Skip to content

hoavdc/CodexKit / skills/codexkit-backlog-refiner

codexkit-backlog-refiner

Unverified

Refine Product Backlog Items to meet INVEST criteria. Write User Stories with Acceptance Criteria in Given/When/Then format, estimate with Story Points, and flag dependencies. Use before sprint planning when backlog items need grooming. Do not use to prioritize the backlog — that is the Product Owner's decision.

Backlog Refiner

Purpose

Transform raw backlog items into sprint-ready User Stories that meet INVEST criteria, with clear Acceptance Criteria and reliable estimates.

When to use

  • mid-sprint refinement sessions (preparing items for the next sprint)
  • when backlog items are vague, oversized, or lack acceptance criteria
  • when the team needs help decomposing epics into estimable stories
  • when onboarding a new Product Owner who needs story-writing structure

When not to use

  • prioritizing backlog order (Product Owner responsibility)
  • strategic roadmap discussions or feature discovery
  • items already refined and ready for sprint planning

Inputs

  • raw backlog items (titles, rough descriptions, business context)
  • product goal or current product increment theme
  • team's story point calibration reference (what does 1 point mean?)
  • known technical constraints or dependencies
  • Definition of Done for the product

Procedure

  1. Review each item against INVEST checklist:
    • I — Independent: not blocked by other stories
    • N — Negotiable: details can be discussed with PO
    • V — Valuable: delivers clear value to user or business
    • E — Estimable: team can estimate the effort
    • S — Small: completable within one sprint
    • T — Testable: has verifiable acceptance criteria
  2. Write User Story using 3C template:
    • Card: "As a [persona], I want [action] so that [benefit]"
    • Conversation: context, questions for clarification
    • Confirmation: Acceptance Criteria in Given/When/Then
  3. Estimate effort using Planning Poker reference scale:
    • 1 pt ≈ 4h | 2 pt ≈ 1 day | 3 pt ≈ 1.5 days | 5 pt ≈ 3 days
    • 8 pt = needs breakdown | 13+ pt = Epic, must split
  4. Flag items that are too large — recommend split strategies.
  5. Identify dependencies on other teams, services, or external parties.
  6. Document risks or unknowns that could block the story.

Output

  • refined User Stories with INVEST checklist scores
  • Acceptance Criteria (3–5 per story, Given/When/Then format)
  • Story Point estimates with rationale
  • split recommendations for oversized items
  • dependency and risk flags

Definition of done

  • every story passes all 6 INVEST criteria
  • every story has at least 3 Acceptance Criteria in Given/When/Then
  • no story exceeds 8 story points without a split recommendation
  • dependencies are explicitly documented

Examples

  • "Refine these 8 raw feature requests into sprint-ready user stories."
  • "This epic 'User Authentication' is too big — help me split it into stories."
  • "Write acceptance criteria for the 'Password Reset' story."

Quality Criteria

  • Feedback is specific and references exact locations in the reviewed material
  • Each critique includes a concrete improvement suggestion
  • Severity is categorized (critical / important / nice-to-have)
  • Positive aspects are acknowledged alongside areas for improvement

Verification (4C)

CheckQuestion
CorrectnessIs the feedback technically accurate and properly contextualized?
CompletenessWere all major sections of the reviewed material addressed?
Context-fitIs the review granularity appropriate for the material's maturity level?
ConsequenceIf the author implemented all feedback literally, what could go wrong?

Edge Cases

  • Material is too early-stage for detailed review — Provide structural feedback only. Note that content review is deferred until it matures.
  • Reviewer lacks domain expertise — Focus on structure, clarity, and consistency. Flag domain-specific claims as 'Needs SME verification'.
  • Author is defensive or resistant to feedback — Lead with what works well. Frame changes as questions rather than mandates.

Changelog

  • v1.0.0 — Initial release
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 464kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 464kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 318kUpdated Claude CodeCodexUnverifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 318kUpdated Claude CodeCodexUnverifiedInstall