contextstream-workflow
Manage persistent AI memory across sessions with ContextStream MCP.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Manage persistent AI memory across sessions with ContextStream MCP.
Manage dormant local skill templates and attach them to project agents or equipment agents.
Analyze coding-agent session transcripts to discover patterns that could become AGENTS.md rules, skills, or prompt templates. Mines your usage history for automation opportunities across local coding-agent tools.
This skill should be used when the user needs to set up, manage, or troubleshoot MCP API Key authentication and tool usage tracking for this stock data service. Use it when configuring external MCP clients (Claude Code, Cursor) to connect to the data service.
Use when the user asks to discover, browse, search, suggest, recommend, or install agents and agentic resources. Author, validate, or import OASF records; push, sign, and publish records; discover, search, browse, suggest, or recommend agents like MCP servers, A2A agents, or agent skills; verify signatures, name ownership, or security scans; synchronize data between servers; or install/uninstall agents and agentic resources into coding agents like VS Code Copilot, Claude Code, or Cursor.
Browse all global and local Claude Code config files (settings.json, settings.local.json, CLAUDE.md), audit them for issues, percolate recurring local patterns into the global config, and review past session transcripts for tool calls denied by the sandbox or allow/deny rules to propose allowlist refinements.
Design and create AI agent packages — manifest format, directory structure, file writing workflow
Honey for plain Claude — the terse-prose core with no agent-harness features. Paste into a claude.ai Project's custom instructions, a Style, or an API system prompt. Strips filler, hedging, and pleasantries from every response while keeping facts, names, numbers, steps, and code exact. No tools required.
Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3). Use when a task is search-heavy or review-heavy, spans many files, or you want to keep the orchestrator's context small. Not for trivial one-file work.