kiro-spec-batch
Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.
gotalab · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add gotalab/cc-sdd --skill kiro-spec-batch技能说明
name: kiro-spec-batch description: Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.
Spec Batch
<background_information>
- Success Criteria:
- All features have complete spec files (spec.json, requirements.md, design.md, tasks.md)
- Dependency ordering respected (upstream specs complete before downstream)
- Independent features processed in parallel via sub-agent dispatch
- Cross-spec consistency verified (data models, interfaces, naming)
- Mixed roadmap context understood without breaking
## Specs (dependency order)parsing - Controller context stays lightweight (sub-agents do the heavy work) </background_information>
Step 1: Read Roadmap and Validate
- Read
{{KIRO_DIR}}/steering/roadmap.md - Parse the
## Specs (dependency order)section to extract:- Feature names
- One-line descriptions
- Dependencies for each feature
- Completion status (
[x]= done,[ ]= pending)
- If present, also read for context:
## Existing Spec Updates## Direct Implementation CandidatesDo not include these in dependency-wave execution; they are awareness-only inputs for sequencing and consistency review.
- For each pending feature in
## Specs (dependency order), verify{{KIRO_DIR}}/specs/<feature>/brief.mdexists - If any brief.md is missing, stop and report: "Missing brief.md for: [list]. Run
/kiro-discoveryto generate briefs first."
Step 2: Build Dependency Waves
Group pending features into waves based on dependencies:
- Wave 1: Features with no dependencies (or all dependencies already completed
[x]) - Wave 2: Features whose dependencies are all in Wave 1 or already completed
- Wave N: Features whose dependencies are all in earlier waves or already completed
Display the execution plan:
Spec Batch Plan:
Wave 1 (parallel): app-foundation
Wave 2 (parallel): block-editor, page-management
Wave 3 (parallel): sidebar-navigation, database-views
Wave 4 (parallel): cli-integration
Total: 6 specs across 4 waves
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.
Step 3: Execute Waves
For each wave, dispatch all features in the wave as parallel sub-agents.
Before dispatch, resolve ../kiro-spec-init/SKILL.md, ../kiro-spec-requirements/SKILL.md, ../kiro-spec-design/SKILL.md, and ../kiro-spec-tasks/SKILL.md relative to this skill’s installed directory. Pass their absolute paths in the prompt below so the worker does not need the parent’s skill-location context.
For each feature in the wave, spawn a sub-agent with this task:
Create a complete specification for feature "{feature-name}".
Bind the feature argument in each phase to "{feature-name}" (including `$1` or `{feature}` references). This batch uses the existing fast-track mode: supply `-y` to design and tasks before entering their approval checks. Required phase review gates still apply.
1. Read the brief at {{KIRO_DIR}}/specs/{feature-name}/brief.md for feature context
2. Read the roadmap at {{KIRO_DIR}}/steering/roadmap.md for project context
3. Execute the full spec pipeline. For each phase, read the corresponding skill's SKILL.md for complete instructions (templates, rules, review gates):
a. Initialize: If spec.json already exists, reuse that spec without reinitializing or renaming it. Otherwise read {spec-init-skill-path}; use the brief as the project description and initialize spec.json and requirements.md in the existing brief directory. Later phases may update their own artifacts.
b. Generate requirements: Read {spec-requirements-skill-path} and execute for feature "{feature-name}"
c. Generate design: Read {spec-design-skill-path} and execute with arguments "{feature-name} -y", including required design review
d. Generate tasks: Read {spec-tasks-skill-path} and execute with arguments "{feature-name} -y", including required task review
4. Let each successful phase record its approvals through its documented fast-track flow. If a phase review fails or needs human input, stop this feature and report the blocker; do not force its approvals to true
5. Report completion with file list and task count
If native subagent tools are unavailable or disabled in the current Antigravity session, execute features in the wave sequentially in the main context and report that no parallel subagents were used.
After all sub-agents in the wave complete:
- Verify each feature has: spec.json, requirements.md, design.md, tasks.md
- If any feature failed, report the error and continue with features that succeeded
- Display wave completion: "Wave N complete: [features]. Files verified."
- Proceed to next wave
Step 4: Cross-Spec Review
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.
Read ALL generated specs and check for consistency across the entire project:
{{KIRO_DIR}}/specs/*/design.md(primary: contains interfaces, data models, architecture){{KIRO_DIR}}/specs/*/requirements.md(for scope and acceptance criteria){{KIRO_DIR}}/specs/*/tasks.md(for boundary annotations only -- read Boundary: lines, skip task descriptions){{KIRO_DIR}}/steering/roadmap.md
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.
Check:
- Data model consistency: Same entities defined consistently across specs (field names, types, relationships)
- Interface alignment: Where spec A outputs what spec B consumes, do contracts match exactly?
- No duplicate functionality: Any capability specified in