plan-sprint
À propos
La compétence `plan-sprint` aide les développeurs à structurer un sprint Scrum ou agile en affinant les éléments du backlog, en fixant un objectif et en calculant la capacité de l'équipe pour sélectionner les travaux. Elle décompose les éléments choisis en tâches et génère un fichier complet `SPRINT-PLAN.md`. Utilisez-la au démarrage d'un nouveau sprint, lors d'une replanification après des changements de périmètre, ou pour passer d'un travail ad hoc à un rythme structuré.
Installation rapide
Claude Code
Recommandénpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/plan-sprintCopiez et collez cette commande dans Claude Code pour installer cette compétence
Documentation
Plan a Sprint
Plan time-boxed sprint. Select refined backlog items up to team capacity. Define clear sprint goal. Decompose selected items into actionable tasks. Produces complete sprint plan that guides team work for sprint duration.
When Use
- Starting new sprint in Scrum or agile project
- Re-planning sprint after significant scope change
- Transitioning from ad-hoc work to structured sprint cadence
- After backlog grooming when items ready for sprint inclusion
- Planning first sprint after project charter approval
Inputs
- Required: Product backlog (prioritized, with estimates)
- Required: Sprint duration (usually 1-2 weeks)
- Required: Team members and availability
- Optional: Previous sprint velocity (story points or items completed)
- Optional: Sprint number and date range
- Optional: Carry-over items from previous sprint
Steps
Step 1: Review and Refine Backlog Items
Read current BACKLOG.md. For each candidate item near top, verify it has:
- Clear title and description
- Acceptance criteria (testable conditions)
- Estimate (story points or T-shirt size)
- No unresolved blockers
Refine any items missing these elements. Split items estimated larger than half sprint capacity into smaller, manageable pieces.
Got: Top 10-15 backlog items "sprint-ready" with acceptance criteria and estimates.
If fail: Items lack acceptance criteria? Write them now. Items can't be estimated? Schedule refinement conversation. Select only ready items.
Step 2: Define Sprint Goal
Write single clear sprint goal — one sentence stating what sprint will achieve. Goal should be:
- Achievable within sprint duration
- Valuable to stakeholders
- Testable (can verify it was met at sprint end)
**Sprint Goal**: [One sentence describing the objective]
Example: "Enable users to reset their password through email verification with two-factor authentication."
Got: Sprint goal articulated as one clear, testable sentence.
If fail: No coherent goal emerges? Backlog priorities may be scattered. Consult product owner — focus on single valuable outcome.
Step 3: Calculate Team Capacity
Compute available person-days per team member:
## Team Capacity
| Team Member | Available Days | Overhead (%) | Net Capacity |
|-------------|---------------|-------------|--------------|
| [Name] | [Sprint days - PTO] | 20% | [Available × 0.8] |
| [Name] | [Sprint days - PTO] | 20% | [Available × 0.8] |
| **Total** | | | **[Sum] person-days** |
Overhead accounts for meetings, reviews, ad-hoc requests (usually 15-25%).
Using story points? Use previous sprint velocity as capacity. First sprint? Use 60-70% of theoretical maximum.
Got: Capacity computed in person-days or story points. Assumptions documented.
If fail: No historical velocity? Be conservative — plan to 60% capacity. Adjust after sprint. Better under-commit and deliver than over-commit and fail.
Step 4: Select Items and Compose Sprint Backlog
Select items from top of product backlog until capacity reached. Decompose each selected item into tasks (2-8 hours each):
# Sprint Plan: Sprint [N]
## Document ID: SP-[PROJECT]-S[NNN]
### Sprint Details
- **Sprint Goal**: [From Step 2]
- **Duration**: [Start date] to [End date]
- **Capacity**: [From Step 3] person-days / [N] story points
- **Team**: [List team members]
### Sprint Backlog
| ID | Item | Points | Tasks | Assignee | Status |
|----|------|--------|-------|----------|--------|
| B-001 | [Item title] | 5 | 4 | [Name] | To Do |
| B-002 | [Item title] | 3 | 3 | [Name] | To Do |
| B-003 | [Item title] | 8 | 6 | [Name] | To Do |
| **Total** | | **16** | **13** | | |
### Task Breakdown
#### B-001: [Item title]
**Acceptance Criteria**: [From backlog item]
- [ ] Task 1: [Description] (4h, [Assignee])
- [ ] Task 2: [Description] (2h, [Assignee])
- [ ] Task 3: [Description] (4h, [Assignee])
- [ ] Task 4: [Description] (2h, [Assignee])
#### B-002: [Item title]
**Acceptance Criteria**: [From backlog item]
- [ ] Task 1: [Description] (3h, [Assignee])
- [ ] Task 2: [Description] (4h, [Assignee])
- [ ] Task 3: [Description] (2h, [Assignee])
#### B-003: [Item title]
**Acceptance Criteria**: [From backlog item]
- [ ] Task 1: [Description] (3h, [Assignee])
- [ ] Task 2: [Description] (4h, [Assignee])
- [ ] Task 3: [Description] (2h, [Assignee])
- [ ] Task 4: [Description] (3h, [Assignee])
- [ ] Task 5: [Description] (4h, [Assignee])
- [ ] Task 6: [Description] (2h, [Assignee])
### Risks and Dependencies
| Risk | Impact | Mitigation |
|------|--------|-----------|
| [Risk 1] | [Impact] | [Mitigation] |
| [Risk 2] | [Impact] | [Mitigation] |
### Carry-Over from Previous Sprint
| ID | Item | Reason | Remaining Effort |
|----|------|--------|-----------------|
| B-XXX | [Item] | [Reason] | [Hours/points] |
Got: Sprint backlog with items selected up to capacity. Each decomposed into tasks with time estimates.
If fail: Total points exceed capacity? Remove lowest-priority item. NEVER exceed capacity by more than 10%. Dependencies block sequencing? Re-order or defer items.
Step 5: Document Commitments and Save
Write sprint plan to SPRINT-PLAN.md (or SPRINT-PLAN-S[NNN].md for archival). Confirm:
- Sprint goal achievable with selected items
- No team member overallocated (>100% capacity)
- Dependencies between items sequenced correctly
- Carry-over items accounted for in capacity
- All acceptance criteria copied from backlog items
Run final validation:
# Check that total task hours align with capacity
grep -A 100 "Task Breakdown" SPRINT-PLAN.md | grep -o '([0-9]*h' | sed 's/[^0-9]//g' | awk '{sum+=$1} END {print "Total hours:", sum}'
Got: SPRINT-PLAN.md created with complete sprint backlog and task breakdown. Total hours ≤80% of available person-days × 8 hours.
If fail: Commitments don't align with goal? Revisit item selection in Step 4. Task hours exceed capacity? Remove last item or decompose tasks more granularly.
Checks
- Sprint goal is one clear, testable sentence
- Team capacity computed with documented assumptions (overhead %, PTO accounted)
- Selected items don't exceed capacity (points or person-days)
- Every selected item has acceptance criteria copied into task breakdown
- Every selected item decomposed into tasks (2-8 hours each)
- No team member overallocated beyond 100% capacity
- Carry-over items from previous sprint documented with remaining effort
- Dependencies between items sequenced correctly
- Risks and mitigations documented
- SPRINT-PLAN.md file created and saved
Pitfalls
- No sprint goal: Without goal, sprint just bag of tasks. Goal provides focus and basis for scope decisions mid-sprint.
- Over-commitment: Planning to 100% capacity ignores interruptions, bugs, overhead. Plan to 70-80% to leave buffer for unexpected.
- Tasks too large: Tasks over 8 hours hide complexity. Make progress tracking difficult. Decompose until tasks are 2-8 hours.
- Ignore carry-over: Unfinished items from last sprint consume this sprint's capacity. Account for them explicitly in capacity calculations.
- Sprint goal as item list: "Complete B-001, B-002, B-003" is not a goal. Goal describes outcome: "Users can reset their password through email verification."
- No task ownership: Every task should have assignee at planning time. Surfaces capacity conflicts early.
- Skip acceptance criteria: Tasks without acceptance criteria can't be tested. Copy acceptance criteria from backlog items into task breakdown section.
See Also
manage-backlog— maintain and prioritize product backlog that feeds sprint planningdraft-project-charter— provides project context and initial scope for first sprintgenerate-status-report— report sprint progress and velocity to stakeholdersconduct-retrospective— review sprint execution and improve planning processcreate-work-breakdown-structure— WBS work packages can feed backlog in hybrid agile-waterfall approaches
Dépôt GitHub
Compétences associées
executing-plans
DesignUtilisez la compétence executing-plans lorsque vous disposez d'un plan de mise en œuvre complet à exécuter par lots contrôlés avec des points de contrôle de revue. Elle charge et examine le plan de manière critique, puis exécute les tâches par petits lots (3 tâches par défaut) tout en rapportant la progression entre chaque lot pour une revue par l'architecte. Cela garantit une mise en œuvre systématique avec des points de contrôle de qualité intégrés.
requesting-code-review
DesignCette compétence délègue un sous-agent réviseur de code pour analyser les modifications apportées au code par rapport aux exigences avant de poursuivre. Elle doit être utilisée après avoir terminé des tâches, implémenté des fonctionnalités majeures, ou avant une fusion vers la branche principale. La revue aide à détecter précocement les problèmes en comparant l'implémentation actuelle avec le plan initial.
connect-mcp-server
DesignCette compétence fournit un guide complet permettant aux développeurs de connecter des serveurs MCP à Claude Code via les transports HTTP, stdio ou SSE. Elle couvre l'installation, la configuration, l'authentification et la sécurité pour intégrer des services externes tels que GitHub, Notion et des API personnalisées. Utilisez-la lors de la configuration d'intégrations MCP, de la configuration d'outils externes ou du travail avec le Protocole de Contexte de Modèle de Claude.
web-cli-teleport
DesignCette compétence aide les développeurs à choisir entre les interfaces Web et CLI de Claude Code en fonction de l'analyse des tâches, puis permet une téléportation transparente des sessions entre ces environnements. Elle optimise le flux de travail en gérant l'état et le contexte de la session lors du passage entre le web, la CLI ou le mobile. Utilisez-la pour des projets complexes nécessitant différents outils à diverses étapes.
