bmad-epics-and-stories

Name: bmad-epics-and-stories
Author: aj-geddes

467stars73forks

How to install bmad-epics-and-stories?

aj-geddes/claude-code-bmad-skills/bmad-epics-and-stories

$npx -y skills add aj-geddes/claude-code-bmad-skills --skill bmad-epics-and-stories

Installs into the current project.

Summary

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 CITATION

Files · 1

View on GitHub

SKILL.md

1	# BMAD Epics & Stories
2
3	Track-adaptive sharding. Turn approved planning docs into the executable backlog: one
4	`epics.md` map plus per-story context objects. This is the final planning step — the next
5	thing that touches a story is an external dev tool, not this plugin.
6
7	Persona flavor: the Architect (Winston) shards; the PM (John) confirms scope. Lightweight
8	flavor only — this is a workflow.
9
10	## Scope Law (read first)
11
12	This skill PLANS. It NEVER writes application code, runs tests, lints, checks coverage, or
13	builds. The last artifact it emits is a story file marked `status: ready-for-dev`. Acceptance
14	Criteria, a Testing strategy, and Dev Notes are planning outputs you author. Executing
15	tests or writing implementation is out of scope — plan it and hand it off. If tempted to
16	"implement" or "run the suite", STOP.
17
18	## Inputs (load these first)
19
20	\| File \| Why \|
21	\|------\|-----\|
22	\| `bmad-output/project-context.md` \| Project constitution — load every run \|
23	\| `bmad-output/prd.md` \| Functional requirements, epic intent \|
24	\| `bmad-output/architecture.md` \| Tech stack, components, module boundaries \|
25	\| `bmad-output/ux-design.md` (if present) \| UI acceptance details \|
26	\| `bmad-output/decision-log.md` \| Threaded decisions to honor \|
27	\| existing `bmad-output/stories/*.story.md` \| Learnings + ID continuity \|
28
29	Output folder default: `bmad-output/` (honor user override). Stories go in
30	`bmad-output/stories/`, the map in `bmad-output/epics.md`.
31
32	## Three Intents
33
34	- Create — shard PRD+architecture into `epics.md`, then compile story files.
35	- Update — revise an existing story (scope, ACs, learnings). Respect LOCKED sections.
36	- Validate — check a draft story against the Context Object contract; report gaps.
37
38	Ask which intent if ambiguous. Do not silently regenerate existing stories.
39
40	## Tracks (never numbered levels)
41
42	Pick interactively; the heuristic suggests, the user confirms.
43
44	- Quick Flow (1-15 stories) — tech-spec only; shard straight to stories, thin `epics.md`.
45	- BMad Method (10-50+) — PRD + Architecture (+ optional UX); full epic map then stories.
46	- Enterprise (30+) — adds Security + DevOps story streams.
47
48	## Sizing Rule (count-based, no points)
49
50	A story must be small enough for one agent session — roughly 2-8h, one dev-day max.
51	If a story is larger, split it; never inflate scope to fill a sprint. There are NO
52	Fibonacci points, NO velocity, NO burndown. Delivery is tracked by COUNT: stories remaining
53	vs. completion rate. See [REFERENCE.md](REFERENCE.md) for the split heuristics.
54
55	## Workflow — Create
56
57	1. Load context — read the inputs above; note the chosen track.
58	2. Derive epics — group PRD requirements into epics (each a shippable slice of value).
59	Write `bmad-output/epics.md` from [templates/epic.template.md](templates/epic.template.md):
60	epic goal, in-scope requirements (cited), ordered story list, cross-epic dependencies.
61	3. Confirm the epic map with the user before compiling stories.
62	4. Generate IDs — `bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-epics-and-stories/scripts/generate-story-id.sh <epic-number>`
63	gives the next `{epic}.{story}` and a slug stub. Filename: `{epic}.{story}.{slug}.story.md`.
64	5. Compile each story as a CONTEXT OBJECT from
65	[templates/story.template.md](templates/story.template.md). It MUST be self-contained
66	(~8K tokens) so a dev agent needs no other file. Fill every section:
67	- Story — as-a / I-want / so-that.
68	- Acceptance Criteria — numbered, testable. LOCKED.
69	- Tasks/Subtasks — checkboxes, each mapped to an AC via `(AC: #N)`.
70	- Dev Notes — concrete guidance WITH SOURCE CITATIONS (e.g.
71	`[Source: architecture.md#auth-service]`, `[Source: prd.md#FR-12]`). LOCKED.
72	- Testing — strategy only (what to verify, test types, fixtures). No execution. *LOCKED.

People who liked this also viewed

6 picks

Type

bmad-epics-and-stories

467stars73forks

View on GitHub

How to install bmad-epics-and-stories?

aj-geddes/claude-code-bmad-skills/bmad-epics-and-stories

$npx -y skills add aj-geddes/claude-code-bmad-skills --skill bmad-epics-and-stories

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# BMAD Epics & Stories
2
3	Track-adaptive sharding. Turn approved planning docs into the executable backlog: one
4	`epics.md` map plus per-story context objects. This is the final planning step — the next
5	thing that touches a story is an external dev tool, not this plugin.
6
7	Persona flavor: the Architect (Winston) shards; the PM (John) confirms scope. Lightweight
8	flavor only — this is a workflow.
9
10	## Scope Law (read first)
11
12	This skill PLANS. It NEVER writes application code, runs tests, lints, checks coverage, or
13	builds. The last artifact it emits is a story file marked `status: ready-for-dev`. Acceptance
14	Criteria, a Testing strategy, and Dev Notes are planning outputs you author. Executing
15	tests or writing implementation is out of scope — plan it and hand it off. If tempted to
16	"implement" or "run the suite", STOP.
17
18	## Inputs (load these first)
19
20	\| File \| Why \|
21	\|------\|-----\|
22	\| `bmad-output/project-context.md` \| Project constitution — load every run \|
23	\| `bmad-output/prd.md` \| Functional requirements, epic intent \|
24	\| `bmad-output/architecture.md` \| Tech stack, components, module boundaries \|
25	\| `bmad-output/ux-design.md` (if present) \| UI acceptance details \|
26	\| `bmad-output/decision-log.md` \| Threaded decisions to honor \|
27	\| existing `bmad-output/stories/*.story.md` \| Learnings + ID continuity \|
28
29	Output folder default: `bmad-output/` (honor user override). Stories go in
30	`bmad-output/stories/`, the map in `bmad-output/epics.md`.
31
32	## Three Intents
33
34	- Create — shard PRD+architecture into `epics.md`, then compile story files.
35	- Update — revise an existing story (scope, ACs, learnings). Respect LOCKED sections.
36	- Validate — check a draft story against the Context Object contract; report gaps.
37
38	Ask which intent if ambiguous. Do not silently regenerate existing stories.
39
40	## Tracks (never numbered levels)
41
42	Pick interactively; the heuristic suggests, the user confirms.
43
44	- Quick Flow (1-15 stories) — tech-spec only; shard straight to stories, thin `epics.md`.
45	- BMad Method (10-50+) — PRD + Architecture (+ optional UX); full epic map then stories.
46	- Enterprise (30+) — adds Security + DevOps story streams.
47
48	## Sizing Rule (count-based, no points)
49
50	A story must be small enough for one agent session — roughly 2-8h, one dev-day max.
51	If a story is larger, split it; never inflate scope to fill a sprint. There are NO
52	Fibonacci points, NO velocity, NO burndown. Delivery is tracked by COUNT: stories remaining
53	vs. completion rate. See [REFERENCE.md](REFERENCE.md) for the split heuristics.
54
55	## Workflow — Create
56
57	1. Load context — read the inputs above; note the chosen track.
58	2. Derive epics — group PRD requirements into epics (each a shippable slice of value).
59	Write `bmad-output/epics.md` from [templates/epic.template.md](templates/epic.template.md):
60	epic goal, in-scope requirements (cited), ordered story list, cross-epic dependencies.
61	3. Confirm the epic map with the user before compiling stories.
62	4. Generate IDs — `bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-epics-and-stories/scripts/generate-story-id.sh <epic-number>`
63	gives the next `{epic}.{story}` and a slug stub. Filename: `{epic}.{story}.{slug}.story.md`.
64	5. Compile each story as a CONTEXT OBJECT from
65	[templates/story.template.md](templates/story.template.md). It MUST be self-contained
66	(~8K tokens) so a dev agent needs no other file. Fill every section:
67	- Story — as-a / I-want / so-that.
68	- Acceptance Criteria — numbered, testable. LOCKED.
69	- Tasks/Subtasks — checkboxes, each mapped to an AC via `(AC: #N)`.
70	- Dev Notes — concrete guidance WITH SOURCE CITATIONS (e.g.
71	`[Source: architecture.md#auth-service]`, `[Source: prd.md#FR-12]`). LOCKED.
72	- Testing — strategy only (what to verify, test types, fixtures). No execution. *LOCKED.

People who liked this also viewed

6 picks

Type