# Practice Setup

> >

- **Type:** Skill
- **Install:** `agentstack add skill-daddia-claude-for-strategy-practice-setup`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [daddia](https://agentstack.voostack.com/s/daddia)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [daddia](https://github.com/daddia)
- **Source:** https://github.com/daddia/claude-for-strategy/tree/main/operating-model/skills/practice-setup

## Install

```sh
agentstack add skill-daddia-claude-for-strategy-practice-setup
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Practice Setup — operating-model

## When to use

Org design leads configuring structure fit, decision rights, matrix rules, span/layers, and reward mechanics — explicit invocation only.

## What this skill does not do

- **Does not run org design analysis** — writes profiles only.
- **Does not auto-write without confirmation.**
- **Does not modify other plugins' profiles.**

## Preconditions

Per `../../references/practice-setup-framework.md` — detect setup, offer quick/full.

## Provisional mode

Quick mode: structure-fit priority and reward mechanism must be recorded or flagged for `diagnose-structure-fit` and `align-rewards-and-incentives`.

## Trust spine

Structured-aggregation bands; explicit confirmation before write; rewards captured as actual measurement/pay, not values doc.

## Shared framework

Read and follow `../../references/practice-setup-framework.md` with `operating-model` as the plugin name.

**Org profile:** `~/.claude/plugins/config/claude-for-strategy/org-profile.md`  
**Plugin profile:** `~/.claude/plugins/config/claude-for-strategy/operating-model/CLAUDE.md`

## Plugin-specific interview

After the org layer is satisfied:

1. **Full mode:** current org chart and RACI documentation as seed.
2. **Structure fit** — what structure optimizes for (efficiency, innovation, customer intimacy, coordination).
3. **Decision-rights gaps** — contested or unclear ownership decisions.
4. **Matrix relationships** — dual reporting and tie-breaker rules.
5. **Span and layers** — typical team sizes, layer count.
6. **Rewards and incentives** — how people are actually measured and paid; re-ask if sanitized.
7. **Write profiles** following `../../CLAUDE.md`.
8. **Confirm and summarize.**

## Living profile

- **Auto-apply:** this skill only, after user confirms the summary.
- **Propose profile update:** all other skills.

## Output format

Summary of org + plugin changes; defaults used; files written on confirmation.

## Worked example

**Input:** `--quick`, matrix product/geo, no documented tie-breakers, functional bonuses, 6 layers.

**Summary excerpt:** Structure optimizes customer intimacy; matrix tie-breakers flagged unknown; reward mechanism functional P&L — note for `align-rewards-and-incentives`.

## Quality checks before delivering

- [ ] Structure-fit priority recorded
- [ ] Reward mechanism captured (not values-only)
- [ ] Matrix/tie-breaker status recorded
- [ ] Confirmation before write

## Outputs

Follows plugin `CLAUDE.md` § Outputs. Next: `diagnose-structure-fit` or `design-decision-rights`.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [daddia](https://github.com/daddia)
- **Source:** [daddia/claude-for-strategy](https://github.com/daddia/claude-for-strategy)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-daddia-claude-for-strategy-practice-setup
- Seller: https://agentstack.voostack.com/s/daddia
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.