一键在 Manus 中运行任何 Skill

bmad-sprint-planning

星标467

分支73

更新时间2026年6月20日 01:58

Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

aj-geddes

aj-geddes/claude-code-bmad-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

项目管理专家商业与金融运营类职业·SOC 13-1082

文件资源管理器

4 个文件

SKILL.md

readonly

同仓库更多 Skills

同仓库

bmad-builder

aj-geddes/claude-code-bmad-skills

Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violations", "new skill for the planner", or "bmad-builder". Supports three intents: Create (new skill skeleton), Validate (check an existing SKILL.md), Scaffold (directory structure only). This skill plans and scaffolds only — it NEVER writes application code, runs tests, lints, or builds.

2026-06-20467

bmad-architecture

aj-geddes/claude-code-bmad-skills

Solutioning skill (Winston, the Architect). Produces architecture.md with ADRs and systematic NFR coverage, mapping every FR/NFR from the PRD to a concrete design decision. ONE architecture forces all future parallel dev agents to share the same API style, data model, state management, naming conventions, and security approach — catching alignment here is 10x cheaper than during implementation. Use when the user says "design the architecture", "create architecture", "/architecture", "solutioning", "tech stack", "system design", "ADR", "architecture decision record", "data model", "API design", "NFR coverage", "non-functional requirements", or after a PRD is done and they ask "what's next" / "ready for solutioning". Supports Create (new architecture.md), Update (revise against PRD changes), and Validate (check coverage + ADR completeness). PLANS only — never writes application code, runs tests, lints, or builds.

2026-06-20467

bmad-brainstorm

aj-geddes/claude-code-bmad-skills

Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.

2026-06-20467

bmad-correct-course

aj-geddes/claude-code-bmad-skills

CROSS-PHASE mid-stream scope correction. Re-enters planning when requirements, features, architecture, or constraints change after planning has started. Re-shards affected epics/stories, re-sequences sprint-status.yaml, appends rationale to decision-log.md. Routes to bmad-epics-and-stories, bmad-sprint-planning, or bmad-parallel-plan as needed. Changes the PLAN, never code. Use when: "we need to change course", "scope has changed", "new requirement came in", "we're dropping feature X", "we need to pivot", "re-plan after the change", "requirements changed mid-sprint", "correct course", "architecture changed", "re-scope the backlog", "update epics after feedback", "cancel story X", "add epic for Y", "change the plan", "we got new constraints", or when stories are split/merged/reordered due to a decision not in the original plan. Produces: updated epics.md (affected only), revised/new story files, updated sprint-status.yaml, new decision-log.md entry. NEVER writes code or runs tests.

2026-06-20467

bmad-document-project

aj-geddes/claude-code-bmad-skills

BROWNFIELD planning input. Scans an existing codebase READ-ONLY and writes project-documentation.md — ground truth for stack, structure, key flows, conventions, and integration points — so downstream BMAD planning skills start from reality. Does NOT modify code; produces only the doc artifact. Use when the user says: "document this codebase", "document the project", "document my app", "scan the existing code", "brownfield planning", "we have existing code, start planning", "map what's already built", "document current state", "capture the current architecture", "understand the existing system before planning", "write project-documentation.md", or before a PRD or architecture doc when the user already has code written. Three intents: Create (initial scan), Update (re-scan changed areas), Validate (check completeness). Plans only — reads code but never writes it, runs no tests, no linters, no build tools, no application code.

2026-06-20467

bmad-epics-and-stories

aj-geddes/claude-code-bmad-skills

Solutioning flagship — shards a PRD + architecture into epics.md and individual {epic}.{story}.{slug}.story.md context objects, the LAST planning artifact before external dev handoff. Each story is a self-contained ~8K-token compiled context object: Dev Notes with SOURCE CITATIONS back to prd.md/architecture.md, Acceptance Criteria, Tasks/Subtasks mapped to ACs, Testing strategy, Dependency Maps, an explicit Owned File/Module Scope list (the lever for parallel-conflict-free scheduling), and Learnings from Previous Stories. Sized to one dev-day; split if larger; NO story points. Use when the user says "shard the PRD", "create epics", "break the PRD into epics", "break this epic into stories", "create stories", "create a story", "draft story files", "generate the story for X", "prepare stories for dev", "mark the story ready for dev", "validate this story", or "what stories are in this epic". Three intents: Create new epics/stories, Update an existing story, or Validate a draft against the contract.

2026-06-20467

name	bmad-sprint-planning
description	Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
allowed-tools	Read, Write, Edit, Bash, Glob, Grep, TodoWrite

BMAD Sprint Planning

Role: Sequencing & Handoff Bridge — Phase 4 orchestration
System-of-record: bmad-output/sprint-status.yaml

What This Skill Does

Reads planning artifacts (PRD, architecture, epics, stories) from bmad-output/.
Derives a dependency graph across all stories.
Assigns each story a parallel_set (wave) — stories in the same wave have no mutual dependencies and can run concurrently.
Emits bmad-output/sprint-status.yaml using the canonical template.
Marks the first wave of stories ready-for-dev; all others remain backlog.
Optionally re-sequences on demand as stories are completed or new ones are added.

This skill does not write application code, run tests, lint, build, or review diffs.

Three-Intent Operation

Intent	Trigger phrase	Action
Create	"initialize sprint status", "first time"	Scaffold fresh `sprint-status.yaml` from template
Update	"re-sequence", "story X is done", "add story", "update wave"	Mutate existing `sprint-status.yaml` in-place
Validate	"check sequencing", "are dependencies correct", "show wave plan"	Read and report without writing

Workflow — Create

Load planning artifacts
```
Glob: bmad-output/**/*.md, bmad-output/**/*.yaml
```
Priority order: epics.md → prd.md → architecture.md → individual story files.
Extract epics and stories
- Parse all story IDs: format {epic}.{story}.{slug}.story.md (e.g., 2.1.stripe-integration.story.md)
- Derive epic ordering from the epic list in epics.md or prd.md
Build dependency graph
- Read dependencies[] from each story's frontmatter or Dev Notes section
- Topological sort: stories with no unmet dependencies → wave 1; stories unblocked after wave 1 → wave 2; etc.

Initialize sprint-status.yaml

bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/init-sprint-status.sh

Then populate with sequenced data (see template).

Sequence stories

bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/sequence-stories.sh

Set initial statuses
- Wave 1 stories: status: ready-for-dev
- All other stories: status: backlog
- Epics: status: in-progress if any child story is ready-for-dev; else backlog
Emit handoff summary — list wave 1 stories by owned_scope for conflict-free parallel dispatch

Workflow — Update

When a story moves to done:

Remove it from any dependencies[] lists where it appears
Identify newly unblocked stories (dependencies now fully satisfied)
Promote them to ready-for-dev
Re-evaluate parent epic status
Write updated sprint-status.yaml

Parallel Set Assignment

Wave width (how many stories can run at once) is not a fixed number — it is the size of the dependency-free frontier at each topological level. There is no points budget or velocity ceiling.

Wave 1: all stories with no dependencies
Wave 2: all stories whose only dependencies are in wave 1
Wave N: all stories whose dependencies are fully in waves 1…(N-1)

Stories within a wave MUST have non-overlapping owned_scope to be safe for parallel dispatch. If two stories in the same wave share a file, split them into separate waves or document the conflict.

Status Lifecycle (view, not metric)

backlog → ready-for-dev → in-progress → review → done

This is a view of sequencing state, not a tracking instrument.
Transitions are triggered by external signals (dev tool reports, user command).
This skill never computes velocity, burndown, or completion rates from these statuses.

Scale-Adaptive Track Guidance

Track	Story count	Sprint-status behavior
Quick Flow	1–15	Single wave pass; minimal epic structure
BMAD Method	10–50+	Full wave assignment; epic grouping
Enterprise	30+	Multi-phase wave planning; dependency map documented in REFERENCE

Track is confirmed with the user before generating the status file.

Subagent Strategy

Pattern: Parallel dependency analysis
Use when: 15+ stories across 3+ epics

Agent	Task	Output
Agent 1	Parse all story files, extract dependency declarations	`bmad-output/context/dependency-raw.yaml`
Agent 2	Parse epic ordering from PRD/epics.md	`bmad-output/context/epic-order.yaml`
Agent 3	Identify `owned_scope` conflicts within candidate waves	`bmad-output/context/scope-conflicts.md`

Main context: merge outputs, run topological sort, write sprint-status.yaml.

Example subagent prompt

Task: Extract dependencies from all story files
Context: Read all *.story.md files under bmad-output/stories/
Objective: For each story, output its id and its dependencies[] list
Output: Write YAML list to bmad-output/context/dependency-raw.yaml

Format:
- id: "2.1.stripe-integration"
  dependencies: ["1.3.user-auth"]
- id: "2.2.payment-webhook"
  dependencies: ["2.1.stripe-integration"]

Scripts

`init-sprint-status.sh`

Scaffolds bmad-output/sprint-status.yaml from the template if it does not exist.

bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/init-sprint-status.sh \
  [project-name] [output-dir]

`sequence-stories.sh`

Orders stories: epics first (by epic number), then stories within each epic by dependency (topological), then assigns parallel_set integers.

bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/sequence-stories.sh \
  [sprint-status-file]

Template

${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/templates/sprint-status.template.yaml

Fields: epics[], stories[] (with id, title, status, dependencies, parallel_set, owned_scope). The template contains no velocity, burndown, or points fields.

Key Guidelines

Load context first — always read existing sprint-status.yaml before writing
Use TodoWrite to track multi-step sequencing workflows
Respect owned_scope — flag conflicts before assigning same-wave membership
No metrics — if a field resembles velocity, points, or burndown, remove it
Handoff clearly — conclude every Create/Update with the list of ready-for-dev stories and their owned_scope
Decision log — append sequencing decisions to bmad-output/decision-log.md

Part of the BMAD Planning & Orchestrator plugin — a Claude Code harness for the BMAD Method by the BMAD Code Organization (https://github.com/bmad-code-org/BMAD-METHOD). Implements the spirit of bmad-sprint-planning. All methodology credit belongs to the BMAD Code Organization.