Split large stories into smaller, delivery-ready slices while preserving user value, testability, and sequencing logic.
Trigger this skill when
The team is working in iterations, sprints, or short delivery cycles.
Backlog items, sprint outcomes, or team process signals need structured review.
You need clearer delivery discipline instead of vague “be more agile” advice.
Expected inputs
epic or oversized story
current acceptance notes
dependencies
technical constraints
delivery context
Deliverables
split story set
splitting rationale
dependency notes
thin vertical slice suggestion
risks/open questions
Operating procedure
Clarify the delivery context, scope, and timebox.
Separate what is known from what is assumed or missing.
Produce the skill-specific artifact or review output.
Surface coordination, quality, sequencing, or blocker risks explicitly.
Recommend the next best handoff instead of trying to solve the whole lifecycle at once.
Quality gates
The output is specific to the current iteration context.
Risks, ambiguity, and dependencies are visible.
Advice is actionable within a real team workflow.
The result does not confuse commitment with aspiration.
Handoff targets
backlog-groomer
acceptance-driven-planner
sprint-goal-writer
Output style
Be explicit about tradeoffs and delivery risk.
Prefer concise operational artifacts over long motivational prose.
Surface evidence gaps instead of inventing certainty.
Keep the result usable by engineers, leads, or PMs.
Failure modes to avoid
Do not treat every backlog item as equally ready.
Do not hide blocker or dependency risk.
Do not reward ticket closure over outcome delivery.
Do not confuse a retrospective observation with a validated root cause.
Minimum output skeleton
## Summary
## Findings
## Structured outputs
## Risks / blockers
## Open questions
## Recommended next skill
1---2name: story-splitting-advisor3description: story-splitting-advisor4---5# story-splitting-advisor67## Purpose8Split large stories into smaller, delivery-ready slices while preserving user value, testability, and sequencing logic.910## Trigger this skill when11- The team is working in iterations, sprints, or short delivery cycles.12- Backlog items, sprint outcomes, or team process signals need structured review.13- You need clearer delivery discipline instead of vague “be more agile” advice.1415## Expected inputs16- epic or oversized story17- current acceptance notes18- dependencies19- technical constraints20- delivery context2122## Deliverables23- split story set24- splitting rationale25- dependency notes26- thin vertical slice suggestion27- risks/open questions2829## Operating procedure301. Clarify the delivery context, scope, and timebox.312. Separate what is known from what is assumed or missing.323. Produce the skill-specific artifact or review output.334. Surface coordination, quality, sequencing, or blocker risks explicitly.345. Recommend the next best handoff instead of trying to solve the whole lifecycle at once.3536## Quality gates37- The output is specific to the current iteration context.38- Risks, ambiguity, and dependencies are visible.39- Advice is actionable within a real team workflow.40- The result does not confuse commitment with aspiration.4142## Handoff targets43- backlog-groomer44- acceptance-driven-planner45- sprint-goal-writer4647## Output style48- Be explicit about tradeoffs and delivery risk.49- Prefer concise operational artifacts over long motivational prose.50- Surface evidence gaps instead of inventing certainty.51- Keep the result usable by engineers, leads, or PMs.5253## Failure modes to avoid54- Do not treat every backlog item as equally ready.55- Do not hide blocker or dependency risk.56- Do not reward ticket closure over outcome delivery.57- Do not confuse a retrospective observation with a validated root cause.5859## Minimum output skeleton60```md61## Summary62## Findings63## Structured outputs64## Risks / blockers65## Open questions66## Recommended next skill67```
Run npx skillmds@latest add 45ck/story-splitting-advisor in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
story-splitting-advisor It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
45ck (@45ck) published this skill. Their other Agent Skills are listed on their SkillMD profile.