iterate-pivot-decision
This Claude Code skill documents strategic pivot or persevere decisions by systematically compiling market evidence, validating hypotheses, and analyzing directional options before committing to a course change. Use it at planned checkpoints after MVP launches, when key market feedback invalidates original assumptions, or when stakeholders need to decide whether to change product direction versus staying the course.
git clone --depth 1 https://github.com/product-on-purpose/pm-skills /tmp/iterate-pivot-decision && cp -r /tmp/iterate-pivot-decision/skills/iterate-pivot-decision ~/.claude/skills/iterate-pivot-decisionSKILL.md
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 --> # Pivot Decision A pivot decision document captures the analysis and rationale behind a strategic direction change.or the decision to stay the course. Based on the Lean Startup concept of "pivot or persevere," this artifact ensures major strategic decisions are made with evidence, communicated clearly, and preserved for organizational learning. ## When to Use - After significant validated learning suggests the current direction may not work - At planned pivot-or-persevere checkpoints (e.g., after MVP launch) - When key hypotheses have been invalidated by market feedback - During strategy reviews when considering major direction changes - When stakeholders are debating whether to change course ## When NOT to Use - You are reporting experiment results without a direction decision attached -> use `measure-experiment-results` - The decision is technical or architectural rather than directional -> use `develop-adr` - You want to explore candidate directions before deciding anything -> use `define-opportunity-tree` - The team needs the period-end reflection ceremony -> use `iterate-retrospective`; a pivot call is a decision document, not a retro - The product is not built yet, and the question is whether to build a new idea, feature, or scope change at all (a build / validate / cut verdict) -> use `foundation-build-risk-review`; a pivot call weighs market feedback on something already shipped ## Instructions When asked to document a pivot decision, follow these steps: 1. **Summarize Current State** Document what you're currently doing, how long you've been doing it, what you've invested, and what results you've achieved. This grounds the decision in reality. 2. **Present the Evidence** Compile all relevant data: metrics, user feedback, experiment results, market signals. Be comprehensive.include evidence that supports both staying and changing course. 3. **Review Hypotheses** Revisit the original hypotheses that justified the current direction. Which have been validated? Which have been invalidated? Which remain untested? 4. **Define Options** Articulate at least three options: persevere (continue current direction), and two or more distinct pivot options. Describe each option concretely.what would change? 5. **Analyze Each Option** Evaluate options against key criteria: market opportunity, competitive advantage, team capability, resource requirements, and risk. Use evidence, not opinions. 6. **Make the Decision** State the chosen direction clearly. Explain the rationale, acknowledging trade-offs. If the team disagrees, capture dissenting views. 7. **Plan Implementation** Outline what happens next: immediate actions, resource needs, success criteria for the new direction, and communication plan. ## Output Format Use the template in `references/TEMPLATE.md` to structure the output. A complete decision document fills every template section: Overview; Executive Summary; Current State; Evidence Summary; Hypothesis Review; Options Considered; Analysis; Decision; Implementation Plan; Communication Plan; and Appendix. ## Quality Checklist Before finalizing, verify: - [ ] Current state includes honest assessment of results - [ ] Evidence is comprehensive, not cherry-picked - [ ] Multiple options are analyzed fairly - [ ] Decision rationale is clear and evidence-based - [ ] Implementation plan is actionable - [ ] Dissenting views are captured ## Examples See `references/EXAMPLE.md` for a completed example.
Run an ad-hoc ordered chain of pm-skills with shared context (ephemeral; routes to the pm-workflow-orchestrator)
Defines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment is designed. To design the A/B test or experiment that will validate the hypothesis, use measure-experiment-design.
Creates a Jobs to be Done canvas capturing the functional, emotional, and social dimensions of a customer job. Use when deeply understanding customer motivations, designing for jobs, or reframing product positioning.
Creates an opportunity solution tree connecting a desired outcome to customer opportunities and candidate solutions, preventing solution-first jumps in continuous discovery. Use when structuring scattered feature ideas or communicating how the roadmap traces to outcomes. For ranking an existing flat list of candidates, use define-prioritization-framework instead; this skill discovers the list, it does not score one.
Run applicable prioritization frameworks (RICE, ICE, MoSCoW, Weighted Scoring, Kano) against a list of features or initiatives. Produces a comparison table showing where rankings agree and diverge across frameworks, and an executive summary with recommendation. Framework applicability is filtered by data availability; Kano requires customer research. Refuses to fabricate scores; produces an estimation scaffold when input data is missing.
Creates a clear problem framing document with user impact, business context, and success criteria. Use when starting a new initiative, realigning a drifted project, or communicating up to leadership.
Generates structured Given/When/Then acceptance criteria for a user story or feature slice, covering the happy path, key failure scenarios, and non-functional expectations in testable form. Use when turning requirements into verifiable scenarios for engineering handoff and QA sign-off. For a dedicated catalog of boundary conditions, error states, and recovery paths across a feature, use deliver-edge-cases; to write the stories themselves, use deliver-user-stories.
Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary and limit scenarios to test. Distinct from deliver-acceptance-criteria, which writes story-level Given/When/Then checks; this skill produces the whole-feature edge-case catalog.