bmad-sprint-planning

Name: bmad-sprint-planning
Author: aj-geddes

467stars73forks

How to install bmad-sprint-planning?

aj-geddes/claude-code-bmad-skills/bmad-sprint-planning

$npx -y skills add aj-geddes/claude-code-bmad-skills --skill bmad-sprint-planning

Installs into the current project.

Summary

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 → don

Files · 1

View on GitHub

SKILL.md

1	# BMAD Sprint Planning
2
3	Role: Sequencing & Handoff Bridge — Phase 4 orchestration
4	System-of-record: `bmad-output/sprint-status.yaml`
5
6	---
7
8	## What This Skill Does
9
10	1. Reads planning artifacts (PRD, architecture, epics, stories) from `bmad-output/`.
11	2. Derives a dependency graph across all stories.
12	3. Assigns each story a `parallel_set` (wave) — stories in the same wave have no mutual dependencies and can run concurrently.
13	4. Emits `bmad-output/sprint-status.yaml` using the canonical template.
14	5. Marks the first wave of stories `ready-for-dev`; all others remain `backlog`.
15	6. Optionally re-sequences on demand as stories are completed or new ones are added.
16
17	This skill does not write application code, run tests, lint, build, or review diffs.
18
19	---
20
21	## Three-Intent Operation
22
23	\| Intent \| Trigger phrase \| Action \|
24	\|--------\|---------------\|--------\|
25	\| Create \| "initialize sprint status", "first time" \| Scaffold fresh `sprint-status.yaml` from template \|
26	\| Update \| "re-sequence", "story X is done", "add story", "update wave" \| Mutate existing `sprint-status.yaml` in-place \|
27	\| Validate \| "check sequencing", "are dependencies correct", "show wave plan" \| Read and report without writing \|
28
29	---
30
31	## Workflow — Create
32
33	1. Load planning artifacts
34	```
35	Glob: bmad-output/*/.md, bmad-output/*/.yaml
36	```
37	Priority order: `epics.md` → `prd.md` → `architecture.md` → individual story files.
38
39	2. Extract epics and stories
40	- Parse all story IDs: format `{epic}.{story}.{slug}.story.md` (e.g., `2.1.stripe-integration.story.md`)
41	- Derive epic ordering from the epic list in `epics.md` or `prd.md`
42
43	3. Build dependency graph
44	- Read `dependencies[]` from each story's frontmatter or Dev Notes section
45	- Topological sort: stories with no unmet dependencies → wave 1; stories unblocked after wave 1 → wave 2; etc.
46
47	4. Initialize sprint-status.yaml
48	```bash
49	bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/init-sprint-status.sh
50	```
51	Then populate with sequenced data (see template).
52
53	5. Sequence stories
54	```bash
55	bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/sequence-stories.sh
56	```
57
58	6. Set initial statuses
59	- Wave 1 stories: `status: ready-for-dev`
60	- All other stories: `status: backlog`
61	- Epics: `status: in-progress` if any child story is ready-for-dev; else `backlog`
62
63	7. Emit handoff summary — list wave 1 stories by `owned_scope` for conflict-free parallel dispatch
64
65	---
66
67	## Workflow — Update
68
69	When a story moves to `done`:
70	1. Remove it from any `dependencies[]` lists where it appears
71	2. Identify newly unblocked stories (dependencies now fully satisfied)
72	3. Promote them to `ready-for-dev`
73	4. Re-evaluate parent epic status
74	5. Write updated `sprint-status.yaml`
75
76	---
77
78	## Parallel Set Assignment
79
80	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.
81
82	```
83	Wave 1: all stories with no dependencies
84	Wave 2: all stories whose only dependencies are in wave 1
85	Wave N: all stories whose dependencies are fully in waves 1…(N-1)
86	```
87
88	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.
89
90	---
91
92	## Status Lifecycle (view, not metric)
93
94	```
95	backlog → ready-for-dev → in-progress → review → done
96	```
97
98	- This is a view of sequencing state, not a tracking instrument.
99	- Transitions are triggered by external signals (dev tool reports, user command).
100	- This skill never computes velocity, burndown, or completion rates from these statuses.
101
102	---
103
104	## Scale-Adaptive Track Guidance
105
106	\| Track \| Story count \| Sprint-status behavior \|
107	\|-------\|-------------\|-

People who liked this also viewed

6 picks

Type

bmad-sprint-planning

467stars73forks

View on GitHub

How to install bmad-sprint-planning?

aj-geddes/claude-code-bmad-skills/bmad-sprint-planning

$npx -y skills add aj-geddes/claude-code-bmad-skills --skill bmad-sprint-planning

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# BMAD Sprint Planning
2
3	Role: Sequencing & Handoff Bridge — Phase 4 orchestration
4	System-of-record: `bmad-output/sprint-status.yaml`
5
6	---
7
8	## What This Skill Does
9
10	1. Reads planning artifacts (PRD, architecture, epics, stories) from `bmad-output/`.
11	2. Derives a dependency graph across all stories.
12	3. Assigns each story a `parallel_set` (wave) — stories in the same wave have no mutual dependencies and can run concurrently.
13	4. Emits `bmad-output/sprint-status.yaml` using the canonical template.
14	5. Marks the first wave of stories `ready-for-dev`; all others remain `backlog`.
15	6. Optionally re-sequences on demand as stories are completed or new ones are added.
16
17	This skill does not write application code, run tests, lint, build, or review diffs.
18
19	---
20
21	## Three-Intent Operation
22
23	\| Intent \| Trigger phrase \| Action \|
24	\|--------\|---------------\|--------\|
25	\| Create \| "initialize sprint status", "first time" \| Scaffold fresh `sprint-status.yaml` from template \|
26	\| Update \| "re-sequence", "story X is done", "add story", "update wave" \| Mutate existing `sprint-status.yaml` in-place \|
27	\| Validate \| "check sequencing", "are dependencies correct", "show wave plan" \| Read and report without writing \|
28
29	---
30
31	## Workflow — Create
32
33	1. Load planning artifacts
34	```
35	Glob: bmad-output/*/.md, bmad-output/*/.yaml
36	```
37	Priority order: `epics.md` → `prd.md` → `architecture.md` → individual story files.
38
39	2. Extract epics and stories
40	- Parse all story IDs: format `{epic}.{story}.{slug}.story.md` (e.g., `2.1.stripe-integration.story.md`)
41	- Derive epic ordering from the epic list in `epics.md` or `prd.md`
42
43	3. Build dependency graph
44	- Read `dependencies[]` from each story's frontmatter or Dev Notes section
45	- Topological sort: stories with no unmet dependencies → wave 1; stories unblocked after wave 1 → wave 2; etc.
46
47	4. Initialize sprint-status.yaml
48	```bash
49	bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/init-sprint-status.sh
50	```
51	Then populate with sequenced data (see template).
52
53	5. Sequence stories
54	```bash
55	bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-sprint-planning/scripts/sequence-stories.sh
56	```
57
58	6. Set initial statuses
59	- Wave 1 stories: `status: ready-for-dev`
60	- All other stories: `status: backlog`
61	- Epics: `status: in-progress` if any child story is ready-for-dev; else `backlog`
62
63	7. Emit handoff summary — list wave 1 stories by `owned_scope` for conflict-free parallel dispatch
64
65	---
66
67	## Workflow — Update
68
69	When a story moves to `done`:
70	1. Remove it from any `dependencies[]` lists where it appears
71	2. Identify newly unblocked stories (dependencies now fully satisfied)
72	3. Promote them to `ready-for-dev`
73	4. Re-evaluate parent epic status
74	5. Write updated `sprint-status.yaml`
75
76	---
77
78	## Parallel Set Assignment
79
80	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.
81
82	```
83	Wave 1: all stories with no dependencies
84	Wave 2: all stories whose only dependencies are in wave 1
85	Wave N: all stories whose dependencies are fully in waves 1…(N-1)
86	```
87
88	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.
89
90	---
91
92	## Status Lifecycle (view, not metric)
93
94	```
95	backlog → ready-for-dev → in-progress → review → done
96	```
97
98	- This is a view of sequencing state, not a tracking instrument.
99	- Transitions are triggered by external signals (dev tool reports, user command).
100	- This skill never computes velocity, burndown, or completion rates from these statuses.
101
102	---
103
104	## Scale-Adaptive Track Guidance
105
106	\| Track \| Story count \| Sprint-status behavior \|
107	\|-------\|-------------\|-

People who liked this also viewed

6 picks

Type