Daa Agent
- 656 installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
daa-agent is a Dynamic Agentic Architecture skill that creates and adapts learning agents via claude-flow MCP for developers who need agents that evolve from performance metrics and shared knowledge.
About
daa-agent is a ruvnet/ruflo skill for creating Dynamic Agentic Architecture (DAA) agents that go beyond static configurations. It exposes create, adapt, and status flows through MCP tools including daa_agent_create, daa_agent_adapt, daa_learning_status, daa_performance_metrics, and daa_knowledge_share, plus Bash access. Developers use it when agents must adapt behavior from performance data, learn across interactions, and share knowledge with peer agents. The argument hint supports create, adapt, and status modes. Reach for daa-agent when building autonomous research, planning, coding, and iteration agents that improve over time rather than one-shot prompt chains.
- Autonomous multi-step agent for development workflows
- Handles research, planning, coding and iteration without constant prompting
- Runs as a persistent agent skill inside Cursor, Claude Code or similar environments
- Reduces context switching for solo indie builders
- Integrates directly with your existing codebase and tools
Daa Agent by the numbers
- 656 all-time installs (skills.sh)
- +6 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #1,492 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill daa-agentAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 656 |
|---|---|
| repo stars | ★ 67k |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you create self-adapting agents with claude-flow?
Create a dedicated agent that autonomously handles research, planning, coding, and iteration tasks.
Who is it for?
Developers building multi-agent systems who need claude-flow DAA agents that learn, adapt, and share knowledge across runs.
Skip if: Developers who only need a single static prompt or a one-off script without persistent agent learning or MCP orchestration.
When should I use this skill?
User needs agents that adapt from metrics, learn over interactions, or share knowledge via claude-flow DAA MCP tools.
What you get
Configured DAA agent instance, adaptation updates, learning status report, and performance metrics output
- DAA agent configuration
- performance metrics report
By the numbers
- Exposes 5 claude-flow DAA MCP tools: create, adapt, learning status, performance metrics, knowledge share
Files
DAA Agent
Create agents with Dynamic Agentic Architecture that adapt and learn over time.
When to use
When you need agents that go beyond static configurations — agents that adapt their behavior based on performance metrics, learn from interactions, and share knowledge with other agents.
Steps
1. Create agent — call mcp__claude-flow__daa_agent_create with initial configuration and learning parameters 2. Monitor learning — call mcp__claude-flow__daa_learning_status to see adaptation progress 3. Check performance — call mcp__claude-flow__daa_performance_metrics for efficiency and accuracy metrics 4. Adapt — call mcp__claude-flow__daa_agent_adapt to trigger manual adaptation based on feedback 5. Share knowledge — call mcp__claude-flow__daa_knowledge_share to propagate learnings to other agents
DAA vs static agents
| Aspect | Static Agent | DAA Agent |
|---|---|---|
| Behavior | Fixed configuration | Adapts over time |
| Learning | None | Continuous from interactions |
| Knowledge | Isolated | Shared across agents |
| Performance | Constant | Improves with use |
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use daa-agent when agents must evolve from metrics and shared knowledge; static agent configs suffice for fixed one-shot tasks.
FAQ
What MCP tools does daa-agent use?
daa-agent calls claude-flow MCP tools: daa_agent_create, daa_agent_adapt, daa_learning_status, daa_performance_metrics, and daa_knowledge_share. Bash is also allowed for supporting commands.
When should I pick daa-agent over static agents?
daa-agent fits when agents must adapt behavior from performance metrics, learn across interactions, and share knowledge with other agents. Static prompt-only agents do not need Dynamic Agentic Architecture.