SKILL.md
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
nek1987Reads credentialsSkillnek1987/auto-agent-harness/.claude/skills/creating-claude-hooks/SKILL.md
Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure
nek1987Skillnek1987/auto-agent-harness/.claude/skills/creating-claude-rules/SKILL.md
Use when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like alwaysApply
nek1987Skillnek1987/auto-agent-harness/.claude/skills/creating-financial-models/SKILL.md
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
Steady4 mentions in 2 weeks
9 projects use a version of this
nek1987Skillnek1987/auto-agent-harness/.claude/skills/css-colors/SKILL.md
Instructions on how to add new colors for CSS rules
nek1987Skillnek1987/auto-agent-harness/.claude/skills/css-module-generator/SKILL.md
Generate css module generator operations. Auto-activating skill for Frontend Development. Triggers on: css module generator, css module generator Part of the Frontend Development skill category. Use when working with css module generator functionality. Trigger with phrases like "css module generator", "css generator", "css".
nek1987Skillnek1987/auto-agent-harness/.claude/skills/csv-processor/SKILL.md
Parse, transform, and analyze CSV files with advanced data manipulation capabilities.
nek1987Skillnek1987/auto-agent-harness/.claude/skills/cto-advisor/SKILL.md
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.
Often used withexecuting-plansreceiving-code-reviewrequesting-code-review
nek1987Skillnek1987/auto-agent-harness/.claude/skills/d2-diagram-creator/SKILL.md
Create d2 diagram creator operations. Auto-activating skill for Visual Content. Triggers on: d2 diagram creator, d2 diagram creator Part of the Visual Content skill category. Use when working with d2 diagram creator functionality. Trigger with phrases like "d2 diagram creator", "d2 creator", "d2".
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
