Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →guaardvark/swarm
Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.
Passed 20 of 20 test cases with the skill, and 12 of 20 without it.
and 6 more in the full report
8 fixed12 passed either way0 still failing0 broke3 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
A swarm run `swarm-332` is generating incorrect code modifications across multiple worktrees and needs to be aborted immediately. What HTTP endpoint stops the running swarm?
| Checked | Without skill | With skill |
|---|---|---|
| The response sends a POST request to /api/swarm/cancel. | Missed | Passed |
The instructions your model reads when the skill loads.
Read setup first; needs the swarm plugin (POST /api/plugins/swarm/start).
B=${GUAARDVARK_URL:-http://localhost:5000}. Status is also the MCP tool swarm_status.
A markdown file in the target repo. Each ## heading is one task. Structured fields are optional;
the parser infers file scope from paths in the prose when they are absent:
# Plan: split the settings page
## Extract the GPU panel
- files: frontend/src/pages/SettingsPage.jsx, frontend/src/components/settings/GpuPanel.jsx
- backend: claude
Move the GPU section into its own component with the same props.
## Add a test for the panel
- files: frontend/src/__tests__/GpuPanel.test.jsx
- depends_on: Extract the GPU panel
backend / assign to picks the agent backend (Claude Code, or a local Cline/OpenClaw agent on
Ollama in Flight Mode). Tasks that touch the same files should depend on each other; the parser
warns about conflicts.
curl -s -X POST $B/api/swarm/launch -H 'Content-Type: application/json' -d '{
"plan_path": "/abs/path/repo/docs/plan.md", "repo_path": "/abs/path/repo",
"max_agents": 4, "auto_merge": false, "flight_mode": false, "dry_run": false,
"acknowledge_dirty_tree": false
}'
acknowledge_dirty_tree: true; tell the user what is
uncommitted first.self_code: true targets Guaardvark's own checkout and is only allowed on the configured root.dry_run: true parses the plan and reports tasks and conflicts without starting agents.test cases passed, vs 12 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.