parcadeiSkillagent-context-isolation
parcadei/Continuous-Claude/.claude/skills/agent-context-isolation/SKILL.md
Agent Context Isolation
Find the best CLAUDE.md, AGENTS.md and Claude skills
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.
Your trail
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.
Worked for most · soon
parcadeiSkillparcadeiSkillagentica-claude-proxy
parcadei/Continuous-Claude/.claude/skills/agentica-claude-proxy/SKILL.md
Guide for integrating Agentica SDK with Claude Code CLI proxy
parcadeiSkillagentica-infrastructure
parcadei/Continuous-Claude/.claude/skills/agentica-infrastructure/SKILL.md
Reference guide for Agentica multi-agent infrastructure APIs
parcadeiSkillagentica-prompts
parcadei/Continuous-Claude/.claude/skills/agentica-prompts/SKILL.md
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
parcadeiSkillagentica-sdk
parcadei/Continuous-Claude/.claude/skills/agentica-sdk/SKILL.md
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
parcadeiSkillagentica-server
parcadei/Continuous-Claude/.claude/skills/agentica-server/SKILL.md
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
parcadeiSkillagentica-spawn
parcadei/Continuous-Claude/.claude/skills/agentica-spawn/SKILL.md
Spawn Agentica multi-agent patterns
parcadeiSkillagentic-workflow
parcadei/Continuous-Claude/.claude/skills/agentic-workflow/SKILL.md
Agentic Workflow Pattern
parcadeiSkillagent-orchestration
parcadei/Continuous-Claude/.claude/skills/agent-orchestration/SKILL.md
Agent Orchestration Rules
parcadeiSkillast-grep-find
parcadei/Continuous-Claude/.claude/skills/ast-grep-find/SKILL.md
AST-based code search and refactoring via ast-grep MCP
parcadeiSkillasync-repl-protocol
parcadei/Continuous-Claude/.claude/skills/async-repl-protocol/SKILL.md
Async REPL Protocol
parcadeiSkillbackground-agent-pings
parcadei/Continuous-Claude/.claude/skills/background-agent-pings/SKILL.md
Background Agent Pings
parcadeiReads credentialsSkillbraintrust-analyze
parcadei/Continuous-Claude/.claude/skills/braintrust-analyze/SKILL.md
Analyze Claude Code sessions via Braintrust
parcadeiReads credentialsSkillbraintrust-tracing
parcadei/Continuous-Claude/.claude/skills/braintrust-tracing/SKILL.md
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
parcadeiSkillbuild
parcadei/Continuous-Claude/.claude/skills/build/SKILL.md
Workflow orchestrator that chains existing skills for feature development
parcadeiSkillcli-reference
parcadei/Continuous-Claude/.claude/skills/cli-reference/SKILL.md
Claude Code CLI commands, flags, headless mode, and automation patterns
parcadeiSkillcommit
parcadei/Continuous-Claude/.claude/skills/commit/SKILL.md
Create git commits with user approval and no Claude attribution
parcadeiSkillcomplete-skill
parcadei/Continuous-Claude/.claude/skills/complete-skill/SKILL.md
A complete skill for E2E testing
parcadeiSkillcompletion-check
parcadei/Continuous-Claude/.claude/skills/completion-check/SKILL.md
Completion Check: Verify Infrastructure Is Wired
parcadeiSkillcompound-learnings
parcadei/Continuous-Claude/.claude/skills/compound-learnings/SKILL.md
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
Agent instruction files
What are agent instruction files?
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 or AGENTS.md?
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.
What is a skill?
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.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.