Install
$ agentstack add skill-daddia-claude-for-strategy-evaluate-strategic-option ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Evaluate Strategic Option
When to use
Major strategic decisions needing staging, steelmanned case against, downside sizing, and pre-commitment kill criteria — not binary go/no-go.
What this skill does not do
- Does not evaluate vague topics — requires committable decision with scope, scale, timing.
- Does not soften case against for sponsors — steelman is mandatory.
- Does not pick winner when trade-offs unquantifiable — say so.
- Does not ship board-final without GATE.
Preconditions
| Input | If missing | |---|---| | Corporate-strategy + org profiles | [PROVISIONAL] balanced posture | | Precise option statement | Ask once to narrow |
Provisional mode
[PROVISIONAL] on risk posture; structured first pass if downside inputs missing.
Trust spine
- Strategic advice vs. support (mandatory): Trade-offs and triggers; IC/board owns decision.
- Per trust-conventions for sourcing, assumptions, numbers, confidence, GATE.
Workflow
Step 1: State option precisely
Reject vague topics; require committable decision.
Step 2: Staging checklist
If plausible: initial commitment, scale trigger, abandon trigger, learning objective. If not: say why.
Step 3: Case for (brief)
3–5 bullets; tag unsourced claims.
Step 4: Case against (steelman — mandatory)
Hardest assumption, cannibalization, timing illusion, integration load, comparable bias, reversibility, sponsor momentum — apply checklist.
Step 5: Downside sizing + survivability test
Direct loss, opportunity cost, reputation, org strain. Survivable on failure: yes/no/unclear with evidence.
Step 6: Kill criteria (pre-commitment)
Dated, specific; stage-1 vs full-program if staged.
Step 7: Recommendation
Proceed staged | proceed in full | do not proceed — with confidence band.
Output format
CONFIDENCE: [...]
LOAD-BEARING ASSUMPTIONS: [...]
OPTION: [precise decision]
CAN THIS BE STAGED: [...]
CASE FOR: [...]
CASE AGAINST (steelman): [...]
DOWNSIDE SIZING: [table]
SURVIVABLE ON FAILURE: [...]
KILL CRITERIA: [...]
RECOMMENDATION: [...]
Worked example
Input: Acquire Company X at $Ym by Q3.
Excerpt: Staged: $Zm pilot with scale trigger on retention ≥X%; case against surfaces integration load on named function; kill criteria by date if metric below threshold; recommendation proceed staged [review].
Quality checks before delivering
- [ ] Committable option, not topic
- [ ] Staging checklist applied
- [ ] Steelman case against
- [ ] Survivability answered
- [ ] Kill criteria dated and specific
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: IC memo, synergy-stress-test, or exit-or-double-down.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: daddia
- Source: daddia/claude-for-strategy
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.