refine
Refine transforms raw ideas into production-ready product backlog items through structured problem validation, requirements elicitation, and BDD-formatted acceptance criteria. The skill enforces hypothesis gates, mandatory user interviews, and dual estimation cycles to ensure teams have complete, testable scope before development begins.
Refine converts ideas into Definition-of-Ready PBIs by validating problems, extracting requirements, and writing testable acceptance criteria.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-18
Refine converts ideas into Definition-of-Ready PBIs by validating problems, extracting requirements, and writing testable acceptance criteria. Refine transforms raw ideas into production-ready product backlog items through structured problem validation, requirements elicitation, and BDD-formatted acceptance criteria. The skill enforces hypothesis gates, mandatory user interviews, and dual estimation cycles to ensure teams have complete, testable scope before development begins.
Use it when
- Refine guides you through writing GIVEN/WHEN/THEN acceptance criteria by first validating your problem hypothesis.
- Refine supports dual estimation cycles covering story points, man-days, and complexity assessment.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Similar skills
Install
duc01226/EasyPlatform/refine · repository language: C#
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does refine help convert ideas to product backlog items?
Refine transforms raw ideas into Definition-of-Ready PBIs by applying structured problem validation, requirements elicitation using BABOK techniques, and BDD-formatted acceptance criteria. The skill enforces hypothesis gates and mandatory stakeholder interviews to ensure teams have complete, testable scope before development begins.
How do you write GIVEN WHEN THEN acceptance criteria?
Refine guides you through writing GIVEN/WHEN/THEN acceptance criteria by first validating your problem hypothesis, then documenting each scenario in BDD format. This ensures acceptance criteria are testable, unambiguous, and directly tied to verified user needs rather than assumptions.
What does refine include for estimating story points?
Refine supports dual estimation cycles covering story points, man-days, and complexity assessment. The skill also documents dependencies and production readiness factors, giving teams a complete picture of effort and risk before committing to a feature.
How does refine validate problem hypotheses before building?
Refine enforces validation interviews with stakeholders to confirm scope, assumptions, and dependencies. By running these interviews early and documenting findings, teams catch misaligned expectations and hidden requirements before development, reducing rework and scope creep.
What refinement workflow does refine recommend?
Refine applies a structured workflow combining BABOK elicitation techniques, domain research, hypothesis validation gates, and Definition-of-Ready checklists. The process moves from raw concept through stakeholder interviews, acceptance criteria authoring, and dual estimation to a production-ready PBI.
What is included in refine's Definition of Ready?
Refine's Definition-of-Ready checklist covers validated problem hypotheses, GIVEN/WHEN/THEN acceptance criteria, story-point and man-day estimates, documented dependencies, production readiness assessment, and stakeholder sign-off. This ensures every PBI is complete and testable before engineering begins.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
> Codex compatibility note:
>
> - Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
> - Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
> - User-question prompts mean to ask the user directly in Codex.
> - Ignore Claude-specific mode-switch instructions when they appear.
> - Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
> - Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
> - Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
> - For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
> - If a required step/tool cannot run in
(truncated - see the full file via the links below)
File tree — 1 file
.agents/skills/refine/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Convert raw ideas into Definition-of-Ready PBIs with validated hypotheses and testable acceptance criteria”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Business Analyst guides you through refining requirements into structured user stories using the As-a/I-want/So-that format while ensuring INVEST compliance. It extracts and references existing business rules from your project docs, investigates domain entities, and generates acceptance criteria in BDD (GIVEN/WHEN/THEN) format to close gaps and improve testability.
e2e-test automates creation of spec-traceable end-to-end tests using your project's configured framework, with every test linked to a TC code and structured via Page Object Model. It handles test generation from recordings, specs, or UI changes while enforcing semantic selectors and self-sufficient test data to keep tests resilient to future changes.
idea guides you through structured idea capture with mandatory discovery and validation gates, ensuring problem statements stay technology-neutral and ready for downstream refinement. It auto-detects your project module, conducts focused user interviews, and outputs validated artifacts ready for conversion into backlog items.
product-owner helps teams structure raw concepts into actionable backlog items by auto-detecting project modules and injecting relevant feature context. It supports RICE scoring, MoSCoW classification, and Value/Effort prioritization to align ideas with business goals. Built for Clean Architecture and CQRS projects, it enforces validation interviews and numeric priority ordering to ensure decisions are grounded in project reality.
Quality Gate Review applies pass/fail criteria at each development stage—from idea to release—ensuring standards compliance and generating audit trails. It defines checklists for gate transitions, verifies acceptance criteria with evidence, and tracks quality metrics including code complexity and defect rates.
problem-solving guides you through five systematic techniques—Simplification Cascades, Collision-Zone Thinking, Meta-Pattern Recognition, Inversion Exercise, and Scale Game—each designed to address specific types of stuck-ness. Match your symptom to the right technique, load its detailed reference, and apply the process step-by-step; combine multiple techniques when a problem requires it.
More skills sequential-thinking (MIT)