一键在 Manus 中运行任何 Skill

delegate-team

星标1

分支0

更新时间2026年7月17日 10:41

Complete agentic engineering supersystem — one command orchestrates the entire engineering chain. Use when the user asks for "the full arsenal", "use everything you have", "/Apeiron", "/delegate-team", "delegate to a backend", "spawn a multi-agent team", "make a CLI to scaffold skills", or any natural-language request that should drive a Claude Code or Codex session through the full brainstorm → plan → execute → verify → ship pipeline. Composes four companion frameworks (superpowers, Waza, unslop-preflight, autoresearch) plus the original `dt` gateway CLI, multi-agent team (MMAS) framework, skill scaffolder, the /Apeiron orchestrator (47-case selftest routing), and the v2.7.0 arsenal: autopilot.sh (7-stage GOD command), apeiron-uni (smart universal wrapper that detects the calling runtime), and 1890 auto-discovered skills across 3 sources.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

imMamdouhaboammar

imMamdouhaboammar/delegate-team

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

其他计算机职业计算机与数学类职业·SOC 15-1299

SKILL.md

readonly

同仓库更多 Skills

同仓库

agent-kernel

imMamdouhaboammar/delegate-team

Local-first governance kernel for AI coding agents — gives Claude Code, Codex, Cursor, Antigravity, and Gemini CLI a shared memory, an approval inbox for new rules, generated AGENTS.md / CLAUDE.md / cursor-rule.mdc, Claude + git hooks, and a deterministic policy guard. Adds a JSON-first memory layer (rules + preferences + workflows + project-notes + skills), an episodic memory archive, and MCP tools for search/read/capture/sync of past sessions. Use when the user asks to "remember this rule", "save this as a memory", "what did we do last time", "search past episodes", "propose a new rule", "make agent follow our standards automatically", or any request to give an agent persistent local memory across sessions. Bundled inside delegate-team v2.5.0 — installed via `./install.sh --kernel`. Triggers on: "agent kernel", "ak", "remember this", "save this rule", "memory tool", "episodic memory", "approval inbox", "guard policy", "rule inbox".

2026-07-171

aonios-agent

imMamdouhaboammar/delegate-team

Route heavy coding tasks to premium multi-model backends (Codex GPT-5.5/5.4 high, GLM-5.2 max, Qwen 3.7 max, Kimi K2.7 code-max, MiniMax M3 high-thinking). Mirrors vertex-coder's structure but shells out to local CLI binaries (codex, opencode) instead of Vertex AI. Two modes: direct (single-file) and interactive (multi-file autonomous with tool use). Use when delegating heavy code generation, debugging, or refactoring tasks to the strongest available model. Triggers on: "delegate to aonios agent", "use the strongest model", "premium model coding", "opencode glm", "codex gpt-5 high", "minimax m3 thinking", "aonios agent direct", "aonios agent interactive". Do NOT use for trivial edits (do them locally) or when the user explicitly forbids external delegation.

2026-07-171

apeiron

imMamdouhaboammar/delegate-team

The ONE-COMMAND orchestrator that wires the full delegate-team arsenal for any task in any project. Use when the user says "use everything you got", "use full engineering arsenal", "go all-in", "/Apeiron <task>", "/ship <task>", "use all capabilities", "full stack", "end to end", "everything intelligently". Composes 38 curated integrations (superpowers, Waza, unslop, autoresearch, agent-kernel, ...) and routes tasks through 7-stage autopilot chain (PREWARM → BRAINSTORM → PLAN → EXECUTE → REVIEW → QUALITY-GUARD → REPORT). Auto-discovers 1890+ skills across 3 sources (apeiron, agents, claude) with intelligent dedupe. Includes apeiron-uni — the smart universal wrapper that detects the calling runtime (Apeiron / codex / claude / gemini / opencode / mmx / shell) and dispatches the right flow. Skip this skill only when the user wants a SPECIFIC tool (e.g. "run /autoresearch with metric X" or "delegate to aonios-agent").

2026-07-171

minimax-coder

imMamdouhaboammar/delegate-team

Local MiniMax-powered coding agent. Uses the official `mmx` CLI (https://github.com/MiniMax-AI/cli) to call MiniMax models (M3 flagship, M2.7, M2.7-highspeed) for direct single-file edits and multi-file autonomous work with full tool use. Sibling backend to vertex-coder inside delegate-team; mirrors its structure (direct + interactive + tools registry) but routes through mmx instead of an SDK. The Python scripts in this directory are local-agent helpers — Apeiron (M3) can also invoke `mmx text chat` directly via bash for fast ad-hoc calls. Three MiniMax models supported. Use when delegating coding work to MiniMax models. Triggers on: "use minimax coder", "MiniMax M3", "MiniMax M2.7", "minimax direct", "minimax interactive", "mmx text chat". Do NOT use for trivial edits (do them locally).

2026-07-171

apeiron-team

imMamdouhaboammar/delegate-team

Apeiron Multi-Agent System (MMAS) — spawn a team of specialized AI agents under your direct command. Each agent has a specific power + model (Atlas orchestrator, Forge deep worker, Scout searcher, Oracle debugger, Librarian docs-finder, Reviewer validator, Visionary media-analyzer, Sentinel security-auditor). A watchdog polls every 30s and reports status back to you. Inspired by oh-my-openagent's specialized agent team + hermes-agent's self-improving learning loop. Use when you want parallel agents working on a complex task while you stay the boss. Triggers on: "spawn team", "multi-agent", "MMAS", "parallel agents", "team of agents", "boss mode", "watchdog", "/apeiron-team". Do NOT use for single-file edits (do them locally).

2026-07-171

apeiron

imMamdouhaboammar/delegate-team

2026-07-171

name

delegate-team

description

delegate-team — the agentic engineering supersystem

Install once. Run dt run "<task>" or /Apeiron "<task>" anywhere.

This is the main skill for the delegate-team supersystem. It bundles and orchestrates six top-level components so a single natural-language task can run through the full engineering chain without the user picking tools manually.

What this skill IS

A bundle that lets Claude Code / Codex / Cursor / any npx skills add-compatible agent run the supersystem end-to-end:

# One command, full chain (from any session) — the DEFAULT entry point
/Apeiron "Make API p95 < 200ms"

# Same chain from any agent (codex / claude / gemini / opencode / mmx)
# → apeiron-uni detects the runtime + dispatches autopilot --background
apeiron-uni "Build a landing page with shadcn components"

# Plain shell (foreground — you watch the log)
apeiron-uni "Refactor the user model for multi-tenancy"

# Or invoke dt CLI for raw delegation
dt run "<task>"

When a Claude Code agent loads this skill, it treats every incoming task as potentially runnable through the supersystem and applies the /Apeiron orchestrator's routing logic before deciding what to do. /Apeiron is the default front door: if no narrower tool is explicitly requested, the supersystem routes the task through it automatically.

Components wired (v2.8.0 — twelve)

Component	Path	Function	Status
`orchestrator/`	`./orchestrator/`	`/Apeiron` skill + regex router (53-case selftest)	✅
`orchestrator/scripts/orchestrate.py`	`./orchestrator/scripts/`	Router with 53 routing cases	✅
`orchestrator/scripts/catalog.py`	`./orchestrator/scripts/`	43 integrations + 1890 skills indexer	✅
`apeiron/`	`./apeiron/`	Standalone /Apeiron skill bundle (SKILL.md + scripts)	✅ NEW v2.7.0
`bin/autopilot.sh`	`./bin/`	GOD command: 7-stage chain (PREWARM → BRAINSTORM → PLAN → EXECUTE → REVIEW → QUALITY-GUARD → REPORT)	✅ NEW v2.7.0
`bin/apeiron-uni`	`./bin/`	Smart universal wrapper: detects Apeiron / codex / claude / gemini / opencode / mmx / shell	✅ NEW v2.7.0
`bin/agents-health.sh`	`./bin/`	Health check for the 10 coding agents in ~/delegate-team/bin/	✅
`scaffolder/`	`./scaffolder/`	`apeiron-skill-scaffold` generator CLI	✅
`mmas/`	`./mmas/`	Multi-agent team framework (8 agents + watchdog)	✅
`agent-kernel/`	`./agent-kernel/`	Local-first memory + governance layer (vendored v0.0.7)	✅
`aonios-agent/`	`./aonios-agent/`	Codex + opencode delegation backend	✅
`minimax-coder/`	`./minimax-coder/`	MiniMax-M3 via `mmx` CLI backend	✅
`vertex-coder/`	`./vertex-coder/`	Gemini backend	✅
`delegate-skills/`	`./delegate-skills/`	Delegate skills: hand a task to Grok/Codex/OpenCode/Kimi/AGY (`dt delegate`)	✅ NEW v2.8.0
`dt` CLI	`./src/` + `./dist/`	Gateway CLI (built via `npm run build`) — `dt delegate <agent>`	✅

Companion frameworks (optional integrations, install via `integrations/` guides)

Framework	What it adds
agent-kernel	Local-first memory + governance layer — shared rules, episodic recall, approval inbox, deterministic guard (now bundled in `agent-kernel/`)
superpowers	Methodology — brainstorm-first hard gate, TDD, review
Waza	Entry-point skills — /think /check /hunt /ui ...
unslop-preflight	UI quality gate — 23 gates block generic slop
autoresearch	Metric-driven iteration loop

When to invoke this skill

delegate-team triggers automatically on:

User prompt signal	Action
"use full engineering arsenal"	full chain
"" + heavy multi-file	routed by signature
"" + measurable metric	autoresearch loop
""	unslop audit (BLOCKING if score <70) then chain
""	handle locally, skip chain
"delegate this to grok / have codex do X / run it through opencode"	DELEGATE path → `<agent>-delegate` skill (review diff yourself); also `dt delegate <agent>`
"build a CLI / make X faster / design Y"	routed by signature

See orchestrator/SKILL.md (the /Apeiron skill) for the full routing matrix and decision logic.

Hard-coded routing rules

# Quick reference
apeiron "<task>"   # Prints the route, no execution

Detection signals (regex scoring 0-3):

Stage	Trigger words
`/think` (Waza)	plan, design, build, create, implement, add, architect
`unslop audit` (BLOCKING)	ui, frontend, page, component, layout, css, shadcn, modal
`systematic-debugging` (superpowers)	fix, bug, broken, regression, failing, crash, error, leak
`autoresearch loop`	\d+%, p\d+, <\s\d, reduce.by, increase.*by, coverage, latency, bundle
`/delegate-team`	refactor, migrate, overhaul, rewrite, across, architecture, service
`/apeiron-team` MMAS	team, squad, parallel, specialize, swarm
`/read + /learn`	research, learn, understand, investigate, study, explore
TRIVIAL skip	rename, comment, remove, bump

Install

git clone https://github.com/imMamdouhaboammar/delegate-team
cd delegate-team
./install.sh --all            # Everything (incl. agent-kernel v0.0.7 + /Apeiron v2.7.0 arsenal)
./install.sh --apeiron        # Just /Apeiron
./install.sh --orchestrator   # Just /Apeiron (alias)
./install.sh --mmas           # Just the multi-agent framework
./install.sh --kernel         # Just agent-kernel (memory + governance)
./install.sh --integrations   # Just companion frameworks
./install.sh --verify         # Check what's installed

./install.sh --verify returns green for all 13 components (v2.7.0).

Verify on Skills.sh:

npx skills add imMamdouhaboammar/delegate-team -a claude-code -g -y
npx skills list               # Should show: delegate-team

Files in this manifest

SKILL.md — THIS FILE — main skill manifest
orchestrator/SKILL.md — /Apeiron specific skill (v2.7.0)
orchestrator/scripts/orchestrate.py — 53-case router (selftest)
orchestrator/scripts/catalog.py — 43 integrations + 1890 skills indexer
delegate-skills/SKILL.md — delegate skills component (v2.8.0)
delegate-skills/*-delegate/ — grok/codex/opencode/kimi/agy delegate skills (v2.8.0)
apeiron/SKILL.md — standalone /Apeiron skill bundle (NEW v2.7.0)
bin/autopilot.sh — 7-stage GOD command (NEW v2.7.0)
bin/apeiron-uni — smart universal wrapper (NEW v2.7.0)
bin/agents-health.sh — health check for 10 coding agents
scaffolder/SKILL.md — apeiron-skill-scaffold specific skill
mmas/SKILL.md — multi-agent team specific skill
agent-kernel/SKILL.md — agent-kernel (memory + governance) specific skill
aonios-agent/SKILL.md — Codex + opencode backend
minimax-coder/SKILL.md — MiniMax backend
vertex-coder/SKILL.md — Gemini backend

Compatibility

Agent	Status
Claude Code	✅ Tested — full install path
Cursor	✅ Via `npx skills add` to `.agents/skills/`
Codex	✅ Via `npx skills add` to `.codex/skills/`
Copilot	✅ Via `npx skills add` to `.copilot/skills/`
Windsurf	✅ Via `npx skills add`
Gemini CLI	✅ Via `npx skills add`
OpenCode	✅ Via `npx skills add`
60+ more agents	✅ See vercel-labs/skills README

License

MIT

Repository

https://github.com/imMamdouhaboammar/delegate-team

delegate-team

同仓库更多 Skills

同仓库更多 Skills

delegate-team — the agentic engineering supersystem

What this skill IS

Components wired (v2.8.0 — twelve)

Companion frameworks (optional integrations, install via integrations/ guides)

When to invoke this skill

Hard-coded routing rules

Install

Files in this manifest

Compatibility

License

Repository

delegate-team — the agentic engineering supersystem

What this skill IS

Components wired (v2.8.0 — twelve)

Companion frameworks (optional integrations, install via integrations/ guides)

When to invoke this skill

Hard-coded routing rules

Install

Files in this manifest

Compatibility

License

Repository

Companion frameworks (optional integrations, install via `integrations/` guides)

Companion frameworks (optional integrations, install via `integrations/` guides)