Agents & orchestration
3,104 rows, by stacks then stars
969 of these skill files have been read, by 848 distinct authors, and what they tell an agent counted. What Agents & orchestration authors agree on, and what they forbid
subhansh-dev/agent-maxxing/system-prompts/05-agent-orchestration Skill
2★ repo95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.
subhansh-dev/agent-maxxing/workflows/batch-orchestration Skill
2★ repo95+ agent skills, 19 UI components, 7 system prompts from Claude Fable 5, GPT-5.5, Gemini CLI & more. Self-fine-tune your agent: paste one prompt and it reads every skill, internalizes patterns, and becomes elite. Works with Claude Code, Codex, Cursor, OpenCode + 60 more agents.
rakibulism/agent-skills-os/skills/design-design-handoff Skill
2★ repoTHE UNIVERSAL AGENT SKILLS LIBRARY
cynco-labs/ai-accounting-skills/accounting-engagement/skills/statutory-handoff Skill
2★ repoAgent-native accounting skills for Claude Code — folder dump → books → Beancount + Fava. MPERS, smart intake, hard gates.
cynco-labs/ai-accounting-skills/finalisation-accounting/skills/statutory-handoff Skill
2★ repoAgent-native accounting skills for Claude Code — folder dump → books → Beancount + Fava. MPERS, smart intake, hard gates.
pingidentity/agent-plugins/plugins/ping-identity/skills/ping-orchestration Skill
2★ repoAgent Plugins (Agent Skills and MCP bundles) that allow agents to understand and interact with Ping Identity products and services
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/40-agent-workflow-design Skill
no license2★ repoInstallable, permission-bounded, multi-platform agent skills & subagents for Claude Code, Codex, Copilot & Gemini/Antigravity — 125 skills + 73 subagents across 18 departments, with a validation harness, native plugin marketplace, and full upstream attribution. by FluxonLab.
FluxonLab/Skillry/plugins/devops-and-release/skills/62-handoff-readiness-check Skill
no license2★ repoInstallable, permission-bounded, multi-platform agent skills & subagents for Claude Code, Codex, Copilot & Gemini/Antigravity — 125 skills + 73 subagents across 18 departments, with a validation harness, native plugin marketplace, and full upstream attribution. by FluxonLab.
hnikoloski/imlazy/skills/imlazy-parallel Skill
2★ repoToken-efficient tier-routed agent orchestrator 40+ skills, 19 agents, Obsidian vault. Works with Claude Code, OpenCode, Codex CLI.
F-e-u-e-r/opus-pack/skills/delegation-and-review Skill
2★ repoDistilled operating skills for daily-driver Claude models — few dense rules, executable gates over long prose.
bogdanbaciu21/skills/handoff Skill
2★ repoUseful Skills from Bogdan Baciu
bogdanbaciu21/skills/parallel-dispatch Skill
2★ repoUseful Skills from Bogdan Baciu
jukrap/ai-agent-playbook/skills/design/image-to-code-handoff Skill
2★ repoReusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.
jukrap/ai-agent-playbook/skills/frontend/design-system-handoff Skill
2★ repoReusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.
jukrap/ai-agent-playbook/skills/project/adr-spec-handoff Skill
2★ repoReusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.
jukrap/ai-agent-playbook/skills/quality/review-work-light Skill
2★ repoReusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.
rumotion/ai-agent-project-template/.cline/skills/delegation-coordinator Skill
2★ repoLow-context AI agent project template for Gemini, Codex, Claude, Cline, and more. One canonical AGENTS.md, shared Memory Bank, portable skills, workflows, hooks, and deterministic validation.
guofu-shiqu/ux-expert-skills/skills/exp-orchestration-design Skill
2★ repoUX Expert Skills — 25 个体验管理专家 Skill,兼容 Claude Code & OpenAI Codex,基于 Agent Skills 开放标准
ProdaZhang/aigd/aigd Skill
2★ repoBrainstorm game design with AI; hand the output to another AI to build directly — with deterministic consistency checkers.
xAmirHamza77/PenKit51/skills/pentest-orchestration Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
mrDesign-ww/vault-os/shell/claude/skills/handoff Skill
2★ repoAn installable Claude Code + Obsidian companion system: persistent wiki-memory, curated skills/agents, isolated zones, and a self-improvement loop.
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/dispatching-parallel-agents Skill
no license2★ repoFull-lifecycle engineering plugin for Claude Code — brainstorm → plan → build → review → ship, with production-grade standards at every step.
AllanWessels/Bratan/docs/build-skills/pre-handoff-clean-state-proof Skill
no license2★ repoBratan is a self-improving Retrieval-Augmented Generation framework built on an adversarial three-agent loop
AllanWessels/Bratan/skills/particle-swarm Skill
no license2★ repoBratan is a self-improving Retrieval-Augmented Generation framework built on an adversarial three-agent loop
gy910210/hermes-research-skills/skills/doc-diagram-orchestrator-zh Skill
2★ repoResearch Skills for Hermes Agents
gy910210/hermes-research-skills/skills/research-orchestrator-zh Skill
2★ repoResearch Skills for Hermes Agents
kimtth/agent-skill-100-lines-or-less/skills/dispatching-parallel-agents Skill
no license2★ repo🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
kimtth/agent-skill-100-lines-or-less/skills/handoff Skill
no license2★ repo🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
rikitrader/glaw/seats/glaw-sec-enforcement-swarm Skill
no license2★ repoGLAW — self-contained open-source virtual law firm AI agent skill. 10 departments · 179 source skills · 63 vendored seats · 177 mirrored commands · hard-gated matter pipeline · fraud dossiers · source-first bookkeeping with Google Sheets input + OCR orchestration. Attorney work-product, not legal advice.
rikitrader/glaw/seats/glaw-valuation-409a-architect Skill
no license2★ repoGLAW — self-contained open-source virtual law firm AI agent skill. 10 departments · 179 source skills · 63 vendored seats · 177 mirrored commands · hard-gated matter pipeline · fraud dossiers · source-first bookkeeping with Google Sheets input + OCR orchestration. Attorney work-product, not legal advice.
Pyfagorass/bookofspells/skills/githubcopilot/ai-team-orchestration Skill
no license2★ repo📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.
Pyfagorass/bookofspells/skills/mattpocock/handoff Skill
no license2★ repo📖 The Book of Spells: a curated, enchanted index of real LLM tooling — and a pipeline that gathers SKILL.md skills from many houses into one searchable shelf.
MadewellRD/skills-lab/dist/skills/customer-success-command-desk/post-sale-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/skills/data-command-desk/batch-orchestration-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/skills/sales-command-desk/customer-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/skills/sdlc-command-desk/implementation-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/anthropic/customer-success-command-desk/post-sale-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/anthropic/data-command-desk/batch-orchestration-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/anthropic/sales-command-desk/customer-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/anthropic/sdlc-command-desk/implementation-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/google/customer-success-command-desk/post-sale-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/google/data-command-desk/batch-orchestration-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/google/sales-command-desk/customer-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/google/sdlc-command-desk/implementation-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/openai/customer-success-command-desk/post-sale-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/openai/data-command-desk/batch-orchestration-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/openai/sales-command-desk/customer-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/implementation-handoff-desk Skill
2★ repoVendor-agnostic agent skill suites for the software lifecycle, web, AI engineering, product, sales, and mobile. Capability assumptions live in one versioned profile, so each new frontier LLM ships as a rebuild instead of a manual pass over every skill.
beremaran/godot-agent-loop/io.github.beremaran/godot-agent-loop MCP server
2★ repoMCP automation loop with 167 tested tools for Godot 4
hirokisakabe/issuekit/skills/worktree-start Skill
1★ repoAgent Skills for issue-driven development.
turntuptechnologies-ai/skills/skills/handoff Skill
1★ repoTurnt Up Technologies株式会社の Claude Code プラグインマーケットプレイス
anshmajumdar121/skill-x/skills/super-skill Skill
1★ repoOpen-source agent skills for Claude Code, Codex, GitHub Copilot, and other coding agents: GPT-5.6-style rigor, delegation, linear probes, and self-evolving workflows.
scoobydont-666/shared-claude-skills/skills/hydra-swarm Skill
1★ repo10 production-tested Claude Code skills — model routing, security hardening, code quality, tax advisory, cost optimization. Install: clone to ~/.claude/skills/
ViktorsBaikers/DevRites/pack/.claude/skills/rite-handoff Skill
no license1★ repoStop your AI from shipping half-baked code. A disciplined senior-engineer workflow for Claude Code (spec, vet, build, prove, review, seal, ship) that keeps each feature's state on disk, catches spec drift mid-build, gates every phase on your project's principles, and refuses to claim "done" without proof.
ViktorsBaikers/DevRites/pack/generated/claude/skills/rite-handoff Skill
no license1★ repoStop your AI from shipping half-baked code. A disciplined senior-engineer workflow for Claude Code (spec, vet, build, prove, review, seal, ship) that keeps each feature's state on disk, catches spec drift mid-build, gates every phase on your project's principles, and refuses to claim "done" without proof.
ViktorsBaikers/DevRites/pack/generated/codex/skills/rite-handoff Skill
no license1★ repoStop your AI from shipping half-baked code. A disciplined senior-engineer workflow for Claude Code (spec, vet, build, prove, review, seal, ship) that keeps each feature's state on disk, catches spec drift mid-build, gates every phase on your project's principles, and refuses to claim "done" without proof.
darbin/claudecraft/plugins/rem-meta/skills/rem-handoff Skill
1★ repoClaude Code skills and plugins for verification-first development, independent code review, and skill engineering. 19 skills across 3 plugins.
goldenprofile/llm-skills/llm-delegation Skill
1★ repoLLM Skills
donatassimkus/claude-ai-skills/skills/handoff Skill
1★ repoGrowth marketing skills for Claude Code, Cursor, and any AI agent: SEO, CRM, marketing automation, inbox triage, and pre-launch QA. Paste one prompt and your agent installs the method, then applies it to your own accounts.
lennney/gate-all-skills/skills/discussion/handoff Skill
no license1★ repoFrontend/Next.js Claude Code Skills — curated + custom