# Strategic Options > Generates a genuinely distinct set of strategic options (not variations on one idea), evaluates them on the same weighted criteria, and stress-tests the leading option against real-option/staged-commitment logic before recommending it. Use whenever the user wants to compare strategic paths, is choosing between build/buy/partner, needs a "should we do A or B" recommendation, or already has one pre… - **Type:** Skill - **Install:** `agentstack add skill-natan-mohart-24-strategy-skills-for-claude-strategic-options` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [Natan-Mohart](https://agentstack.voostack.com/s/natan-mohart) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [Natan-Mohart](https://github.com/Natan-Mohart) - **Source:** https://github.com/Natan-Mohart/24-strategy-skills-for-claude/tree/main/skills/strategic-options ## Install ```sh agentstack add skill-natan-mohart-24-strategy-skills-for-claude-strategic-options ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Strategic Options ## When to use Use whenever a strategic choice needs to be made between genuinely different paths — not when someone has already picked an answer and wants confirmation dressed up as analysis (a sign of that: only one option has been fleshed out in any detail). Also use for build/buy/partner decisions, market entry mode choices, and any "should we do X" question that has more than one real alternative. ## What it does Forces at least three genuinely distinct options onto the table (not the same idea at three levels of aggressiveness), evaluates each against the same explicit weighted criteria so the comparison is apples-to-apples, and applies real-options thinking to the leading choice — checking whether it can be staged into smaller reversible commitments rather than one large bet. ## Method 1. **Generate at least three genuinely distinct options**, not degrees of the same idea. A test: if two options would use the same core capability and channel and just differ in speed or budget, they're not distinct — force a structurally different path (e.g., build vs. partner vs. acquire; organic vs. category-redefinition; focus vs. platform). 2. **Include the null option explicitly** — do nothing differently, or the minimal-change baseline — so every option is compared against a real counterfactual, not an implied "the alternative is disaster." 3. **Set weighted evaluation criteria before scoring any option**, agreed with the decision-maker up front (e.g., strategic fit 25%, financial return 30%, execution risk 20%, time to value 15%, reversibility 10%). Setting weights after seeing the options invites reverse-engineering the criteria to fit a preferred answer. 4. **Score every option against every criterion** on the same scale, with the evidence for each score stated, not just a number. 5. **Compute weighted scores and rank** — but treat a close result (within ~10%) as a signal to look harder at qualitative factors and risk, not as false precision to break the tie with. 6. **Apply real-options logic to the leading option**: can it be staged — a pilot, a smaller reversible first step, an option to expand — rather than committed to in full immediately? Where the answer is yes, the staged version is almost always the better recommendation, since it preserves the ability to learn and course-correct at a fraction of the committed capital. 7. **Name the option that was NOT chosen and why**, explicitly — this is what separates a real evaluation from a foregone conclusion, and it's the section most self-serving "analyses" skip. ## Inputs - The strategic question and the range of paths already under consideration (push for more if only one is developed) - Constraints: budget, timeline, capabilities, risk appetite - Decision-maker's actual priorities, to set criteria weights honestly ## Output format At least three distinct options plus the null option, each described in comparable depth; weighted scoring matrix with evidence per cell; ranked result; real-options staging plan for the recommended option; explicit note on the runner-up and why it wasn't chosen. ## Example A company considering international expansion has only fleshed out "enter via wholly-owned subsidiary." Forcing distinct options surfaces partner/licensing and acquisition-of-a-local-player as structurally different paths. Weighted scoring puts wholly-owned ahead on long-term control but behind on time-to-value and execution risk; applying real-options logic reframes the recommendation as a licensing partnership with a contractual option to acquire after 18 months of validated demand — capturing most of the long-term upside with a fraction of the initial risk. ## Common pitfalls - Generating options that are really the same idea at different intensities, producing an analysis that only ever confirms the preferred answer. - Setting evaluation criteria after seeing how options would score, which lets the criteria be reverse-engineered. - Recommending the full-commitment version of an option when a staged version would preserve optionality at much lower risk. ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Natan-Mohart](https://github.com/Natan-Mohart) - **Source:** [Natan-Mohart/24-strategy-skills-for-claude](https://github.com/Natan-Mohart/24-strategy-skills-for-claude) - **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-natan-mohart-24-strategy-skills-for-claude-strategic-options - Seller: https://agentstack.voostack.com/s/natan-mohart - 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%.