В каталоге 182 820 навыков в 14 категориях.
Fan out N parallel workers, drain them, and return one report. Use for $swarm, 'swarm this', or parallel coverage, races...
Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoin...
Use when asked to run partitioned parallel coverage or races across isolated workers. Don't use for remote, credential,...
Use when a person asks to swarm, delegate or parallelize work without a plan ('swarm this', 'run a swarm on…', 'get a fe...
Fan out N independent workers, collect their results, and return one report for coverage, races, gauntlets, or explorati...
Parallel task execution using Gemini Flash workers. 200x cheaper than Opus. Use for any parallelizable work to preserve...
Parallel dispatch to all Project Directors in the agency — one-shot status, blocker, or priority check across the entire...
Atomic multi-agent batch execution engine. Executes a single concurrent batch of M Interns via subagent_batch and aggreg...
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architec...
Swarm audit of a repository: Workflow fleet of single-lens Sonnet investigators, adversarial verification, Opus interpre...
Interact with the swarm task board. Use when you need to query existing tasks, check backlog status, create new tasks, o...
Use when agents run together on the project's swarm board: a plan, a task swarm or a brainswarm, as its orchestrator or...
Coordinate multi-agent swarm workflows. Use when working in parallel with other agents, managing shared resources, or or...
Multi-agent coordination patterns for OpenCode swarm workflows. Use when working on complex tasks that benefit from para...
Multi-agent swarm coordination patterns. Orchestrates parallel agent execution, manages agent communication, handles tas...
Exploratory discussion pattern for unsolved problems. Replicate the thinking of Staff+ engineers: "When there's no clear...
Execute a swarm plan wave by wave with filesystem isolation via git worktrees. For each wave, main context decides the s...
Fan-out parallel specialists for concurrent analysis. Dispatch read-only reviewers, researchers, and analyzers against a...
End-of-session orchestration handoff. Wraps current conversation into a structured prompt that spawns a fresh orchestrat...
Initialize a Ruflo swarm and coordinate Codex-native follow-up work
Initialize a multi-agent swarm with anti-drift configuration. Use when starting a complex multi-file task that needs 3+...
Initialize a multi-agent swarm with anti-drift configuration
Map-reduce orchestration. Parallel mappers process input chunks independently, then a dedicated reducer merges all outpu...
Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and ant...
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordina...
Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and e...
Orchestrator workflow for coordinating a team of subagents via task board delegation. Covers the workflow (understand, d...
Orchestrator workflow for coordinating a team of subagents via task board delegation in DM-only mode (no BBS). Covers th...
Event-driven orchestrator workflow for coordinating a team of subagents via task board delegation in DM-only mode (no BB...
Orchestrator workflow for coordinating a team of subagents via task board delegation in DM-only mode (no BBS) with agent...
Orchestrator workflow for coordinating on-demand subagents via task board delegation with dynamic scaling. Workers are s...
Orchestrator workflow for coordinating on-demand subagents via task board delegation in DM-only mode (no BBS) with dynam...
Orchestrator workflow for coordinating on-demand web-research subagents via task board delegation with dynamic scaling.
Ablation variant of swarm-orchestration-dynamic-web with the orchestrator's final-verification / alternative-forcing ins...
Ablation variant of swarm-orchestration-dynamic-web with BOTH the board-review narration (auditor auto-spawn + idle revi...
Orchestrator workflow for coordinating a team of web-research subagents via task board delegation. Covers the workflow (...
Orchestrate multi-bot trading swarms on Pump.fun with persona-driven agents
Pipeline and task-graph orchestration. Sequential stages with dependency edges — linear chain or arbitrary DAG.
Decompose an approved spec into a dependency-ordered swarm plan — one task per component, each with an explicit write_se...
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.
Build a dependency-aware task graph for parallel multi-agent execution. Use when create-plan decomposes work into Tn tas...
Orquestador central y despachador inteligente de enjambres multi-agente con auto-detección contextual y tolerancia a typ...
Swarm reliability watchdog for OpenClaw — validates gateway/channel and every lane, performs bounded recovery, and emits...
Speculative orchestration. Competing implementations in isolated worktrees, evaluated by a judge who selects the winner.
Become the supervisor of a multi-session agent swarm. Use when handed a batch of work (a fixes list, an upgrade plan, QA...
Self-claiming pool orchestration. Workers race to claim tasks from a shared pool, loop until the pool is empty.
Auto-loads when CLAUDE_CODE_IS_TEAM_LEAD environment variable is set. Provides guidance for spawned team-leads on monito...
Auto-loads when CLAUDE_CODE_TEAM_NAME environment variable is set. Provides guidance for Claude Code teammates working i...
Diagnostic and recovery guidance for swarm coordination issues. Use this skill when you encounter 'spawn failed', need t...
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint,...
Runs a long swarm of hundreds to thousands of cheap headless coding workers that drive a large failing-test backlog to g...
SwarmKit SDK development for TypeScript and Python. Use when building applications with SwarmKit to run AI agents (Claud...
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard,...
Configures Sway window manager. Use when user asks about sway keybindings, window rules, outputs, inputs, workspaces, or...
SWC Rust-based JS/TS compiler. Use for fast compilation.
You are an expert in SWC, the Rust-based JavaScript/TypeScript compiler. You help developers replace Babel and Terser wi...
Generate SWC configuration files for high-performance JavaScript/TypeScript compilation. Triggers on "create swc config"...
Diagnose and fix Lingui SWC plugin compatibility errors with Next.js, Rspack, or other SWC runtimes. Use when seeing err...
Manage Southwestern College Recording Arts & Technology teaching workflows - Canvas LMS integration, quiz/question manag...
Apply software-engineering standards when authoring or reviewing project plans, build/spec/PRD documents, architecture R...
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
SWE-bench pipeline for A/B testing Grafema with Claude Code. Use when: (1) running SWE-bench experiments, (2) comparing...
Draw an interactive system architecture or Git-history diagram for a repo. Architecture maps start from existing rendere...
Use when the user has a coding prompt — a feature, bug fix, or refactor — and wants it implemented end to end by a self-...
Improve SWE agent RL via execution-free reward models optimized for three metrics beyond TTS: discriminative ability (AU...
Mentor Swedish language learners by selecting YouTube video clips and podcast episodes by CEFR level and skill (listenin...
Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterat...
Batch-verify PARTIAL build queue items via Playwright. Reads UNIFIED-BUILD-QUEUE.md, filters PARTIAL items needing verif...
Cross-company language sweep via Quartr full-text search — date the adoption curve of a term/phrase across the global tr...
ai-fixable が付いた open Issue を1件ずつ片付け、コミットして close する。人間が `/sweep` と打ったときだけ起動する。
Dig for one problem nobody has noticed yet (a latent bug, silent production error, slow path, or test gap), prove it, fi...
Systematically read an entire codebase to discover quality issues, document findings, then triage them into AgentBoard w...
Detects unnecessary files, identifies unused code, discovers orphaned files, and proposes safe deletions. Used for repos...
Two-phase code quality skill: (1) review codebase for structural smells — file LOC, method LOC, accidental complexity, t...
Detecting unnecessary files, unused code, and orphaned files, and proposing safe deletion. Not for removal execution (Bu...
Bulk-delete uploaded chat sessions from a deployed ace-web, after a report and your approval.
Find orphaned Connect programs, opportunities, payment units, and invites; deactivate or delete the safe ones. Needs a l...
Find orphaned items under ACE's Drive root and trash the ones you approve. Needs a live-set from sweep-live-set.
Hestia's HEAT_INDEX dormant flip skill. Reads HEAT_INDEX.md, finds the cold bottom-20 notes, and sets status:dormant in...
Find orphaned CommCare HQ apps in the ACE domain and soft-delete the ones you approve. Needs a live-set from sweep-live-...
Find orphaned connect-labs workflows, pipelines, synthetic data, and solicitations and clean them up. Needs a live-set f...
Hestia's broken wikilink detection skill. Scans vault notes for [[wikilinks]] that point to non-existent files. Reports...
List every identifier still referenced by visible ACE opps in Drive: the keep-list every orphan sweep diffs against.
Run the three read-mostly vault sweeps for stale tracker items, dormant-note candidates, and broken wikilinks, then appe...
Find orphaned OCS chatbots, pipelines, collections, and sessions and delete per-opp clones; the template is protected. N...
Prune old ACE runs in Drive: keep the newest N per opp and trash the rest after approval.
This Article Describes Sweep Through Your Contacts with Speed and Skill
Hestia's delegation tracker sweep skill. Reads DELEGATION_TRACKER.md, closes finished items, archives stale items beyond...
Turn one reported defect in ffmpeg-skill into the full list of places the same thing happens — naming the defect's class...
Automated EDA comparison reports with target analysis, feature comparison, and HTML report generation for pandas DataFra...
SWI-Prolog-specific tooling, standards, and idioms. Use when working with SWI-Prolog code. Emphasizes relational thinkin...
Write Swift with optionals, value types, protocols, async/await, and actors; manage state in SwiftUI workflows.
Swift language fundamentals (5.10+ / 6.x). Covers optionals, value vs reference semantics, protocols & generics, Swift C...
Write Swift code for iOS/macOS following best practices. Use when developing with SwiftUI, UIKit, or Swift packages. Cov...
Language-specific super-code guidelines for swift.
Swift project layout, XcodeGen, xcodebuild, testing, code signing, and device deployment conventions for native iOS, mac...
Swift programming patterns for iOS and macOS
Design, implement, and review Swift APIs and Apple-platform code. Use when working on .swift files, Swift types, Foundat...