Skip to content

borghei/Claude-Skills / project-management/discovery/identify-assumptions

identify-assumptions

Verified

Surfaces the assumptions behind a product bet, scores impact against confidence and picks the few to test first. Use when an idea feels right but is unproven, the team disagrees on risk, or before designing experiments.

assets/sample_assumptions_overloaded.json

View on GitHub
{
  "assumptions": [
    {
      "description": "Users will prefer AI-generated summaries over manual note-taking",
      "category": "value",
      "confidence": "low",
      "impact": 9
    },
    {
      "description": "Our infrastructure can handle real-time processing for 10K concurrent users",
      "category": "feasibility",
      "confidence": "medium",
      "impact": 8
    },
    {
      "description": "Users will understand the drag-and-drop interface without a tutorial",
      "category": "usability",
      "confidence": "high",
      "impact": 7
    },
    {
      "description": "The feature will generate enough upgrades to justify the 3-month engineering cost",
      "category": "viability",
      "confidence": "low",
      "impact": 8
    },
    {
      "description": "Collecting usage data will not create GDPR compliance issues",
      "category": "ethics",
      "confidence": "medium",
      "impact": 9
    },
    {
      "description": "Our target segment actively searches for solutions on Google",
      "category": "gtm",
      "confidence": "low",
      "impact": 6
    },
    {
      "description": "This feature aligns with the company's Q3 objectives",
      "category": "strategy",
      "confidence": "high",
      "impact": 5
    },
    {
      "description": "The team can learn the required ML skills within the project timeline",
      "category": "team",
      "confidence": "low",
      "impact": 7
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall