skills/store-sop/SKILL.md
Document Computer Connection store processes in AI-queryable format. Use to capture SOPs for the store AI server POC.
npx skillsauth add ComputerConnection/zach-pack store-sopInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Document this Computer Connection process for AI consumption.
Your 6-month goal: AI server that serves store SOPs. The AI can only serve what's documented. Every SOP captured = more value from the AI.
I'll ask questions to extract the process. Answer quickly - don't overthink.
Walk me through it like I'm a new employee:
Where do you have to make a judgment call?
What do new people get wrong?
What do you need access to?
sop:
id: SOP-[category]-[number]
name: [Process Name]
version: 1.0
last_updated: [date]
owner: [who maintains this]
metadata:
category: [sales | repair | inventory | customer-service | admin | other]
frequency: [daily | weekly | as-needed | rare]
duration: [typical time]
difficulty: [easy | medium | complex]
trigger: |
When to use this process:
[condition or situation]
prerequisites:
- [what must be true before starting]
- [access/permissions needed]
steps:
- step: 1
action: |
[What to do]
details: |
[How to do it - specific clicks, words, etc.]
tips:
- [helpful hint]
warnings:
- [thing to avoid]
- step: 2
action: |
[Next action]
decision_point:
condition: [if X]
if_true: [do Y]
if_false: [do Z]
edge_cases:
- scenario: [unusual situation]
handling: [what to do]
common_mistakes:
- mistake: [what people do wrong]
prevention: [how to avoid]
recovery: [how to fix if it happens]
tools_required:
- name: [tool/system]
purpose: [why needed]
access: [how to get access]
related_sops:
- [SOP-XXX-NNN]
ai_queryable:
keywords: [search terms customers or staff might use]
questions_this_answers:
- "How do I...?"
- "What's the process for...?"
- "When should I...?"
Make it queryable by adding:
ai_triggers:
- "customer wants to return"
- "how do I process a return"
- "return policy"
- "refund"
faq:
- q: "Can I return this?"
a: "See return eligibility in step 2"
- q: "How long do returns take?"
a: "Typically [X] minutes"
escalation:
- condition: "Customer is angry"
action: "Get Zach or manager"
- condition: "System won't process"
action: "Manual override - see SOP-ADMIN-005"
Store SOPs in:
~/store-ai-poc/sops/
├── sales/
│ ├── SOP-SALES-001-new-customer.yaml
│ └── SOP-SALES-002-quote-build.yaml
├── repair/
│ ├── SOP-REPAIR-001-intake.yaml
│ └── SOP-REPAIR-002-diagnosis.yaml
├── inventory/
├── customer-service/
└── admin/
Also maintain an index:
~/store-ai-poc/sops/INDEX.md
Before finalizing:
For fast documentation:
# SOP: [Name]
**When**: [trigger]
**Time**: [duration]
## Steps
1. [action]
2. [action]
3. [action]
## If Problems
- [issue] → [solution]
## Don't Forget
- [common mistake to avoid]
Expand to full format later.
Track progress:
data-ai
Inject Zach's full identity, business context, and working preferences. Use at session start to eliminate cold starts. Lightweight context load — not a full agent like Vision, just who Zach is and how to work with him.
tools
--- name: vision description: "Zach's personal AI — his Jarvis. NOT a store agent. This is the owner's private command center that sits above everything else. Handles anything Zach needs — business, personal, technical, strategic, creative. High-systems AI: precise, anticipatory, authoritative. Invoke for ANY task." context: fork allowed-tools: Read, Grep, Glob, Bash, Edit, Write, Task, TodoWrite argument-hint: [what-do-you-need] — freeform. Vision figures out the rest. --- # VISION — Zach's Ja
development
Tauri-specific development patterns for NEXUS. Use when building desktop app features, handling IPC, or working with Rust backend.
development
Orchestrates the full product strategy pipeline: product audit → roadmap → sprint plan with PM decision gates. This skill reads ACTUAL source code, cross-references git history, and produces three deliverables — a brutally honest product audit, a thesis-driven roadmap, and a sprint plan with PM decision gates between every phase. Use this skill whenever someone mentions: "sprint plan", "product roadmap", "plan the sprints", "PM questions", "product strategy", "audit this app", "roadmap this feature", "plan development", "break this into sprints", "phase this work", "create a development plan", "quarter planning", "what should we build next", "evaluate this app", "feature audit", "product review", "development roadmap", or any request for deliberate, methodical planning of software work. Also trigger when users want to evaluate whether features earn their place, when they reference PM decision gates or go/no-go checkpoints, or when they want to understand what's worth keeping in a codebase before planning new work. Even if the user only asks for one stage (just an audit, just a sprint plan), use this skill — it will guide them through the appropriate subset.