sprint-plan
Skill40 starsChanged 7 months agoMITView on GitHub
Generates a new sprint plan or updates an existing one based on the current milestone, completed work, and team capacity. Pulls context from production docs and the story backlog. Run at sprint start, sprint mid-correction, or after a milestone shift.
35 other projects use a version of this.
Adopted by
Most recently taken up by
- alunadev/ald-skillstheir own version, first seen Nov 8, 2026
- mehboobali98/rmine-skillstheir own version, first seen Nov 6, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- yuusakuri/agent-skillstheir own version, first seen Nov 1, 2026
- daviszhen/agent-skillstheir own version, first seen Oct 25, 2026
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use team-combat, team-ui and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CoralGameSkillteam-combat
Orchestrate the combat team: coordinates game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, and qa-tester to design, implement, and validate a combat feature end-to-end.
Also in 5 projects that use this
CoralGameSkillteam-ui
Orchestrate the UI team: coordinates ux-designer, ui-programmer, and art-director to design, implement, and polish a user interface feature from wireframe to final.
Also in 5 projects that use this
- +2 more from CoralGame
Other versions35 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 35
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- striderZA/OpenCodeGameStudios★ 118same name
- faizkhairi/claude-code-blueprint★ 73same name
- tranhieutt/software_development_department★ 71same name
- a-lottes/aSPARK★ 25same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
- dawn840705/codex-code-studios★ 17same name
- CodePhobiia/claude-roblox-game-studio★ 9same name
- lilangMax/ClaudeCodeGameStudios★ 8same name
25 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-bibleSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- extractSkill
- gate-checkSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- prd-reviewSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-prdsSkill
- scope-checkSkill
- security-auditSkill
- setup-frameworkSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 34 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 43
If argument is new, create a new sprint.
- Distinctive: line 65
If a previous sprint exists, read it.
- Very specific: line 174
Ask: "Approve and write to production/sprints/sprint-NNN-<slug>.md?"
- Very specific: line 205
If argument is update, read the latest active sprint and:
- Distinctive: line 207
Ask what is changing:
- Distinctive: line 216
If a story is being removed mid-sprint, ask whether it carries to next sprint or is killed.
“Common” is measured: kept by at least 6 in 10 of the 34 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sprint Plan
Builds the bridge between epic story backlogs and what gets worked on in the next 1-2 weeks. Decides which stories enter the sprint, who owns them (when team info is known), and what the sprint's outcome target is.
Output: production/sprints/sprint-NNN-<slug>.md
Purpose / When to Run
Run when:
- The previous sprint just ended
- A new epic is ready to be tackled
- A milestone shift requires re-planning
- The team wants to update an in-flight sprint (
updatemode)
Inputs
- All epics:
production/epics/*/EPIC.md - All stories:
production/epics/*/story-*.md - Existing sprints:
production/sprints/*.md - Optional
production/milestones/*.md design/concept.mdfor primary metric contextproduction/session-state/active.md
Outputs
production/sprints/sprint-NNN-<slug>.md
Phase 1: Mode
If argument is new, create a new sprint. If update, edit the most recent in-flight sprint. If empty, ask:
- Prompt: "New sprint or update existing?"
- Options:
New sprint,Update existing,Show me current sprint first
For Show me current sprint first: dispatch to /sprint-status and exit.
Phase 2: Inventory Backlog & Capacity
2a: Story inventory
Glob production/epics/*/story-*.md and bucket by Status:
- Ready
- In Progress
- Blocked
- Complete
Print counts.
2b: Last-sprint signals
If a previous sprint exists, read it. Capture:
- Stories planned vs. completed
- Velocity (stories or rough hours)
- Carry-over
2c: Capacity
Use AskUserQuestion:
- Prompt: "How many engineering days are available for this sprint?"
- Options:
5 (1-week sprint, 1 dev),10,15,20,Custom (free text)
Convert to a rough story budget (e.g., 1 day = 1-2 stories of typical size). The user can override.
Use AskUserQuestion:
- Prompt: "How many designers / QA / data days available?"
- Options:
Solo dev (none),Designer + QA shared,Full team,Free text
This affects which story types can be parallelized.
Phase 3: Pick Sprint Goal
Sprint goals must be a single sentence the team can rally around. Examples:
- "Ship the OAuth login flow end to end."
- "Make the Home screen feel responsive — no skeleton longer than 300ms."
Use AskUserQuestion:
- Prompt: "Which is the sprint's primary goal?"
- Options: derived from epics with the most Ready stories. If unclear, free text.
Phase 4: Select Stories
Walk through Ready stories, prioritized by:
- Foundation epics first
- Critical path to the sprint goal
- Stories that unblock multiple downstream stories
- Stories not blocked by Proposed ADRs
For each candidate, present:
- Story slug + title
- Type
- Estimated effort (from
/estimateif run, else rough) - Dependencies on other Ready stories
User picks; capture into the plan.
Cap selection at the story budget. If the user wants more, surface scope creep:
"Selected
<N>stories — that exceeds your<M>-story budget by<X>. Want to remove some, or accept the over-commit?"
Phase 5: Write the Plan
# Sprint <NNN>: <slug>
> **Status**: Active
> **Start**: <date>
> **End**: <target date>
> **Capacity**: <days>
> **Manifest Version**: <date from control-manifest>
## Goal
<one sentence>
## Success Looks Like
- <observable end-of-sprint outcomes — e.g., "User can sign in with Apple and Google", "Crash-free rate ≥ 99.5% on internal builds">
## Sprint Backlog
| Story | Title | Epic | Type | Owner | Status |
|-------|-------|------|------|-------|--------|
| 001 | OAuth network call | auth-sign-in | Logic | <name or unassigned> | Ready |
| ... | | | | | |
## Out of Scope (carry to next sprint)
- <list — stories considered but not selected>
## Risks
- <list — engineering or external risks that could derail>
## Dependencies on Other Tracks
- Design: <list>
- Backend / API: <list>
- QA: <list>
## Daily Rhythm
- Standup: <time> (or "async via <channel>")
- Sprint review: <date>
- Retrospective: <date>
## Definition of Sprint Done
- [ ] All Sprint Backlog stories at Status: Complete
- [ ] Smoke check passes (`/smoke-check` in second skill set)
- [ ] No new control-manifest violations introduced
- [ ] Sprint demo deck (or video) prepared
- [ ] Retrospective scheduled
## Metrics to Watch
<from concept.md primary metric — note current baseline if known>
## Notes
- Review mode for the sprint: <full / lean / solo>
- Special calendar items: <holidays, on-call rotations>Ask: "Approve and write to production/sprints/sprint-NNN-<slug>.md?"
Phase 6: Update Story Headers
For each story selected, update its Status: Ready to Status: In Sprint <NNN> (or simply leave as Ready and let the sprint plan be the source of truth — pick one convention and stick with it).
Recommended: keep Story Status reflecting development progress (Ready / In Progress / Blocked / Complete) and let the sprint plan be the assignment doc. Engineers move Story Status as they work; the sprint plan stays static for the period.
Phase 7: Update Active State & Hand Off
Update production/session-state/active.md:
- Active sprint: sprint-NNN-
<slug> - Sprint goal:
<goal> - Top story to start:
<story-001>
Print:
"Sprint plan written. Engineers can pick stories with
/story-readiness <path>then/dev-story <path>. Run/sprint-statusany time for a snapshot."
Use AskUserQuestion:
Run /story-readiness for the first storyRun /scope-check on this sprintStop here
Update Mode
If argument is update, read the latest active sprint and:
- Show current state (stories by status, days remaining, burndown estimate)
- Ask what is changing:
Add stories (scope expansion)Remove stories (scope reduction)Reassign ownersMove datesUpdate sprint goal
- Apply changes via Edit
- Append a
## Mid-Sprint Update <date>section recording what changed and why — never silently overwrite
If a story is being removed mid-sprint, ask whether it carries to next sprint or is killed.
Quality Gates
- Sprint goal is one sentence, not a paragraph
- Success Looks Like is observable (not "improve quality")
- Backlog count fits within capacity, or over-commit is explicit
- Manifest Version is recorded
- Risks section is non-empty (a sprint without surfaced risks is unrealistic)
Examples
/sprint-plan new
- Capacity: 10 dev-days, 1 designer half-time, 1 QA half-time
- Goal: "Ship sign-in end to end."
- Backlog: 8 stories from auth-sign-in epic (5 Logic, 2 UI, 1 Platform)
- Out of scope: account-recovery (next sprint)
- Risks: ADR-0007 (biometric) still Proposed; sign-in story 005 is Blocked until that lands
/sprint-plan update
- Adds 1 story (paywall copy quick-design)
- Removes 1 story (push token registration — pushed to next sprint)
- Logs change rationale in
## Mid-Sprint Update
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

