# Diagnose Structure Fit

> >

- **Type:** Skill
- **Install:** `agentstack add skill-daddia-claude-for-strategy-diagnose-structure-fit`
- **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/diagnose-structure-fit

## Install

```sh
agentstack add skill-daddia-claude-for-strategy-diagnose-structure-fit
```

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

## About

# Diagnose Structure Fit

## When to use

Test current/proposed structure against coordination needs the strategy requires — no universally "best" org chart.

## What this skill does not do

- **Does not align rewards** — route to `/operating-model:align-rewards-and-incentives`.
- **Does not design RACI** — route to `/operating-model:design-decision-rights`.
- **Does not recommend full redesign by default** — targeted fixes only.

## Preconditions

| Input | If missing |
|---|---|
| Strategic priority / coordination need | Ask what structure should optimize for |
| Current or proposed structure by area | Ask user to describe or provide org chart |
| Practice profile | Proceed with labeled assumptions |

## Provisional mode

Without area breakdown: assess at highest level available; flag `[review]` on incomplete area coverage.

## Trust spine

- **Confidence bands** (`hypothesis-driven-analysis`):
  - **High:** Coordination needs stated per area; fit/mismatch specific; blank-page test complete.
  - **Medium:** Some areas inferred; mismatches flagged with hypotheses.
  - **Low:** Strategy priority unstated — halt.
- **Failure modes:**
  - **Strategic advice vs. support:** Recommendations are options; leadership owns reorg decision.
  - **Client confidentiality:** Structure politics sensitive — CONFIDENTIAL header.
  - **Accountability gap:** Blank-page test names political drivers when present `[review]`.
  - **Analytical Rigor:** MECE area coverage; mismatches falsifiable.
  - **Incentive Gaming:** N/A — structure focus.
- **Escalation triggers:** Structure driven by personalities not work — name directly.

## Workflow

1. **Read practice profile** for structure optimization goal.
2. **State coordination need precisely** by area — cross-functional speed, expertise depth, local responsiveness, central control.
3. **Test structure against need per area** — name specific mismatches.
4. **Run blank-page test** — designed fresh around work, or legacy of titles/politics?
5. **Recommend targeted changes** where fit breaks down.
6. **MECE check** before output: areas in scope covered.

## Output format

```
CONFIDENCE: [defensible recommendation | structured first pass]
STRATEGIC PRIORITY: [what the structure should optimize for]

AREA: [function/business line] — Coordination need: [...]
  Current structure: [...] — Fit: [match / mismatch — specifics]

[repeat per area]

BLANK-PAGE TEST: [yes/no — if no, what's driving current shape]

RECOMMENDED CHANGES: [targeted, by area]
```

## Worked example

**Input:** Strategy needs fast cross-functional product decisions; strict functional hierarchy with no integrator.

**Expected output (excerpt):**

```
AREA: Product delivery — Coordination need: fast cross-functional decisions
  Current structure: strict functional silos — Fit: mismatch — no integrating mechanism [review]
BLANK-PAGE TEST: no — structure mirrors current VP titles [review]
RECOMMENDED CHANGES: Add product integrator role or cross-functional squad layer for delivery area only
```

## Quality checks before delivering

- [ ] Coordination need stated per area
- [ ] Mismatches specific, not vague
- [ ] Blank-page test completed
- [ ] Changes targeted, not blanket redesign
- [ ] MECE area coverage

## Propose profile update

When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), **propose a profile update**: show the exact diff against `~/.claude/plugins/config/claude-for-strategy/operating-model/CLAUDE.md` (org-wide facts go to `org-profile.md`), ask for confirmation, and write only on yes. Only `/operating-model:practice-setup` auto-applies a full profile write.

## Outputs

Follows plugin `CLAUDE.md` § Outputs. Next: `align-rewards-and-incentives`, `design-decision-rights`, or exec workshop.

## 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-diagnose-structure-fit
- 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%.