agent-launcher-orchest…
Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an…
Use to land the winning AgentHub branch, archive the others and clean up worktrees.
Claude Code
$ npx -y skills add alirezarezvani/claude-skills --skill merge --agent claude-code
Codex
$ npx skills add alirezarezvani/claude-skills --skill merge -a codex -y
Cursor
$ npx skills add alirezarezvani/claude-skills --skill merge -a cursor -y
Gemini CLI
$ npx skills add alirezarezvani/claude-skills --skill merge -a gemini-cli -y
GitHub Copilot
$ npx skills add alirezarezvani/claude-skills --skill merge -a github-copilot -y
OpenCode
$ npx skills add alirezarezvani/claude-skills --skill merge -a opencode -y
Windsurf
$ npx skills add alirezarezvani/claude-skills --skill merge -a windsurf -y
name: "merge" description: "Use to land the winning AgentHub branch, archive the others and clean up worktrees." metadata: command: /agenthub:merge
Merge the best agent's branch into the base branch, archive losing branches via git tags, and clean up worktrees.
/agenthub:merge # Merge winner of latest session /agenthub:merge 20260317-143022 # Merge winner of specific session /agenthub:merge 20260317-143022 --agent agent-2 # Explicitly choose winner
If `--agent` specified, use that. Otherwise, use the #1 ranked agent from the most recent `/agenthub:eval`.
git checkout {base_branch}
git merge --no-ff hub/{session-id}/{winner}/attempt-1 \
-m "hub: merge {winner} from session {session-id}
Task: {task}
Winner: {winner}
Session: {session-id}"For each non-winning agent:
# Create archive tag (preserves commits forever)
git tag hub/archive/{session-id}/{agent-id} hub/{session-id}/{agent-id}/attempt-1
# Delete branch ref (commits preserved via tag)
git branch -D hub/{session-id}/{agent-id}/attempt-1python {skill_path}/scripts/session_manager.py --cleanup {session-id}Write `.agenthub/board/results/merge-summary.md`:
---
author: coordinator
timestamp: {now}
channel: results
---
## Merge Summary
- **Session**: {session-id}
- **Winner**: {winner}
- **Merged into**: {base_branch}
- **Archived**: {loser-1}, {loser-2}, ...
- **Worktrees cleaned**: {count}python {skill_path}/scripts/session_manager.py --update {session-id} --state mergedTell the user:
411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.
Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an…
Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds…
Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and…
Use when a graded managed agent should run on a schedule, on an event trigger or on demand ('run it every morning'). Validates…
Use when a managed-agent build sheet is ready to launch ('launch it', 'deploy the agent'). Generates and validates API payloads…
Use when closing out a launched managed agent ('wrap up', 'what do I own now'). Inventories primitives with…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…