| name | sprint-planning |
| description | Facilitate a Scrum Sprint Planning event, producing a sprint goal and a committed Sprint Backlog drawn from the prioritized Product Backlog. Invoke when the team is about to begin a new sprint and needs to select and plan its work. |
Adapted from bmad-method:bmad-sprint-planning (MIT, © 2025 BMad Code, LLC). See THIRD_PARTY_NOTICES.md.
When to use
Use this skill at the start of each sprint, before any delivery work begins. Typical triggers include:
- The previous sprint has concluded and the team is ready to commit to the next sprint.
- The Product Backlog has been refined and a prioritized set of items is ready for selection.
- The Product Owner has prepared candidate sprint goal statements and wants to align the team.
- Stakeholder priorities have shifted and the team needs to replan the upcoming sprint.
Do not invoke for backlog refinement, retrospective facilitation, or mid-sprint replanning; those are separate events with distinct skills.
Summon the SME
Before facilitating, load the Scrum Guide reference on Sprint Planning to ground the session in established Scrum practice.
Reading the config. Check .pm-kit.config.json for the sourcesMode field:
- If
sourcesMode is "online" (opt-in): fetch the URL stored at the key sources.scrumGuide in vendor/pm-kit/sources-index.json using your available web-fetch capability. Do not name a specific tool — use whatever your runtime provides. Navigate to the Sprint Planning section and ground the facilitation in what you read. Do not fabricate quotations or page numbers.
- If
sourcesMode is "offline" or the field is absent (the default): rely on your general knowledge of Sprint Planning as defined in the 2020 Scrum Guide by Ken Schwaber and Jeff Sutherland, covering the three topics: why the sprint is valuable, what can be done, and how the work will be accomplished. Cite the canonical URL from vendor/pm-kit/sources-index.json at key sources.scrumGuide in the output. Do not fabricate quotations or page numbers.
In both cases, the URL to cite is https://scrumguides.org/scrum-guide.html.
Facilitation script
Walk the user through these steps in sequence. Do not skip steps or combine them.
Step 1 — Gather inputs. Ask the user to provide: (a) the sprint number and proposed dates, (b) the team roster and any known unavailability or holidays during the sprint, (c) the team's historical velocity or a capacity estimate in person-days, and (d) the top of the Product Backlog — at minimum the stories the Product Owner considers candidates for this sprint.
Step 2 — Draft the sprint goal. Ask the Product Owner (or the user representing them) to propose why this sprint is valuable. Guide the discussion toward a single, outcome-oriented sentence that communicates the sprint's purpose to stakeholders. Confirm the sprint goal with the user before proceeding.
Step 3 — Establish team capacity. Calculate available person-days from the team roster, sprint length, and known absences. Present the result as the working capacity ceiling. Note any factors (onboarding, support duty, planned leave) that reduce effective capacity.
Step 4 — Select Sprint Backlog items. Working through the prioritized backlog from the top, help the user select stories whose combined estimate fits within the team's capacity. For each candidate story, confirm: (a) acceptance criteria are clear, (b) dependencies are identified, and (c) the story meets the team's Definition of Ready. Stop selection when capacity is reached or the backlog candidates are exhausted.
Step 5 — Identify risks and dependencies. Ask the user to surface any dependencies on external teams, components, or decisions that could block sprint execution. Record each risk with a brief mitigation note.
Step 6 — Definition of Done reminder. Present the team's Definition of Done (ask the user to state it if not already on record) and confirm that every story in the Sprint Backlog can realistically meet it within the sprint.
Step 7 — Produce the artifact. Assemble the completed Sprint Planning document using the structure in TEMPLATE.md (sibling file). Fill every section. Leave no placeholder unfilled.
Step 8 — Save the artifact. Save the filled artifact to docs/pm-kit/outputs/sprint-planning/<short-slug>.md. <short-slug> is a kebab-case ASCII slug (max 40 chars) derived from the sprint number and goal (e.g., sprint-03-payment-flow). Confirm the final path with the user before writing. If the file exists, ask: overwrite, append a date suffix (e.g., -2026-04-20), or pick a new slug. The artifact begins with the three-line provenance header below (HTML comments, do not render):
<!-- Generated by agentic-pm-kit:sprint-planning on YYYY-MM-DD -->
<!-- Languages: communication=<value>, output=<value> -->
<!-- Source mode: offline | online -->
Languages
The kit separates the language used for live agent–user dialogue from the language used in the saved artifact. Both values live in .pm-kit.config.json and are free-form strings — read each value verbatim, never infer a language from the conversation, and never select from a hardcoded list.
Facilitation dialogue. Speak to the user during facilitation in the language at language.communication. Use the string verbatim.
Filled artifact (saved TEMPLATE.md output). Produce the written artifact in the language at language.output. If language.output is absent or empty, fall back to language.communication.
Example values either field might contain: "en-US", "es-MX", "Português brasileiro", "Mandarin Chinese". Accept any string as given. This bifurcation is the normative pattern for every skill in the kit.
Acceptance gate
When Sprint Planning is complete, point the user to CHECKLIST.md (sibling file) and ask them to verify each item. Remind them that the output must be marked PASS or FAIL. On FAIL, invite the user to return with specific notes so the facilitation can be resumed or corrected.
