Agent Orchestration
Results
- skill-agent-topology
Before adding another agent, seat, or phase to a workflow that already works.
- ulw-research
Maximum-saturation research orchestration: ALWAYS proposes the final materials first (PDF+DOCX default), then parallel explore+librarian…
- keqian-method
The publisher’s description is only a heading. Open the skill to read what it does.
- agent-coordination
Agent assignment matrix, blocker escalation, and TDM coordination patterns.
- orchestration-patterns
Agentic orchestration patterns for long-running tasks.
- team-coordination
Agent Teams orchestration patterns for multi-agent SAFe workflows.
- scnet-chat
The publisher’s description is only a heading. Open the skill to read what it does.
- ultra-mode
Execute explicitly authorized Ultracode / Ultra Mode requests: optimize for exhaustive, correct answers within the user's stated scope by using any…
- content-illustration-strategy
The publisher’s description is only a heading. Open the skill to read what it does.
- mk:cook
Orchestrates single-task implementation pipeline: plan → test → build → review.
- migration-guide
Turn a breaking change (an API rename, removed flag, changed default, or moved module) into concrete upgrade steps with before/after examples.
- master-debate
The publisher’s description is only a heading. Open the skill to read what it does.
- agent-network
Multi-Agent group chat collaboration system inspired by DingTalk/Lark.
- agent-skill-repository-index
Find and compare Daniel's reviewed GitHub skill sources.
- article-to-infographic
The publisher’s description is only a heading. Open the skill to read what it does.
- audit-code
Run a two-pass, multidisciplinary code audit led by a tie-breaker lead, combining security, performance, UX, DX, and edge-case analysis into one…
- auto-memory
Indestructible agent memory — permanently stored, never lost.
- av-sync-workflow
Audio-to-video synchronization workflow: analyze audio (beats, tempo, emotion, mood), find/match video clips to match scene and feeling, sync cuts to…
- btc-5min-scalper
BTC 5-minute Up/Down paper trading on Polymarket.
- grove
Designing and auditing repository structure for humans and LLM agents: layouts, monorepos, docs/tests/scripts, progressive disclosure,…
- judge
Reviewing code via multi-engine orchestration (Claude + Codex) on three axes — secure, correct, and lean — shipping only findings worth fixing.
- magi
Deliberating decisions and founder priorities through multi-perspective, named-expert, and YC-style advisory lenses.
- summon
Channeling the documented thinking of named notable figures (an 'itako' medium) — their mental models, heuristics, and decision-style as…
- governed-autonomy-loop
Turn any work-queue + any enforcement pipeline into a self-driving, self-healing, human-minimal autonomy loop with a control-systems safety…
- okf-frontmatter
Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF).
- skill-work-slicing
Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces
- catalog-babysitter-users
Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated catalog of those repositories in…
- dp-pattern-library
Maintain and match against a library of classic dynamic programming patterns.
- git-integration
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic,…
- mcp-app-verification
Comprehensive verification checklists for MCP Apps.
- mcp-csp-investigation
Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes.
- mcp-tool-resource-pattern
Implements the core MCP Apps architectural pattern where a Tool declares _meta.ui.resourceUri referencing a registered Resource.
- model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models.
- state-management
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic,…
- template-scaffolding
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic,…
- verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation.
- swarma
Agent teams that run growth experiments and build their own playbook.
- onescience-runtime
The publisher’s description is only a heading. Open the skill to read what it does.
- OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps.
- agentsop-agent-topology-selection
Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent.
- agentsop-bounded-loop
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles.
- agentsop-langgraph
Decision protocol for building, debugging, and operating LangGraph-based agent systems.
- hephaestus-build
1. Treat this as the public Codex build surface. Do not expose or ask the user to invoke the older internal support skill names. 2. Resolve the trusted engine root before reading any build contract:
- agent-teams
Coordinates Claude agent teams via filesystem protocol.
- agent-to-agent
Agent-to-Agent (A2A) communication protocol.
- multi-agent-client-onboarding
Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter.
- loop-orchestration
Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy
- oneskills
The publisher’s description is only a heading. Open the skill to read what it does.
- delegate-team
Complete agentic engineering supersystem — one command orchestrates the entire engineering chain.
- ask
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via omc ask, with artifact capture and no raw CLI assembly
- spring-cloud-gateway
Keep the gateway an edge adapter.
- requirement-convergence
Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure.
- skill-optimization
Evaluates and optimizes skill file quality using 9 content patterns and 10 editing principles.
- subagents-orchestration-guide
Coordinates subagents through scale-based planning, approval, implementation, verification, and escalation flows.
- suede-ship-copy
Suede Labs copy-only orchestration DAG.
- challenge-plans
Before you execute a drafted plan/spec/design doc, run a multi-agent adversarial cross-review to surface the flaws that cause downstream rework,…
- cancel
Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, ultragoal, swarm, ultrapilot, pipeline, team)
- skill-doc-sync
Post-ship doc sync across project markdown.
- model-cost-compare
The user describes a task (bulk refactor, deep review, quick lookup, long-context analysis) and wants the cheapest seat that is still…
- choosing-swarm-patterns
The Agent Relay workflow engine (@relayflows/core) supports 24 swarm patterns via a single swarm.pattern field.
