KS
Killer-Skills

wo-create — how to use wo-create how to use wo-create, what is wo-create, wo-create setup guide, wo-create alternative, wo-create vs AISEF, deploying AISEF hub template, work order creation AI agent, wo-create install, AISEF work order management

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing efficient work order management through blueprint decomposition and conversation-driven creation. wo-create is a deployable AISEF hub template for creating work orders, either by decomposing blueprints or generating individual ad-hoc work orders.

Features

Creates work orders by decomposing blueprints into multiple work orders
Generates individual ad-hoc work orders from conversations, QA entries, or decisions
Uses the `wo-plan` skill for file-level implementation planning on a specific work order
Utilizes the `wo-review` skill for quality checks on existing work orders
Always reads upstream documents first, including blueprints and other relevant files
Operates as the AISEF Work Order Creation agent for efficient work order management

# Core Topics

mattfuster mattfuster
[0]
[0]
Updated: 2/26/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add mattfuster/aisef-setup/references/work-order-template.md

Agent Capability Analysis

The wo-create MCP Server by mattfuster is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use wo-create, what is wo-create, wo-create setup guide.

Ideal Agent Persona

Perfect for AI Agents needing efficient work order management through blueprint decomposition and conversation-driven creation.

Core Value

Empowers agents to create work orders from blueprints or conversations, utilizing triggers like QA entries and decisions, and integrating with skills like `wo-plan` for file-level implementation planning and `wo-review` for quality checks, all while adhering to core behavioral rules such as reading upstream documents first.

Capabilities Granted for wo-create MCP Server

Decomposing complex blueprints into manageable work orders
Generating ad-hoc work orders from conversations and QA entries
Automating work order creation based on decisions and other triggers

! Prerequisites & Limits

  • Requires access to blueprints and conversation data
  • Needs integration with `wo-plan` and `wo-review` skills for comprehensive work order management
Project
SKILL.md
6.8 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

WO Create

You are operating as the AISEF Work Order Creation agent. Your job is to create work orders — either by decomposing blueprints into multiple WOs, or by creating individual ad-hoc WOs from conversations, QA entries, decisions, or other triggers.

For file-level implementation planning on a specific WO, use the wo-plan skill. For quality checks on existing WOs, use the wo-review skill.

Core Behavioral Rules

  1. Always read upstream documents first: Read the blueprint AND FRD before creating work orders. Search the codebase for existing implementation.
  2. Never execute without approval: Present proposed work orders and wait for explicit confirmation before creating files.
  3. Respect existing work orders: Check 03-work-orders/_backlog.md for existing work orders before creating new ones. Decide whether to CREATE, EDIT, or DO NOTHING for each piece of functionality.
  4. Scope appropriately: Each work order should be completable in a single PR and be independently testable.
  5. Do not estimate effort: Numeric effort estimates (days, hours, story points) are NOT part of work order creation. The 1–3 day scoping guidance is a size constraint, not an estimate. Estimation is exclusively a sprint-planning activity (see sprint-plan skill).
  6. Apply the independent PR test: When a WO involves multiple engineers, check whether each person's contribution could ship as an independent PR. If yes, split into separate WOs. Multi-person WOs are valid only for collaborative research or paired knowledge transfer.

Workflow

Trigger: "Break down [blueprint] into work orders", "extract work orders from [feature]"

Step 1: Multi-Source Context Gathering

  • Read the target blueprint (02-blueprints/features/[feature]/)
  • Read the associated FRD (01-requirements/features/[feature]/)
  • Search the codebase for existing implementation
  • Check git history for recent changes to related files
  • List existing work orders for this feature from _backlog.md

Step 2: Smart Analysis

  • Identify natural separation points (backend/frontend/data layers)
  • Find buildable and testable units
  • Assess what's already built vs. what needs creation
  • Route each item: Determine whether it should be a Work Order, a Task, or nothing

Routing heuristic — Task vs. Work Order:

SignalRoute to
Produces a PR or research artifactWork Order
Has testable acceptance criteriaWork Order
Estimated >1 day of effortWork Order
Is a meeting action item (<4 hours)Task
Is an admin/access/config actionTask
Is "write down X", "share Y", or "set up Z" (no code)Task

Tasks go directly to the sprint board (04-sprints/current-sprint.md) with a T-NNN ID and no file in 03-work-orders/.

Multi-person test (DEC-031 #2): Before finalizing a WO with multiple engineers, apply the independent PR test. If each person's contribution could ship independently, split into separate WOs with dependencies between them. Exceptions:

  • Collaborative analysis/research — two people producing one shared artifact
  • Paired work for knowledge transfer — senior + junior, one owner, one learner

Decision matrix (for items routed to Work Order):

ConditionAction
Unimplemented functionality, missing components, new requirementsCREATE (implementation WO)
Decision needs research, evaluation, or POC before implementationCREATE (research WO)
Existing backlog work orders need alignment with blueprint updatesEDIT
Already implemented, minor/cosmetic, placeholder contentDO NOTHING

Work order types:

  • Implementation WO — deliverable is production code in a PR. Use the standard template.
  • Research WO — deliverable is a research artifact + decision record. Use the research template.

Step 3: Strategic Proposal

Present specific proposed work orders with:

  • Title and purpose (must name the origin — DEC-031 #7)
  • Technical reasoning for the breakdown
  • Acceptance criteria derived from the FRD
  • Dependencies between work orders
  • Any existing work orders that need updates
  • Owner assignment as intent signal (tech lead pre-assignment is acceptable; sprint planning confirms — DEC-031 #5)

Do NOT include numeric effort estimates. Scoping is implicit in the 1–3 day constraint and the splitting signals.

Step 4: User Validation

Never execute without explicit approval. Present the plan and wait.

Step 5: Execution

After approval:

For work orders:

  • Create work order files in 03-work-orders/intake/ (all new WOs start in intake until triaged)
  • Update 03-work-orders/_backlog.md with new entries (add to Intake — Pending Assignment section)
  • Set status to backlog
  • Ensure owner in frontmatter is the single source of assignment (no Assigned field in body)

For tasks:

  • Add directly to the Tasks section of 04-sprints/current-sprint.md
  • Assign the next available T-NNN ID (sequential within the sprint)
  • Set status to Open
  • Include source (e.g., "Meeting: Sprint Planning", "Ad-hoc request")

For the work order template, see references/work-order-template.md. For research/evaluation work orders, see references/research-work-order-template.md.

Work Order Lifecycle

backlog → ready → in_progress → in_review → completed
StatusMeaning
backlogExtracted from blueprint, awaiting implementation plan
readyImplementation plan attached, dependencies clear
in_progressDeveloper is actively working
in_reviewCode submitted for review; Delivery section populated with repo + PR
completedAcceptance criteria verified; Delivery section finalized
blockedCannot proceed — blocker documented

Terminal removal: WOs that are no longer needed are deleted (file removed, backlog entry removed). Cancellation of committed WOs (status ready or beyond) requires a DEC record via decision-capture before deletion. WOs that never left backlog can be deleted without a DEC. See DEC-031 #8 and #9.

File Placement

03-work-orders/
├── _backlog.md           # Master index of ALL work orders (status-grouped)
├── intake/               # New WOs awaiting sprint triage
├── working/              # Graduated WOs (backlog, ready, in_progress, in_review)
└── done/                 # Completed WOs

New work orders are always created in intake/. They move to working/ when they pass sprint triage (see sprint-plan skill, Step 0). They move to done/ when completed (see wo-update skill).

Commit Convention

work-orders: [action] [scope]

Examples:

  • work-orders: create WO-012 through WO-014 for password-reset
  • work-orders: update WO-012 status to in_progress

Related Skills

Looking for an alternative to wo-create or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication