bmad-init

Name: bmad-init
Author: aj-geddes

467stars73forks

How to install bmad-init?

aj-geddes/claude-code-bmad-skills/bmad-init

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

Installs into the current project.

Summary

Initialize a BMAD planning workspace: pick a scale-adaptive TRACK (Quick Flow / BMad Method / Enterprise) interactively, then scaffold the output folder, a config file, an empty decision-log.md, and a project-context.md "constitution". Use when the user says "initialize BMAD", "s

Files · 1

View on GitHub

SKILL.md

1	# BMAD Init — Workspace Scaffolder
2
3	Set up the planning workspace and choose the TRACK that scales the rest of the BMAD
4	planning workflows. This is a planning skill: it creates folders and seed
5	documents only. It never writes application code, runs tests, or builds anything.
6
7	## What it produces
8
9	Under the configured output folder (default `bmad-output/`):
10
11	```
12	bmad-output/
13	├── config.yaml # project name, track, output paths, languages
14	├── decision-log.md # empty threaded decision log (grows across workflows)
15	├── project-context.md # the project "constitution" loaded by every later skill
16	└── stories/ # empty; future story files land here
17	```
18
19	`config.yaml` is the single source of truth other skills read to find the output
20	folder and the chosen track.
21
22	## The three TRACKS (never numbered Levels)
23
24	\| Track \| Story count \| Planning artifacts \|
25	\|-------\|-------------\|--------------------\|
26	\| Quick Flow \| 1–15 stories \| tech-spec only \|
27	\| BMad Method \| 10–50+ stories \| PRD + Architecture (+ optional UX) \|
28	\| Enterprise \| 30+ stories \| PRD + Architecture + Security + DevOps planning \|
29
30	The track is a planning-need decision, not a points/velocity decision. Story
31	count is a rough signal only; let scope, cross-team coordination, and risk drive the
32	call. A heuristic may suggest a default — the user always confirms.
33
34	## Workflow
35
36	1. Check for an existing workspace. Glob for `bmad-output/config.yaml` (or a
37	custom output folder if the user names one). If it exists, read it and ask whether
38	to keep, re-run idempotently (safe — existing files are preserved), or change the
39	track. Do not clobber a populated decision-log.md or project-context.md.
40
41	2. Gather rough scope signals in conversation (don't interrogate):
42	- One-line project description.
43	- Roughly how many distinct pieces of work / stories? (ranges are fine)
44	- Multiple teams or just one builder?
45	- Hard compliance / security / infra requirements?
46
47	3. Suggest a track. Run the helper to print the three tracks and a suggested
48	default, then state your recommendation and ask the user to confirm or override:
49
50	```bash
51	bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-init/scripts/select-track.sh" --stories <N> --teams <one\|many> --compliance <yes\|no>
52	```
53
54	Heuristic the helper applies (you may reason past it):
55	- compliance/infra = yes, or 30+ stories → Enterprise
56	- 10+ stories, or PRD/architecture clearly needed → BMad Method
57	- otherwise → Quick Flow
58
59	4. Scaffold. Once the user confirms name + track, run:
60
61	```bash
62	bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-init/scripts/init-project.sh" \
63	--name "<project name>" \
64	--track <quick-flow\|bmad-method\|enterprise> \
65	--output "bmad-output"
66	```
67
68	The script is idempotent: it creates missing folders and seeds any missing
69	template files, but never overwrites `decision-log.md` or `project-context.md`
70	if they already contain content. It always (re)writes `config.yaml`.
71
72	5. Open the constitution. Walk the user through filling the first sections of
73	`project-context.md` (project goal, primary users, constraints, non-goals). This
74	is the document every downstream skill loads, so a few good sentences here pay off.
75	Record the track choice and rationale as the first entry in `decision-log.md`.
76
77	6. Hand off. Recommend the next planning step based on track:
78	- Quick Flow → tech-spec, then sprint-planning / story creation.
79	- BMad Method → product brief → PRD → architecture.
80	- Enterprise → product brief → PRD → architecture (+ security & DevOps planning).
81
82	## Three intents
83
84	- Create — fresh workspace (the common case).
85	- Update — change the track or rename the project: edit `config.yaml` and append
86	the change to `decision-log.md` with a date and reason. Do not wipe other files.
87	- Validate — confirm the workspace is well-formed:
88	```bash
89	bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-init/scripts/init-project.sh" --validate --output "bmad-output"
90	```
91
92	## Guardrails
93
94	- No numbered Levels anywhere — only the three named tracks.
95	- No story points, velocity, burndown. Delivery is count-based (stories
96	remaining / complet

People who liked this also viewed

6 picks

Type

bmad-init

467stars73forks

View on GitHub

How to install bmad-init?

aj-geddes/claude-code-bmad-skills/bmad-init

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# BMAD Init — Workspace Scaffolder
2
3	Set up the planning workspace and choose the TRACK that scales the rest of the BMAD
4	planning workflows. This is a planning skill: it creates folders and seed
5	documents only. It never writes application code, runs tests, or builds anything.
6
7	## What it produces
8
9	Under the configured output folder (default `bmad-output/`):
10
11	```
12	bmad-output/
13	├── config.yaml # project name, track, output paths, languages
14	├── decision-log.md # empty threaded decision log (grows across workflows)
15	├── project-context.md # the project "constitution" loaded by every later skill
16	└── stories/ # empty; future story files land here
17	```
18
19	`config.yaml` is the single source of truth other skills read to find the output
20	folder and the chosen track.
21
22	## The three TRACKS (never numbered Levels)
23
24	\| Track \| Story count \| Planning artifacts \|
25	\|-------\|-------------\|--------------------\|
26	\| Quick Flow \| 1–15 stories \| tech-spec only \|
27	\| BMad Method \| 10–50+ stories \| PRD + Architecture (+ optional UX) \|
28	\| Enterprise \| 30+ stories \| PRD + Architecture + Security + DevOps planning \|
29
30	The track is a planning-need decision, not a points/velocity decision. Story
31	count is a rough signal only; let scope, cross-team coordination, and risk drive the
32	call. A heuristic may suggest a default — the user always confirms.
33
34	## Workflow
35
36	1. Check for an existing workspace. Glob for `bmad-output/config.yaml` (or a
37	custom output folder if the user names one). If it exists, read it and ask whether
38	to keep, re-run idempotently (safe — existing files are preserved), or change the
39	track. Do not clobber a populated decision-log.md or project-context.md.
40
41	2. Gather rough scope signals in conversation (don't interrogate):
42	- One-line project description.
43	- Roughly how many distinct pieces of work / stories? (ranges are fine)
44	- Multiple teams or just one builder?
45	- Hard compliance / security / infra requirements?
46
47	3. Suggest a track. Run the helper to print the three tracks and a suggested
48	default, then state your recommendation and ask the user to confirm or override:
49
50	```bash
51	bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-init/scripts/select-track.sh" --stories <N> --teams <one\|many> --compliance <yes\|no>
52	```
53
54	Heuristic the helper applies (you may reason past it):
55	- compliance/infra = yes, or 30+ stories → Enterprise
56	- 10+ stories, or PRD/architecture clearly needed → BMad Method
57	- otherwise → Quick Flow
58
59	4. Scaffold. Once the user confirms name + track, run:
60
61	```bash
62	bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-init/scripts/init-project.sh" \
63	--name "<project name>" \
64	--track <quick-flow\|bmad-method\|enterprise> \
65	--output "bmad-output"
66	```
67
68	The script is idempotent: it creates missing folders and seeds any missing
69	template files, but never overwrites `decision-log.md` or `project-context.md`
70	if they already contain content. It always (re)writes `config.yaml`.
71
72	5. Open the constitution. Walk the user through filling the first sections of
73	`project-context.md` (project goal, primary users, constraints, non-goals). This
74	is the document every downstream skill loads, so a few good sentences here pay off.
75	Record the track choice and rationale as the first entry in `decision-log.md`.
76
77	6. Hand off. Recommend the next planning step based on track:
78	- Quick Flow → tech-spec, then sprint-planning / story creation.
79	- BMad Method → product brief → PRD → architecture.
80	- Enterprise → product brief → PRD → architecture (+ security & DevOps planning).
81
82	## Three intents
83
84	- Create — fresh workspace (the common case).
85	- Update — change the track or rename the project: edit `config.yaml` and append
86	the change to `decision-log.md` with a date and reason. Do not wipe other files.
87	- Validate — confirm the workspace is well-formed:
88	```bash
89	bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-init/scripts/init-project.sh" --validate --output "bmad-output"
90	```
91
92	## Guardrails
93
94	- No numbered Levels anywhere — only the three named tracks.
95	- No story points, velocity, burndown. Delivery is count-based (stories
96	remaining / complet

People who liked this also viewed

6 picks

Type