How do I install the Project Planning Task Ordering skill?

Run npx skillmds@latest add krmorehead/project-planning-task-ordering in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Project Planning Task Ordering safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Project Planning Task Ordering?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Project Planning Task Ordering free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Project Planning Task Ordering?

krmorehead (@krmorehead) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Project Planning Task Ordering by krmorehead

Name: Project Planning Task Ordering
Author: krmorehead

File contents

Task Ordering & Implementation Rules

Configure Milestone Ordering

Every milestone's task list MUST follow dependency order. Walk through each task and ask: "What must already exist for this to succeed?"
Canonical ordering for a configure milestone:
1. Fix system baseline state (broken packages, missing modules)
2. Install packages
3. Generate keys/credentials (requires package tools like wg genkey)
4. Template configuration files (requires generated keys)
5. Start/enable services (requires config files)
6. Configure runtime state (firewall rules, sysctl, NAT — requires services)
7. Persist runtime state (save iptables rules, write generated env file)

Provisioning Milestone Ordering

For a provisioning milestone:
1. Load host-side kernel modules (LXC shares host kernel)
2. Upload images/templates
3. Create VM/container
4. Configure auto-start
5. Start VM/container
6. Clean template baseline (fix broken packages in LXC)
7. Register in dynamic inventory

Dependency Constraint Rules

NEVER put key generation before package installation. NEVER put service start before configuration. NEVER install packages before fixing broken system state.

Implementation Pattern Specification

Every feature milestone MUST include an implementation pattern note specifying:
- Which task file to create
- Which plays to add to site.yml
- Which tags to use
- Which molecule scenario to create
Never leave "how it integrates" as an open question. Implementation ambiguity causes inconsistent implementations.

Architectural Decision Documentation

The project plan MUST reference the architectural decisions that were made and WHY, using the tree diagram format from docs/architecture/overview.md.

Plan Review Execution

Before execution, ALWAYS run the plan through the Plan Review Checklist against all referenced skills. This catches critical issues that would break implementation.
Previous bug: the OpenWrt router plan had two critical issues (SSH auth transition, dynamic group persistence) that would have broken implementation — both caught only by cross-referencing skills during review.

---name: project-planning-task-orderingdescription: Project milestone task ordering and implementation patterns. Use when structuring task dependencies, ordering milestone work, or planning implementation sequences.---# Task Ordering & Implementation Rules## Configure Milestone Ordering1. Every milestone's task list MUST follow dependency order. Walk through each task and ask: "What must already exist for this to succeed?"2. Canonical ordering for a configure milestone: 1. Fix system baseline state (broken packages, missing modules) 2. Install packages 3. Generate keys/credentials (requires package tools like `wg genkey`) 4. Template configuration files (requires generated keys) 5. Start/enable services (requires config files) 6. Configure runtime state (firewall rules, sysctl, NAT — requires services) 7. Persist runtime state (save iptables rules, write generated env file)## Provisioning Milestone Ordering3. For a provisioning milestone: 1. Load host-side kernel modules (LXC shares host kernel) 2. Upload images/templates 3. Create VM/container 4. Configure auto-start 5. Start VM/container 6. Clean template baseline (fix broken packages in LXC) 7. Register in dynamic inventory## Dependency Constraint Rules4. NEVER put key generation before package installation. NEVER put service start before configuration. NEVER install packages before fixing broken system state.## Implementation Pattern Specification5. Every feature milestone MUST include an **implementation pattern** note specifying: - Which task file to create - Which plays to add to `site.yml` - Which tags to use - Which molecule scenario to create6. Never leave "how it integrates" as an open question. Implementation ambiguity causes inconsistent implementations.## Architectural Decision Documentation7. The project plan MUST reference the architectural decisions that were made and WHY, using the tree diagram format from `docs/architecture/overview.md`.## Plan Review Execution8. Before execution, ALWAYS run the plan through the **Plan Review Checklist** against all referenced skills. This catches critical issues that would break implementation.9. Previous bug: the OpenWrt router plan had two critical issues (SSH auth transition, dynamic group persistence) that would have broken implementation — both caught only by cross-referencing skills during review.

Frequently asked questions

Project Planning Task Ordering