跳到正文
cccskills
免费在 GitHub 公开

agentic-orchestrating

Provides the "how-to" for workflow / task execution orchestration. Defines methods for planning multi-phase task/workflows, implementing them through agent delegation, and managing artifacts.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md4.5 KB
  • metadata.json1.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Workflow Orchestration

Knowledge base for orchestrating multi-phase workflow executions with standardized folder structures and agent delegation.

Core Concepts

This skill embodies seven key orchestration principles:

  1. Planning - HOW to create execution plans with phase breakdown and artifact definition
  2. Implementation - HOW to execute plans through agent delegation and artifact management
  3. Executing - HOW to run pre-defined workflows using EXECUTE.md blueprints
  4. Workflow to Execute - HOW to convert plain-English WORKFLOW.md into structured EXECUTE.md
  5. Resuming - HOW to restart workflows from specific phases with selective regeneration
  6. Delegation - HOW to maintain focused context through strategic agent handoffs
  7. Artifacts - HOW to standardize outputs that flow between phases

Progressive Disclosure

A core architectural principle that emerges from delegation: pass file paths, not content. This enables agents to load context when needed, maintaining high signal-to-noise ratio. Instead of inlining everything upfront, each agent reads only the files it needs for its specific task.

Standard Execution Folder

All task/workflow executions follow this structure:

/{base-dir}/{task/workflow-name}/{YYYY-MM-DD_HH:MM}/
├── data/              # Input files (optional)
├── artifacts/         # Phase outputs
│   ├── 01-*.md
│   ├── 02a-*.md
│   ├── 02b-*.md
│   └── 03-*.md
├── PLAN.md           # Initial plan
└── RESEARCH.md/STRATEGY.md/CONTENT.md       # Final output

Where base-dir is either research, strategy or content.

See Artifacts for naming conventions and folder structure details.

Orchestration Workflows

Custom Task Execution (Planning → Implementation)

For one-off, custom tasks that require bespoke execution plans:

Planning Phase

Purpose: Create a structured execution plan

Inputs:

  • Task description or workflow definition
  • User requirements and context

Process: See Planning

Outputs:

  • Execution folder structure
  • PLAN.md with phase breakdown
  • Expected artifact definitions

Implementation Phase

Purpose: Execute the plan through agent delegation

Inputs:

  • PLAN.md from execution folder
  • data/ (optional, created in planning phase)

Process: See Implementation

Outputs:

  • Phase artifacts in execution folder
  • Final RESEARCH.md/STRATEGY.md/CONTENT.md

Standardized Workflow Execution

For repeatable, standardized workflows defined by Marketing Architects:

Workflow Conversion (One-time Setup)

Purpose: Convert plain-English WORKFLOW.md into structured EXECUTE.md

Inputs:

  • WORKFLOW.md from skill folder
  • Understanding of agent types and capabilities

Process: See Workflow to Execute

Outputs:

  • EXECUTE.md in same folder as WORKFLOW.md
  • Ready for repeated execution via /execute command

Execution Phase

Purpose: Run pre-defined workflow using EXECUTE.md blueprint

Inputs:

  • EXECUTE.md from skill workflow folder
  • User inputs (slug, topic, context)
  • data/ (optional, if EXECUTE.md specifies)

Process: See Executing

Outputs:

  • Execution folder in appropriate location
  • Phase artifacts
  • Final RESEARCH.md/STRATEGY.md/CONTENT.md

Resumption Phase

Purpose: Restart execution from specific phase with selective regeneration

Inputs:

  • Existing execution folder with PLAN.md (or EXECUTE.md)
  • User specification of resume point
  • Existing artifacts/ (some preserved, some regenerated)

Process: See Resuming

Outputs:

  • Regenerated artifacts from resume point forward
  • Preserved artifacts from before resume point
  • Updated final output

Tools and Resources

Scripts

  • scripts/create_execution_folder.py - Creates timestamped execution folders

Templates

  • assets/PLAN_EXECUTE_template.md - Plan/Execute blueprint template

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

2agent

免费

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

add-agent

免费

Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

Add new Agent templates to the meta-agent-skills framework.

中文简介正在准备中。当前显示原文说明。

diegosouzapw/awesome-omni-skill642026年3月2日 更新

查看 diegosouzapw 的全部技能

报告此技能的问题