problem-statement-builder
Skill3 starsChanged 4 months agoMITView on GitHub
Transform a raw problem hypothesis into a structured, testable Problem Statement using Jobs-to-be-Done (JTBD) framing. Use when working on product discovery, PRDs, user stories, OKRs, or backlog planning.
In this repository59 other files it gives its agents.
- agent-memory-designerSkill
- ai-cost-optimizerSkill
- ai-evaluation-builderSkill
- ai-latency-optimizerSkill
- ai-solution-architectSkill
- ai-workflow-builderSkill
- context-engineeringSkill
- human-in-the-loop-designerSkill
- multi-agent-plannerSkill
- prompt-engineerSkill
- prompt-optimizerSkill
- prompt-reviewerSkill
- adr-generatorSkill
- api-designerSkill
- architecture-reviewSkill
- component-diagram-builderSkill
- container-diagram-builderSkill
- data-flow-analyzerSkill
- integration-plannerSkill
- observability-plannerSkill
- scalability-advisorSkill
- solution-architectureSkill
- system-context-builderSkill
- experiment-designerSkill
- go-to-market-plannerSkill
- pricing-strategy-advisorSkill
- mcp-best-practicesSkill
- mcp-client-generatorSkill
- mcp-security-reviewSkill
- mcp-server-generatorSkill
- mcp-tool-generatorSkill
- acceptance-criteria-generatorSkill
- analytics-instrumentation-plannerSkill
- competitive-analysisSkill
- epic-generatorSkill
- feature-prioritizationSkill
- idea-validatorSkill
- north-star-metric-advisorSkill
- okr-builderSkill
- persona-generatorSkill
- prd-generatorSkill
- product-discovery-assistantSkill
- product-vision-builderSkill
- sprint-plannerSkill
- story-mappingSkill
- user-story-generatorSkill
- value-proposition-designerSkill
- chunking-strategy-advisorSkill
- embedding-strategy-advisorSkill
- hybrid-search-advisorSkill
- knowledge-ingestion-plannerSkill
- rag-architecture-designerSkill
- retriever-optimizerSkill
- ai-governance-advisorSkill
- ai-threat-modelingSkill
- guardrails-builderSkill
- owasp-llm-reviewerSkill
- prompt-injection-detectorSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
When/where the problem occurs (context)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Problem Statement Builder
Purpose
Transform a raw problem hypothesis into a structured, testable Problem Statement using Jobs-to-be-Done (JTBD) framing.
Input: Problem hypothesis, target user context, evidence (optional)
Output: Problem Statement document with JTBD frame, success criteria, and scope boundaries
Examples: See examples.md for worked input/output.
Workflow
Step 1: Extract problem signals
Gather:
- Who experiences the problem (user segment)
- When/where the problem occurs (context)
- Current workaround (how they cope today)
- Cost of the problem (time, money, risk, emotion)
- Evidence source (interviews, data, observation)
Step 2: Apply JTBD framing
Structure the problem as:
When [situation] I want to [motivation] so I can [expected outcome]
Identify:
- Functional job (task to complete)
- Emotional job (how they want to feel)
- Social job (how they want to be perceived)
Step 3: Define problem boundaries
Specify:
- In scope: what this problem statement covers
- Out of scope: adjacent problems explicitly excluded
- Root cause vs symptom: flag if current framing may be a symptom
Step 4: Write success criteria
Define measurable indicators that the problem is solved:
- Leading indicators (behavior change)
- Lagging indicators (outcome metrics)
- Minimum viable improvement (what "good enough" looks like)
Step 5: Validate
Run Validation checklist.
Decision Rules
| Condition | Action |
| Problem describes a solution, not a need | Reframe from solution to underlying job |
| Multiple unrelated problems in input | Split into separate problem statements; complete one |
| No target user specified | Stop; request user segment |
| Problem is a symptom | Add "Root Cause Hypothesis" section; flag for discovery |
| Success criteria are not measurable | Rewrite with specific metrics or observable behaviors |
Validation
- JTBD sentence follows When/Want/So format
- Functional, emotional, and social jobs identified
- In-scope and out-of-scope boundaries defined
- At least 2 measurable success criteria
- Current workaround documented
- Cost of problem articulated
- No solution embedded in problem statement
Anti-patterns
- Solution disguised as problem — "Users need an AI dashboard" instead of the underlying job.
- Vague pain — "Users are frustrated" without specific context or cost.
- Everyone's problem — no specific segment or situation.
- Unmeasurable success — "better experience" without criteria.
- Ignoring workarounds — not documenting how users cope today.
Best Practices
- Quote user language when evidence is available.
- Quantify cost of problem where possible (hours/week, error rate, churn).
- Separate problem statement from proposed solution entirely.
- Link to Idea Validation Report if available from prior Skill.
- Flag assumptions that need user research validation.
Output Structure
# Problem Statement: [Short Title]
## JTBD Frame
**When** ... **I want to** ... **so I can** ...
## Job Types
| Type | Job |
|------|-----|
| Functional | |
| Emotional | |
| Social | |
## Problem Details
- **Who:** [segment]
- **Context:** [when/where]
- **Current workaround:** [how they cope]
- **Cost of problem:** [quantified if possible]
## Scope
- **In scope:**
- **Out of scope:**
## Success Criteria
| Criterion | Type | Target |
|-----------|------|--------|
## Root Cause Hypothesis
[If symptom detected]
## Assumptions
- [ ] [Assumption needing validation]
## Evidence
| Source | Finding |
|--------|---------|Next Skills
| Outcome | Recommended Skill |
| Need user segment detail | product/persona-generator |
| Problem validated, ready for vision | product/product-vision-builder |
| Multiple solutions to compare | product/feature-prioritization |
| Ready for requirements | product/prd-generator |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

