Productivity
mission-orchestrator
Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase
Automation
summon
Autonomous orchestrator for manifest work items through the development lifecycle
Productivity
speckit-orchestrator
Orchestrates Spec Driven Development by coordinating spec, plan, and task skills
Automation
cmux
MUST be read ANY time you interact with cmux in ANY way — listing/inspecting/creating/closing cmux workspaces, panes, or surfaces; reading or capturing pane/screen output; sending …
Automation
workflow-automation
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry custom…
General
doncheli-skills
Router to all 43 Don Cheli skills covering token optimization, code-rag, SOLID refactoring, living documentation, captures, stub detection, loop detection, Nyquist validation, sess…
Automation
agenticflow-skills
ALWAYS use this skill when the user mentions AgenticFlow, AF CLI, AI agents, agent workflows, business packs, workforce orchestration, or wants to create/deploy/run AI agents. Also…
Automation
loop-up
Multi-agent loop that auto-corrects multi-stage work: an orchestrator plans and validates upgrades, an implementer executes changes, a read-only observer logs actions, and an inspe…
Automation
dynamic-workflow-packets
Plans and runs large tasks with compact dynamic workflow packets, risk gates, integration, and verification. Use when the user explicitly asks for dynamic workflows, packets, subag…
General
gcp-maestro
GCP Maestro routing skill. Classify the user's GCP task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single special…
Productivity
fleet-economy
Use when orchestrating any non-trivial multi-part task with subagents or model lanes — builds, audits, refactors, research sweeps, migrations — or when deciding which model tier ha…
DevOps
gitmoot
Use Gitmoot for local-first AI agent coordination across repositories, goals, reviews, GitHub PR comments, daemon jobs, stuck jobs, branch locks, agent templates, template capture …
Automation
oh-my-hermes
Multi-agent orchestration skills for Hermes inspired by `oh-my-claudecode` and rebuilt on Hermes primitives. Suite covers deep-research, deep-interview, `ralplan` (Planner → Archit…
Automation
roll-loop
Autonomous BACKLOG executor. Runs on a schedule (hourly via cron or GitHub Actions), scans BACKLOG.md for 📋 Todo items, and routes each to the appropriate skill: US-XXX → roll-buil…
AI / ML
forge-multi-agent
When to spawn subagents versus work inline with patterns including fan-out, sequential, orchestrator/worker, judge/critic, retry-with-fallback, and pipeline. Covers context budget …
Research
jonc-workflow
Orchestrates end-to-end Journal on Communications submissions by sequencing twelve skills across topic framing, writing, validation, audit, three-stage review navigation, revision,…
Automation
zenflow
Multi-agent workflow engine for Go. Declarative YAML workflows; an LLM coordinator routes events through hub-and-spoke mailboxes. Three CLI verbs (flow / goal / agent) cover determ…
Productivity
discourse-coordinator
Orchestrates the discourse skill suite by routing between steel-man-argument, socratic-questioning, toulmin-argument-analysis, logical-fallacy-detector, bad-faith-rhetoric-detector…
Automation
custom-agent-router
Selects interaction mode, capability tier, risk level, task shape, review intensity, and limited redundancy for non-trivial agent work with clear goals, scope, and authority. Guide…
Engineering
diagnose-and-fix-batch
Orchestrates batch debugging from a problem list (.md/.json/.yaml/.txt). Queues unresolved issues, dispatches each to an isolated subagent running diagnose-and-fix through the full…
Automation
overseer
Manages parallel development tracks with a daemon that monitors tmux sessions and escalates wrap-ups at thresholds, restarting only sessions that explicitly declare ready via files…
Productivity
stray-subcards
Fan out parallel sub-cards from the current session via stray spawn, monitor progress with stray subtasks, and relay messages into any sub-card using stray send. Activates on reque…
Automation
power-platform-maestro
Routes Power Platform tasks to the right specialist or team from the catalog. Classifies, dispatches, and synthesizes results without answering directly. Dispatches one agent for f…
DevOps
id-promote
Orchestrates cross-environment promotion by re-running the target environment's delivery loop with re-derived posture, gitops classification, and infra binding; surfaces advisory b…
Research
openai--life-science-research--research-router-skill
Route broad or ambiguous life-sciences research requests to the right skills, normalize core entities, optionally parallelize independent evidence gathering with subagents when ava…
Business
fx-risk-master
Orchestrates end-to-end foreign exchange risk management: exposure calculation, scenario analysis, hedging strategy, execution monitoring, and model recalibration. Integrates fx-ex…
Automation
cto-orchestration
Orchestrates multi-agent development as CTO: dispatches execution and review agents via tmux, drives work from goal docs with watcher monitoring, adversarial review loops, flag gat…
Research
feature-library-scout-fleet
Orchestrates parallel library research across multiple feature problems: derives the problem list, assigns each to a worker for adoption-signal ranking against the project ecosyste…
Automation
ab-scripting-feature-dev
Creates an AgenticBrowser Scripting DSL orchestration for end-to-end feature development: planning, TDD implementation, testing, and lint review. Outputs docs/scripting-features/fe…
Testing
shape-test-plan
Orchestrates stateful phased test rollouts for existing products by writing a durable plan at context/foundation/test-plan.md then sequencing through research, planning, and implem…
DevOps
ai-sdlc-evidence-council
Orchestrates multi-perspective AI reviews of high-impact topics, running simulated or independent reviewer executions to surface evidence-backed agreements, conflicts, proposals, o…
Automation
forge-autopilot
Routes any product, engineering, or SDLC activity to Forge. Trigger on work spanning discovery, planning, execution, review, release, or reporting—including features, bugs, PRDs, e…
Automation
loop-backlog
Autonomous backlog worker that monitors backlog.md and orchestrates both lanes: executes basic-ready tasks in isolated git worktrees, auto-decomposes epics into child tasks, and re…
Engineering
minimal-agent-design
Reference for building minimal, hackable agent harnesses — linear message history over branching state, shell-based tool access over custom abstractions, and subprocess isolation f…
Automation
aspirations-execute
Executes a chosen goal end-to-end: runs precondition checks, intelligent retrieval, memory deliberation, subagent delegation, primary execution, fail-fast handling, archival, and d…
AI / ML
model-orchestration
Enforces model-role and effort policies for all delegation: top-tier model sets direction, reviews specs with multi-persona input, owns improvements and security audits; core work …
Productivity
sherpy-flow
Orchestrates the complete Sherpy planning workflow from requirements through QA-ready delivery. Detects existing artifacts, displays pipeline status, and guides sequential executio…
Automation
d365-maestro
Routes Dynamics 365 work to the right specialist from the catalog. Classifies requests, dispatches single or parallel agents (max 4), and enforces Success by Design gates plus segr…
Content
scheherazade
Meta-orchestrator that drives a shared world-state through iterative worldbuilding, character, and story loops, gated by consistency and quality critics with human checkpoints at c…
General
cc-master-skillsmith
Enforces discipline rules for creating, editing, or reviewing skills—especially orchestration and workflow skills—preventing rationalization of violations under pressure. Triggers …
Automation
bstack
Twenty automation primitives (P1–P20) that convert any agent workspace into a self-operating system: Bridge, Gate, Tickets, Pipeline, Fanout, Bookkeeping, Freshness, Janitor, Wait,…
DevOps
hermes-deploy
Deploy a self-hosted Hermes Agent end-to-end over SSH. Orchestrates install, model, platforms, skills, memory, personality, home channel, autostart, and verification — idempotent, …
DevOps
finalize-release
Runs the complete post-release sequence for TrainLCD MobileApp: tag origin/master, publish GitHub Release with auto-generated notes, and sync dev from master via temporary branch-r…
Automation
wengine
Use the `wengine` CLI to explore, compose, validate, and execute typed workflows from the aceteam-workflow-engine package. Activate when users reference workflows, nodes, value sch…
AI / ML
code-and-llm-collaboration
Designs hybrid pipelines blending deterministic code with LLM calls. Catalogs four proven layering patterns—LLM→Code guard, Code filter→LLM, LLM judge + Code enforce, Code orchestr…
Productivity
feature-workflow-runner
Orchestrates the complete feature lifecycle: refines an FRD draft into polished requirements, decomposes it into traceable PLAN tasks, then executes those tasks sequentially or in …
Automation
forge-delegate
Delegate current-phase implementation from this runtime to another (Claude-SB, Codex-SB, OpenCode-SB, or alternate Forge) under existing phase-lock. Spawns the target CLI with SB_P…
Automation
orchestrating-subagents
Manages subagent delegation: selects agent type, model, and effort level by role (explorer, implementer, reviewer, critic), determines parallel launch counts, crafts scoped prompts…
AI / ML
PolyBrain
Multi-agent, multi-model orchestration skill that decomposes an objective into a JSON task plan, runs research and build subtasks in parallel, then synthesizes and verifies a final…
Automation
light-orchestrator
Orchestrates multi-phase workflows for large tasks by planning pipelines, routing to appropriate skills per stage, and inserting mandatory checkpoints for decisions and handoffs. M…
Productivity
prai-workflow
Orchestrates a full submission lifecycle for PR&AI journal—spanning topic selection, writing, validation, submission, multi-round review, and acceptance—by sequencing 11 supporting…
AI / ML
build-local-context-builder
Orchestrates a multi-agent team (infra-architect, schema-designer, collector-engineer, processor-engineer, integration-qa) to implement the full local-context-builder pipeline from…
Engineering
arib-build
Coordinates a multi-agent engineering effort to deliver a specified goal: decomposes work, dispatches specialists in parallel where possible, integrates results, and verifies befor…
AI / ML
codex-model-routing-team
Routes complex or parallel tasks across multiple models and agents by planning, delegating, integrating, and validating results. Activates for multi-source research, multi-chapter …
Automation
legion
Orchestrates multiple user stories in parallel across a shared repo by creating isolated git worktrees, batching work to respect concurrency limits, and coordinating design gates w…
AI / ML
hermes-evolution-orchestrator
Orchestrates systematic self-evolution by linking an agent's built-in learning loop to a full suite of meta-skills (OODA, self-improver, loop auditor, mental-model updater, experim…
Engineering
expert-analysis
Dispatches parallel subagents, one per domain, to analyze a feature against the codebase. Each expert covers architecture, performance, data/state, UI/UX, security, testing, or bui…
AI / ML
orchestrator-core
Domain-agnostic orchestration kernel for multi-agent systems. Extracts a reusable supervisor layer with context stripping, contract-based dispatch, layered merging, and adversarial…
Web
astro-orchestrator
Routes Astro tasks to the appropriate handler for site builds (components, islands, SSR, content, actions, i18n) or docs/wiki/press-kit publishing. Use when working on Astro projec…
General
cambium-mode
Sets default execution mode for tasks: Solo for quick edits and lookups, or Cambium (orchestrator + councils + approval gate) for substantial work like analysis, research, proposal…
Showing the top 60 of 2,129. See the full list →