ai-orchestration skills

395 tagged ai-orchestration, measured the same way as everything else here.

Browse within: agent-framework 76coding-assistant 60AI Safety 57Multi-Agent 56ai-for-cybersecurity 51copilot 47multi-agent-system 43bugbounty 41devtools 27governance 27tmux 27agent-fleet 26agent-infrastructure 26agent-orchestrator 26

flow-deliver

01

nyldn/claude-octopus

Skill Claude CodeCodex

Part of octo

Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase).

4.0k +9 3d ago A 23 tokens original MIT

flow-develop

02

nyldn/claude-octopus

Skill Claude CodeCodex

Part of octo

Multi-AI implementation using available external providers (Double Diamond Develop phase).

4.0k +9 3d ago A 0 tokens original MIT

flow-discover

03

nyldn/claude-octopus

Skill Claude CodeCodex

Part of octo

Multi-AI research using available external providers (Double Diamond Discover phase).

4.0k +9 3d ago A 0 tokens original MIT

bernstein-agents

04

sipyourdrink-ltd/bernstein

Skill Claude CodeCodex

Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.

1.0k +2 2d ago A 49 tokens original Apache-2.0

bernstein-plan

05

sipyourdrink-ltd/bernstein

Skill Claude CodeCodex

Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.

1.0k +2 2d ago A 51 tokens original Apache-2.0

bernstein-run

06

sipyourdrink-ltd/bernstein

Skill Claude CodeCodex

Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its…

1.0k +2 2d ago A 75 tokens original Apache-2.0

DemonDamon/AgenticX

Skill Claude CodeCodexCursor

Use when scanning an arbitrary Git repository to create, refresh, or selectively update Markdown summaries of code modules, especially when changes must be traced from each module's last successful update.

219 3d ago A 41 tokens original Apache-2.0

DemonDamon/AgenticX

Skill Claude CodeCodex

Guide for using the A2A (Agent-to-Agent) communication protocol in AgenticX including agent discovery, skill invocation, remote agent cards, and distributed agent systems. Use when the user wants agents to communicate with each other, set up distributed agent systems, invoke remote agent skills, or build…

219 3d ago A 73 tokens original Apache-2.0

DemonDamon/AgenticX

Skill Claude CodeCodex

Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.

219 3d ago A 49 tokens original Apache-2.0

cas-search

10

codingagentsystem/cas

Skill Claude CodeCodex

Search across CAS content (memories, tasks, rules, skills, code). Use when needing to find information, understand codebase, or locate specific patterns. Supports hybrid BM25+semantic search, code symbol search, grep, context, and entity operations.

151 5mo ago A 55 tokens original MIT

codingagentsystem/cas

Skill Claude CodeCodex

Quick startup checklist for factory supervisors. Use at the beginning of a factory session to load context, check EPICs, and confirm worker availability.

151 5mo ago A 35 tokens original MIT

cas-worker

12

codingagentsystem/cas

Skill Claude CodeCodex

Factory worker guide for task execution in CAS multi-agent sessions. Use when acting as a worker to execute assigned tasks, report progress, handle blockers, and communicate with the supervisor.

151 5mo ago A 38 tokens original MIT

alfredolopez80/multi-agent-ralph-loop

Skill Claude CodeCodex

Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and…

146 5d ago A 55 tokens

autoresearch

14

alfredolopez80/multi-agent-ralph-loop

Skill Claude CodeCodex

Autonomous experiment loop: modifies code, runs experiments, evaluates metrics, keeps improvements. Inspired by karpathy/autoresearch + pi-autoresearch + autoexp. Triggers: /autoresearch, 'auto research', 'optimize continuously', 'experiment loop', 'autonomous optimization'.

146 5d ago A 61 tokens

create-task-batch

15

alfredolopez80/multi-agent-ralph-loop

Skill Claude CodeCodex

Interactive wizard to create PRD or task lists for /task-batch. Uses /clarify and /ask-questions-if-underspecified for precise task definition. Use when: (1) preparing batch execution, (2) creating PRDs, (3) defining task lists with dependencies. Triggers: /create-task-batch, 'create tasks', 'new batch', 'prepare PRD'.

146 5d ago A 86 tokens

code-review

16

sortie-ai/sortie

Skill Claude CodeCodex

Reviews pull requests in this repository for the defect classes a mechanical checklist misses: documentation that outlived the code it describes, reaction and retry state that leaks or clobbers a sibling, contract widenings that leave test doubles silently asserting nothing, kind-keyed maps missing a new entry…

135 3d ago A 130 tokens original Apache-2.0

haoyu-haoyu/Multi-AI-Workflow

Skill Claude CodeCodex

Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSIONID.

109 4mo ago B 48 tokens copy · 100% MIT

haoyu-haoyu/Multi-AI-Workflow

Skill Claude CodeCodex

Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSIONID.

109 4mo ago A 47 tokens original MIT

report-generator

19

haoyu-haoyu/Multi-AI-Workflow

Skill Claude CodeCodex

Multi-AI collaborative report generator. Uses Claude for planning/writing and Gemini for diagram generation. Creates professional reports with auto-generated figures from your research content.

109 4mo ago A 34 tokens original MIT

extra-org/extra

Skill Claude CodeCodex

The standard for writing Python here — small, typed, explicit, testable modules with side effects pushed to the edges. Use when implementing or designing any Python code.

108 5d ago A 39 tokens original MIT

skill-authoring

21

extra-org/extra

Skill Claude CodeCodex

How to create or restructure a skill so the .ai/skills/ system stays consistent, operational, and trustworthy. A skill is a short, repeatable playbook — not an essay.

108 5d ago A 42 tokens original MIT

testing

22

extra-org/extra

Skill Claude CodeCodex

How to write and run fast, deterministic, behavior-focused pytest tests that never touch real external systems. Use whenever adding or changing behavior, or fixing a bug.

108 5d ago A 34 tokens original MIT

core

23

friday-platform/friday-studio

Skill Claude CodeCodex

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…

101 5d ago A 112 tokens

workspace-api

24

friday-platform/friday-studio

Skill Claude CodeCodex

Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYDURL. Use when the user asks to create, edit, delete, or list workspaces, spaces, projects, or environments; add or patch signals / agents / jobs / memory / skills; convert a workspace.yml into a live workspace; wire up triggers…

101 5d ago A 103 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: