kiro-spec-batch

Name: kiro-spec-batch
Author: gotalab

3.6kstars271forks

How to install kiro-spec-batch?

gotalab/cc-sdd/kiro-spec-batch

$npx -y skills add gotalab/cc-sdd --skill kiro-spec-batch

Installs into the current project.

Summary

Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.

Files · 1

View on GitHub

SKILL.md

1	# Spec Batch
2
3	<background_information>
4	- Success Criteria:
5	- All features have complete spec files (spec.json, requirements.md, design.md, tasks.md)
6	- Dependency ordering respected (upstream specs complete before downstream)
7	- Independent features processed in parallel via sub-agent dispatch
8	- Cross-spec consistency verified (data models, interfaces, naming)
9	- Mixed roadmap context understood without breaking `## Specs (dependency order)` parsing
10	- Controller context stays lightweight (sub-agents do the heavy work)
11	</background_information>
12
13	<instructions>
14
15	## Step 1: Read Roadmap and Validate
16
17	1. Read `{{KIRO_DIR}}/steering/roadmap.md`
18	2. Parse the `## Specs (dependency order)` section to extract:
19	- Feature names
20	- One-line descriptions
21	- Dependencies for each feature
22	- Completion status (`[x]` = done, `[ ]` = pending)
23	3. If present, also read for context:
24	- `## Existing Spec Updates`
25	- `## Direct Implementation Candidates`
26	Do not include these in dependency-wave execution; they are awareness-only inputs for sequencing and consistency review.
27	4. For each pending feature in `## Specs (dependency order)`, verify `{{KIRO_DIR}}/specs/<feature>/brief.md` exists
28	5. If any brief.md is missing, stop and report: "Missing brief.md for: [list]. Run `/kiro-discovery` to generate briefs first."
29
30	## Step 2: Build Dependency Waves
31
32	Group pending features into waves based on dependencies:
33
34	- Wave 1: Features with no dependencies (or all dependencies already completed `[x]`)
35	- Wave 2: Features whose dependencies are all in Wave 1 or already completed
36	- Wave N: Features whose dependencies are all in earlier waves or already completed
37
38	Display the execution plan:
39	```
40	Spec Batch Plan:
41	Wave 1 (parallel): app-foundation
42	Wave 2 (parallel): block-editor, page-management
43	Wave 3 (parallel): sidebar-navigation, database-views
44	Wave 4 (parallel): cli-integration
45	Total: 6 specs across 4 waves
46	```
47
48	If roadmap contains `## Existing Spec Updates` or `## Direct Implementation Candidates`, mention them separately as non-batch items so the user can see the whole decomposition.
49
50	## Step 3: Execute Waves
51
52	For each wave, dispatch all features in the wave as parallel sub-agents.
53
54	For each feature in the wave, spawn a sub-agent with this task:
55
56	```
57	Create a complete specification for feature "{feature-name}".
58
59	1. Read the brief at {{KIRO_DIR}}/specs/{feature-name}/brief.md for feature context
60	2. Read the roadmap at {{KIRO_DIR}}/steering/roadmap.md for project context
61	3. Execute the full spec pipeline. For each phase, read the corresponding skill's SKILL.md for complete instructions (templates, rules, review gates):
62	a. Initialize: Read .agent/skills/kiro-spec-init/SKILL.md, then create spec.json and requirements.md
63	b. Generate requirements: Read .agent/skills/kiro-spec-requirements/SKILL.md, then follow its steps
64	c. Generate design: Read .agent/skills/kiro-spec-design/SKILL.md, then follow its steps
65	d. Generate tasks: Read .agent/skills/kiro-spec-tasks/SKILL.md, then follow its steps
66	4. Set all approvals to true in spec.json (auto-approve mode, equivalent of -y flag)
67	5. Report completion with file list and task count
68	```
69
70	Antigravity does not support programmatic sub-agent dispatch. Execute features in the wave sequentially in the main context.
71
72	After all sub-agents in the wave complete:
73	1. Verify each feature has: spec.json, requirements.md, design.md, tasks.md
74	2. If any feature failed, report the error and continue with features that succeeded
75	3. Display wave completion: "Wave N complete: [features]. Files verified."
76	4. Proceed to next wave
77
78	## Step 4: Cross-Spec Review
79
80	After all waves complete, perform a cross-spec consistency review. This is the highest-value quality gate -- it catches issues that per-spec review gates cannot.
81
82	Read ALL generated specs and check for consistency across the entire project:
83	- `{{KIRO_DIR}}/specs/*/design.md` (primary: contains interfaces, data models, architecture)
84	- `{{KIRO_DIR}}/specs/*/requirements.md` (for scope and acceptance criteria)
85	- `{{KIRO_DIR}}/specs/*/tasks.md` (for boundary annotations only -- read _Boundary:_ lines, skip task descriptions)
86	- `{{KIRO_DIR}}/steering/roadmap.md`
87
88	Reading priority: Focus on design.md files (they contain interfaces, data models, architecture). For requirements.md, focus on section headings and acceptance criteria. For tasks.md, focus on _Boundary:_ annotations.
89
90	Check:
91	1. Data model consistency: Same entities defined consistently across specs (field names, types, relationships)
92	2. Interface alignment: Where spec A outputs what spec B consumes, do contracts match exactly?
93	3. No duplicate functionality: Any capability specified in more than one spec?
94	4. Dependency completeness: Every design.md r

People who liked this also viewed

6 picks

Type

kiro-spec-batch

3.6kstars271forks

View on GitHub

How to install kiro-spec-batch?

gotalab/cc-sdd/kiro-spec-batch

$npx -y skills add gotalab/cc-sdd --skill kiro-spec-batch

Installs into the current project.

Summary

Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.

Files · 1

View on GitHub

SKILL.md

1	# Spec Batch
2
3	<background_information>
4	- Success Criteria:
5	- All features have complete spec files (spec.json, requirements.md, design.md, tasks.md)
6	- Dependency ordering respected (upstream specs complete before downstream)
7	- Independent features processed in parallel via sub-agent dispatch
8	- Cross-spec consistency verified (data models, interfaces, naming)
9	- Mixed roadmap context understood without breaking `## Specs (dependency order)` parsing
10	- Controller context stays lightweight (sub-agents do the heavy work)
11	</background_information>
12
13	<instructions>
14
15	## Step 1: Read Roadmap and Validate
16
17	1. Read `{{KIRO_DIR}}/steering/roadmap.md`
18	2. Parse the `## Specs (dependency order)` section to extract:
19	- Feature names
20	- One-line descriptions
21	- Dependencies for each feature
22	- Completion status (`[x]` = done, `[ ]` = pending)
23	3. If present, also read for context:
24	- `## Existing Spec Updates`
25	- `## Direct Implementation Candidates`
26	Do not include these in dependency-wave execution; they are awareness-only inputs for sequencing and consistency review.
27	4. For each pending feature in `## Specs (dependency order)`, verify `{{KIRO_DIR}}/specs/<feature>/brief.md` exists
28	5. If any brief.md is missing, stop and report: "Missing brief.md for: [list]. Run `/kiro-discovery` to generate briefs first."
29
30	## Step 2: Build Dependency Waves
31
32	Group pending features into waves based on dependencies:
33
34	- Wave 1: Features with no dependencies (or all dependencies already completed `[x]`)
35	- Wave 2: Features whose dependencies are all in Wave 1 or already completed
36	- Wave N: Features whose dependencies are all in earlier waves or already completed
37
38	Display the execution plan:
39	```
40	Spec Batch Plan:
41	Wave 1 (parallel): app-foundation
42	Wave 2 (parallel): block-editor, page-management
43	Wave 3 (parallel): sidebar-navigation, database-views
44	Wave 4 (parallel): cli-integration
45	Total: 6 specs across 4 waves
46	```
47
48	If roadmap contains `## Existing Spec Updates` or `## Direct Implementation Candidates`, mention them separately as non-batch items so the user can see the whole decomposition.
49
50	## Step 3: Execute Waves
51
52	For each wave, dispatch all features in the wave as parallel sub-agents.
53
54	For each feature in the wave, spawn a sub-agent with this task:
55
56	```
57	Create a complete specification for feature "{feature-name}".
58
59	1. Read the brief at {{KIRO_DIR}}/specs/{feature-name}/brief.md for feature context
60	2. Read the roadmap at {{KIRO_DIR}}/steering/roadmap.md for project context
61	3. Execute the full spec pipeline. For each phase, read the corresponding skill's SKILL.md for complete instructions (templates, rules, review gates):
62	a. Initialize: Read .agent/skills/kiro-spec-init/SKILL.md, then create spec.json and requirements.md
63	b. Generate requirements: Read .agent/skills/kiro-spec-requirements/SKILL.md, then follow its steps
64	c. Generate design: Read .agent/skills/kiro-spec-design/SKILL.md, then follow its steps
65	d. Generate tasks: Read .agent/skills/kiro-spec-tasks/SKILL.md, then follow its steps
66	4. Set all approvals to true in spec.json (auto-approve mode, equivalent of -y flag)
67	5. Report completion with file list and task count
68	```
69
70	Antigravity does not support programmatic sub-agent dispatch. Execute features in the wave sequentially in the main context.
71
72	After all sub-agents in the wave complete:
73	1. Verify each feature has: spec.json, requirements.md, design.md, tasks.md
74	2. If any feature failed, report the error and continue with features that succeeded
75	3. Display wave completion: "Wave N complete: [features]. Files verified."
76	4. Proceed to next wave
77
78	## Step 4: Cross-Spec Review
79
80	After all waves complete, perform a cross-spec consistency review. This is the highest-value quality gate -- it catches issues that per-spec review gates cannot.
81
82	Read ALL generated specs and check for consistency across the entire project:
83	- `{{KIRO_DIR}}/specs/*/design.md` (primary: contains interfaces, data models, architecture)
84	- `{{KIRO_DIR}}/specs/*/requirements.md` (for scope and acceptance criteria)
85	- `{{KIRO_DIR}}/specs/*/tasks.md` (for boundary annotations only -- read _Boundary:_ lines, skip task descriptions)
86	- `{{KIRO_DIR}}/steering/roadmap.md`
87
88	Reading priority: Focus on design.md files (they contain interfaces, data models, architecture). For requirements.md, focus on section headings and acceptance criteria. For tasks.md, focus on _Boundary:_ annotations.
89
90	Check:
91	1. Data model consistency: Same entities defined consistently across specs (field names, types, relationships)
92	2. Interface alignment: Where spec A outputs what spec B consumes, do contracts match exactly?
93	3. No duplicate functionality: Any capability specified in more than one spec?
94	4. Dependency completeness: Every design.md r

People who liked this also viewed

6 picks

Type