agent-orchestration skills

3,173 tagged agent-orchestration, measured the same way as everything else here.

Browse within: agentic-ai 584cli 369agentic-workflow 221Multi-Agent 200ai-automation 178babysitter 178ai-agent-framework 144ai-coding 140local-first 136no-code 135agent-framework 131ai-assistant 130acp 120agent-ecosystem 114

manual

73

yaodub/cast

Skill Claude CodeCodex

Texting as a person's proxy — reading threads, sending irreversibly, and watching conversations without over-answering.

not rated 41 18d ago B 22 tokens original MIT

gitnexus-cli

74

qualixar/qualixar-os

Skill Claude Code

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki".

not rated 41 3mo ago A 59 tokens

isomux-handoff

76

nmamano/isomux

Skill Claude CodeCodex

Continue an unfinished task on a fresh session. The agent writes a short forward-looking brief of what's left, the boss approves it, and the agent then hands off to a fresh copy of itself that resumes on just that brief.

not rated 37 today A SkillSpector: warn 51 tokens original MIT

fable-commander

77

DennisWei9898/fable-commander

Skill Claude CodeCodex

A planning and review workflow in which one model prepares decisions while selected models handle research and execution. It is written for Fable and Claude Code, tools for coordinating multi-step software work.

not rated 35 1mo ago A 176 tokens original MIT

systempromptio/systemprompt-template

Skill Claude CodeCodex

Drive every stage of the governance pipeline end to end, then prove that each decision was audited. This is the guided tour of the enforcement spine: the same four stages run on every tool call in the workspace.

not rated 28 today A 0 tokens

a2wave-memory

79

LilithGames/a2wave

Skill Claude CodeCodex

Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.

not rated 26 +1 2d ago A SkillSpector: pass 29 tokens original Apache-2.0

jayvee/aigon

Skill Claude CodeCodex

Review feature - code review with fixes by a different agent.

not rated 25 +1 9d ago A SkillSpector: pass 20 tokens original Apache-2.0

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when an architect must run the detailed-design portion of technical design, preserve the full lifecycle-stage doctrine for detailed design, and define the concrete runtime, project, flow, data, interface, non-functional, security, recovery, hardware, and implementation-plan surfaces needed for execution.

not rated 25 +1 2d ago A SkillSpector: warn 65 tokens original MIT

goga-cookbook

82

qarium/goga

Skill Claude CodeCodex

Principles for applying DSL specification in cell and CODEMANIFEST design.

not rated 25 +12 2d ago A SkillSpector: pass 19 tokens original BSD-3-Clause

projector-creator

83

ClawixAI/clawix

Skill Claude CodeCodex

Create polished, functional projector tools. Use when building any projector item — ensures correct styling, real functionality, and proper structure.

not rated 24 1mo ago A 30 tokens

reply-conventions

84

UstaLabs/supermux

Skill Claude CodeCodex

Use whenever you need to send anything to the user from a supermux session — establishes that all user-facing words go through the supermux reply tool, and the per-channel rules (Telegram vs web).

not rated 24 +2 today A 44 tokens original MIT

sonol-multi-agent

85

volition79/sonol-multi-agent

Skill Claude CodeCodex

Sonol multi-agent orchestration skill. Use when a user wants one request decomposed into single-agent or multi-agent execution, with local-AI creative draft generation, hosted normalization/binding, adapter-backed sub-agent controls, runtime reporting, dashboard monitoring, plan/run persistence, and final result…

not rated 23 4mo ago A 65 tokens

loop

86

taurus42119-stack/godkiller-mcp

Skill Claude CodeCodex

Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).

not rated 23 +1 1mo ago A SkillSpector: pass 28 tokens original MIT

skill-router

87

hussi9/skill-router

Skill Claude Code

Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.

not rated 21 changed yesterday A 69 tokens original MIT

beastmode

88

lac5q/beastmode

Skill Claude CodeCodex

Multi-agent orchestration framework for high-intensity feature implementation. Routes work across model tiers: frontier models (Claude Fable, Kimi 3, Opus; Codex only when explicitly selected) own design, architecture, and review sign-off, while the pinned Luna Max economy lane handles implementation and mechanical…

not rated 21 changed 2d ago A 125 tokens

handoff

90

Xsxdot/handoff

Skill Claude Code

A coordination skill for handing an implementation plan to a separate coding process or remote machine, then tracking its progress. It uses the handoff command-line tool and supports independent executors such as Claude, Codex, or OpenCode.

not rated 20 +1 changed 5d ago A SkillSpector: pass 216 tokens original Apache-2.0

platform_management

91

ParendumOU/Nexora

Skill Claude CodeCodex

/workspace-root = volume mount of parent dir.

not rated 20 8d ago A SkillSpector: warn 0 tokens original MIT

ad-creative

92

rondoflow/rondoflow

Skill Claude CodeCodex needs its repo

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…

not rated 19 +1 today A SkillSpector: warn 142 tokens original MIT

arch-first

93

bearded-illirian/trailmark

Skill Claude CodeCodex

Protocol for architecturally clean execution of complex multi-block tasks. Decomposition into blocks → research before library-first → explicit decision pinning → clear scope vs out-of-scope → report after each block. Principle: every architectural decision is pinned explicitly, no ambiguity, epics don't sprawl. Use…

not rated 19 changed 6d ago A SkillSpector: warn 91 tokens original MIT

anthony-chaudhary/dos-kernel

Skill Claude CodeCodex

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

not rated 19 yesterday A SkillSpector: pass 61 tokens original MIT

flo

95

eric-cielo/moflo

Skill Claude Code

MoFlo ticket spell - analyze and execute GitHub issues.

not rated 18 today A SkillSpector: warn 13 tokens original MIT

thinking-partner

96

SienkLogic/plan-build-run

Skill Claude CodeCodex

A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says "help me think through X", "challenge my thinking", "what am I missing", "apply mental models to this", "play devil's advocate"…

not rated 17 5mo ago B 183 tokens copy · 100% MIT

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: