advisor
Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use…
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
$ npx -y skills add cursor/plugins --skill swarm --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/swarmContext preview
The summary Claude sees to decide when to auto-load this skill.
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
name: swarm description: "Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration." disable-model-invocation: true
Fan out N parallel cloud workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.
Open a todolist with one entry per phase before launching anything.
1. Frame 2. Fan out 3. Aggregate 4. Report
1. State the done predicate and the artifact or report the swarm must return. 2. Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare `first pass`, `rank all`, or `best-of` before spawning. 3. Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit. 4. Pick the worker model from `swarm workers` in `~/.cursor/rules/pstack-models.mdc` when present. Otherwise use `grok-4.6-fast-xhigh`. For a model race, name each arm's model up front. 5. Give each worker its own writable output when it writes.
Spawn all N workers in one message with `subagent_type: generalPurpose`, `environment: "cloud"`, `run_in_background: true`, and the configured model. Use `environment: "local"` only when the worker needs access to something on the user's computer.
When a worker must start from a non-default pushed branch, pass `cloud_base_branch`.
Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use `PASS`, `ISSUES`, or `BLOCKED` with evidence.
If a worker drops out, proceed with N-1 and note it.
Read the terminal results. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.
Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.
Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.
Official Cursor plugins for popular developer tools, frameworks, and SaaS products. Each plugin is a standalone directory at the repository root with its own .cursor-plugin/plugin.json manifest.
Repo: cursor/plugins
Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use…
Run the full repository compatibility pass: scanner score, startup path, validation loop, and docs reliability.
Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors,…
Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring. Use when starting a new plugin or adding a plugin to…
Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishing.