# Synergy Stress Test

> >

- **Type:** Skill
- **Install:** `agentstack add skill-daddia-claude-for-strategy-synergy-stress-test`
- **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/corporate-strategy/skills/synergy-stress-test

## Install

```sh
agentstack add skill-daddia-claude-for-strategy-synergy-stress-test
```

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

## About

# Synergy Stress Test

## When to use

Stress-test deal synergies — separate cost vs revenue, grade evidence, apply haircuts, bar-test deal economics. Revenue synergies must not borrow credibility from cost lines.

## What this skill does not do

- **Does not blend cost and revenue lines.**
- **Does not invent deal economics** — INPUT NEEDED for price/hurdle.
- **Does not approve deal** — recommendation on adjusted case.
- **Does not skip mechanism check on revenue.**

## Preconditions

| Input | If missing |
|---|---|
| Synergy line items | Ask user or deck |
| Profile synergy haircut / track record | Use default base-rate table; cite source |
| Purchase price / hurdle for bar test | INPUT NEEDED — no fabricated IRR |

## Provisional mode

Default haircuts tagged `[unverified — industry pattern]` unless profile has org track record.

## Trust spine

- **Analytical Rigor (mandatory):** Per-line tier, haircut arithmetic, double-count scan.
- Per trust-conventions; GATE before board finals.

## Base-rate anchor

| Type | Typical realization |
|---|---|
| Cost strong evidence | ~70–90% |
| Cost weak | ~40–60% |
| Revenue any tier | ~20–40% |

Use profile overrides when configured.

## Workflow

1. Separate every line: cost vs revenue.
2. Grade evidence per line; state tier, haircut %, adjusted value. Connector-sourced figures (`~~bi analytics`, `~~crm`, `~~spreadsheet`) require `[sourced: , , ]` on each load-bearing number; otherwise use `INPUT NEEDED`.
3. Revenue mechanism check — missing mechanism → Weak.
4. Double-counting scan.
5. Recompute totals; bar test at adjusted number.

## Output format

```
CONFIDENCE: [...]
COST SYNERGIES: [table]
REVENUE SYNERGIES: [table]
DOUBLE-COUNTING FLAGS: [...]
TOTALS: [...]
DEAL BAR TEST: [...]
RECOMMENDATION: [...]
```

## Worked example

**Input:** $30M cost synergy (generic 10% G&A) + $50M revenue cross-sell (no mechanism).

**Excerpt:** Cost weak → ~50% haircut; revenue Weak → ~80% haircut; only works at optimistic number — material finding.

## Quality checks before delivering

- [ ] No blended lines
- [ ] Every line tier + arithmetic
- [ ] Revenue without mechanism = Weak
- [ ] Double-count scan done
- [ ] Bar test plain if optimistic-only

## 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/corporate-strategy/CLAUDE.md` (org-wide facts go to `org-profile.md`), ask for confirmation, and write only on yes. Only `/corporate-strategy:practice-setup` auto-applies a full profile write.

## Outputs

Follows plugin `CLAUDE.md` § Outputs. Next: renegotiate, `evaluate-strategic-option`, or IC with cost-only case.

## 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-synergy-stress-test
- 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%.