# Problem Framing > Reframe problems to unlock better solutions. Use when a team is stuck, stakeholders disagree on approach, or the obvious solutions aren't working. - **Type:** Skill - **Install:** `agentstack add skill-uthumany-uthy-legacy-os-problem-framing` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [uthumany](https://agentstack.voostack.com/s/uthumany) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [uthumany](https://github.com/uthumany) - **Source:** https://github.com/uthumany/uthy-legacy-os/tree/main/skills/problem-definition/problem-framing - **Website:** https://uthumany.github.io/uthy-legacy-os/ ## Install ```sh agentstack add skill-uthumany-uthy-legacy-os-problem-framing ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Problem Framing ## Overview The way you frame a problem determines the range of solutions you can see. A narrow frame leads to narrow solutions. This skill teaches techniques to reframe problems — expanding the solution space, getting teams unstuck, and finding breakthrough approaches. ## When to Use - The team is arguing about solutions but hasn't agreed on the problem - All obvious solutions have been tried and failed - Stakeholders are blocking each other with different frames - You want to find innovative approaches, not just incremental improvements - Don't use for: well-understood execution problems where reframing adds noise ## Instructions ### 1. Surface the Current Frame Ask: "What's the problem we're trying to solve?" Have each stakeholder answer independently. Compare the frames: - **Narrow frame**: "We need a better onboarding screen" - **Broader frame**: "Users don't reach the 'aha moment' quickly enough" - **Widest frame**: "Our activation rate is 30%, below the 60% benchmark" The narrower the frame, the more it prescribes a solution. Surface this. ### 2. Apply Reframing Techniques **Technique 1: The Five Whys** Ask "why" five times to expand the frame: 1. "Users aren't completing onboarding" → "Why?" 2. "They don't understand the value" → "Why?" 3. "They skip the tutorial because it's too long" → "Why?" 4. "They're busy and want immediate value" → "Why?" 5. "They haven't committed to the product yet" → **Real frame**: "We're asking for time investment before demonstrating value" **Technique 2: Flip the Frame** Turn the problem around: - From: "How do we get users to complete onboarding?" - To: "How do we deliver value before onboarding is complete?" - To: "How do we eliminate the need for onboarding?" **Technique 3: Change the Subject** - From: "How can we make our search better?" - To: "How can users find what they need without searching?" - To: "How can the information come to them?" **Technique 4: Expand the Constraints** - What if we had unlimited budget? → frees from resource thinking - What if we had zero budget? → forces creativity - What if we had to solve it in one week? → forces prioritization - What if users had to pay $100/month? → forces value thinking **Technique 5: The Question Ladder** Move up or down the abstraction ladder: - Concrete: "How do we reduce form fields from 12 to 5?" - Mid-level: "How do we reduce signup friction?" - Abstract: "How do we earn users' trust to share their data?" ### 3. Choose the Best Frame A good frame is one that: - Everyone agrees "yes, that's the real problem" - Opens up more solution possibilities than the current frame - Can be validated (you can test whether solving it matters) - Is specific enough to be actionable ### 4. Test the New Frame Before committing, validate: - Does this frame resonate with users? (not just stakeholders) - If we solve this frame, does the original pain go away? - Does this frame lead to measurably different solutions? ## Sample Output **Original frame**: "How do we make our notification settings page easier to use?" **After reframing**: - 5 Whys → "Users get too many irrelevant notifications and turn them all off" - Flip → "How do we send fewer, better notifications so users don't need settings?" - Change subject → "How do we let users decide their notification preferences in the moment, not in a settings page?" **Resulting solution**: Instead of a settings page redesign, build in-context notification controls — an "unmute this conversation" button in the notification itself. Eliminates the need for a settings page entirely. ## Common Pitfalls 1. **Assuming your frame is correct** — Your first framing of a problem is rarely the best one 2. **Skipping to solutions** — Teams want to solve, not explore. Force the reframing step 3. **Losing specificity** — "Make users happy" is too broad. Find the right level of abstraction 4. **Frame imposed by authority** — If the most senior person says "the problem is X," others won't reframe. Use anonymous framing exercises 5. **Analysis paralysis** — Reframing is a 30-minute exercise, not a 2-week project ## Verification Checklist - [ ] Current frame surfaced from all stakeholders - [ ] At least 2 reframing techniques applied - [ ] New frame agreed upon by team - [ ] New frame is testable (can validate) - [ ] Original problem is still addressed by the new frame ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [uthumany](https://github.com/uthumany) - **Source:** [uthumany/uthy-legacy-os](https://github.com/uthumany/uthy-legacy-os) - **License:** MIT - **Homepage:** https://uthumany.github.io/uthy-legacy-os/ 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-uthumany-uthy-legacy-os-problem-framing - Seller: https://agentstack.voostack.com/s/uthumany - 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%.