305 skills · sorted by relevance
Build and debug Python agents with Swarms, a framework for coordinating multiple AI agents. Covers tool connections, saved memory, autonomous execution, and workflow choices such as sequential steps, parallel work, specialist delegation, and combined answers.
Monitor a swarm, a group of agents, and receive notifications when its status or agent count changes. A watcher script checks status periodically and streams changes through Monitor; separate tools provide one-time status and health checks.
Runs a long swarm of hundreds to thousands of cheap headless coding workers that drive a large failing-test backlog to green. Failures are clustered by signature, each worker fixes one cluster in its own git worktree, a serial no-regression merge gate lands the fixes, the loop resumes across restarts for hours, and it federates across sibling sessions over git branches when one container's CPU is not enough. Use for "fix these thousands of failing tests with a Haiku swarm", "drive the test suite to green with hundreds of agents", "build this compiler or interpreter against a conformance suite", "launch, relaunch or check in on the swarm loop", "the swarm is stuck, idle or rejecting everything", "parallel agents fixing tests keep hitting merge conflicts and regressions", "add sibling containers to the swarm", or "compare models on the tail the swarm could not fix". Ships the harness, a per-project TOML config, a fake-worker selftest, check-in signals and the 2026-10-12 haiku-cc failure catalogue.
The English summary is being prepared. Showing the original description.
Generate 20,000+ particle swarm simulators in two modes: sandbox (complete Three.js host runtime with gesture controls, security validation, code injection pipeline) and sim (behavior function bodies that position/color particles via a sandboxed API). The AI writes ONLY a function body — the host handles rendering, input, and security. Triggers on particle swarm, swarm simulator, particle behavior, swarm sandbox, gesture particles, 20K particles, particle function body, swarm sim, particle playground.
The English summary is being prepared. Showing the original description.
Coordinate groups of AI agents across multiple GitHub repositories. Analyze dependencies, organize shared updates and refactoring, run tests, and create linked pull requests so related projects can be changed together.
Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller. Coordinator generates swarm-config from user task, then runs K iterations of N parallel ants guided by pheromone state. Universal task space via config (nodes + scoring rule). Triggers on "team swarm", "swarm intelligence", "蚁群".
The English summary is being prepared. Showing the original description.
Track the full Toulmin epistemic ancestry of every claim produced by a multi-agent swarm. Each agent output is tagged with an argument chain (claim / data / warrant / relationship) derived from SwarmTracer spans and LineageEdge records, so operators can zoom into any sub-claim and see precisely which agents asserted it, what triggered each assertion, and how contradictions propagated or were synthesised away. The SwarmTracer pattern — wrapping the SwarmAgentExecutor to capture spans, record messages, and build a lineage graph — is the concrete runtime substrate. Argumentative lineage lifts that graph into the Toulmin vocabulary so reasoning provenance is both machine-queryable and human-interpretable.
The English summary is being prepared. Showing the original description.
Review GitHub pull requests with specialized AI agents that check security, performance, architecture, and coding conventions. Generate actionable comments with suggested fixes, and connect review findings to automated approval or change requests.
Review a GitNexus pull request for production readiness with seven coordinated reviewer agents. Combine their findings and have a final critic check the draft, producing a review without editing code or posting results.
Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically. Use when the user wants several agents on one codebase at once, says "swarm this", or asks about a running swarm, worktrees, or merge status.
The English summary is being prepared. Showing the original description.
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
The English summary is being prepared. Showing the original description.
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
The English summary is being prepared. Showing the original description.
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
The English summary is being prepared. Showing the original description.
Treat tokens as a coding swarm's cost-of-goods-sold and legibility engine while accounting for finite subscription allowance when per-call price is unknown. Covers provider windows, remaining-usage evidence, burn forecasts, preemptive checkpoint/model switching, per-agent budgets, compaction, shared digests, context degradation, and spend metering. Activate on: "token budget", "context budget", "compaction strategy", "briefing as compression", "context rot", "summarization collapse", "COGS for agents", "subscription usage remaining", "five-hour or weekly limit", "burn forecast", "model switch before limit", or "/context-economics-for-agent-swarms". NOT for: memory architecture (use always-on-agent-architecture), single-prompt wording (use prompt-engineer), mechanism-design proofs (use nisan-et-al-2007-algorithmic-game-theory), physical containment (use sandboxed-adversarial-test-harness), or production rebodiment and fencing (use agent-resurrection-and-body-continuity).
The English summary is being prepared. Showing the original description.
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
The English summary is being prepared. Showing the original description.
Coordinate multiple AI agents for research, development, testing, and system analysis. It guides role assignment, communication structures, parallel and sequential tasks, shared memory, progress monitoring, and recovery, bringing separate contributions into reports or coordinated development workflows.
Organize software releases on GitHub, from version suggestions and release notes to testing, builds, and deployment. Coordinate multiple packages or repositories, roll changes out in stages, and configure rollback to restore an earlier release when problems occur.
Review GitHub pull requests, or proposed code changes, with specialized agents covering security, performance, architecture, and style. Generate actionable comments, apply quality thresholds, and coordinate automated review workflows.
Manage GitHub issues, synchronize project boards, and plan sprints, short development cycles. Coordinate multiple AI agents to break work into tasks, assign responsibilities, update progress, and produce reports on completion and blockers.
Create and improve GitHub Actions workflows for automated testing and deployment. Coordinate multiple AI agents to review pull requests, investigate failed runs, scan for security issues, and manage releases across repositories.
Initialize a group of collaborating AI agents by choosing how they connect, allocating resources, and setting up communication. Establish shared-memory rules so agents record progress, share outputs, check dependencies, and signal completion.
Run a ruflo agent on your ruOS cloud desktop through an authenticated connection. Follow its output as it runs, record execution status in ruflo, and release the task claim when the run finishes.
Delegate research, coding, and testing from Claude Code to opencode workers. Run independent tasks in parallel with separate Git working directories, combine findings, track token use, and compare solo execution with coordinated workers.
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
The English summary is being prepared. Showing the original description.