📋
AI EngineeringTypeScript

Spec Batch

by gotalab

Spec Batch is an AI Engineering skill for Claude Code, published by gotalab in cc-sdd.

3.6K stars275 forkson gotalab/cc-sddAdded 2026/08/16Repository updated 2026/05/20
View source on GitHubDownload repo ZIP
agent-skillsclaude-codecodexcursorgemini-cligithub-copilotkiroopencodesddspec-driven-developmentsteeringsubagents
Install in seconds
Install Spec Batch
Copy Spec Batch into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/gotalab/cc-sdd/tree/main/tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-spec-batch ~/.claude/skills/kiro-spec-batch

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/gotalab/cc-sdd.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-spec-batch/SKILL.md in gotalab/cc-sdd
Installs to
~/.claude/skills/kiro-spec-batch
Collection
One of 24 skills cataloged from this repository
Category
AI Engineering — 2451 skills

What Spec Batch does

Spec Batch creates complete specification files (spec.json, requirements.md, design.md, tasks.md) for all features in a roadmap by dispatching sub-agents in dependency-ordered waves. Use it when you need to generate specs for a whole project roadmap and verify cross-spec consistency.

Spec Batch is cataloged under AI Engineering on DirSkills. Spec Batch comes from a repository tagged agent-skills, claude-code, codex, cursor and gemini-cli.

Documentation

README

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

This is the opening of the README. Read the full README on GitHub.

Commands Spec Batch provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /kiro-discovery
  • /kiro-impl
  • /kiro-spec-quick

Frequently asked about Spec Batch

  • What else does gotalab publish alongside Spec Batch?

    Spec Batch is one of 24 skills that DirSkills catalogs from gotalab/cc-sdd, the repository it ships in. Its siblings there include CC-SDD New Agent Integration, Implementation Gap Validation and Implementation Integration Validation. Each one is a separate skill with its own page in this directory, installs the same way Spec Batch does, and is maintained by gotalab in that same repository. The rest of the collection is listed on the gotalab/cc-sdd page.

  • How does Spec Batch compare to other AI Engineering skills?

    Spec Batch ranks #582 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Spec Batch against them. Open each page to compare what they document and how they install.

More from gotalab/cc-sdd

Spec Batch is one of 24 skills cataloged on DirSkills from gotalab/cc-sdd.

See all 24 skills →
🤖
2w ago

CC-SDD New Agent Integration

CC-SDD New Agent Integration adds or extends coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use it when introducing a new agent, adding a subagent-capable variant, or migrating an existing supported agent to skills-based templates.
AI Engineering
3.6K275
🔍
2w ago

Implementation Gap Validation

Implementation Gap Validation analyzes gaps between approved requirements and an existing codebase to inform implementation strategy. Use it before design to identify missing capabilities, integration challenges, and viable implementation approaches.
Quality
3.6K275
🧪
2w ago

Implementation Integration Validation

Implementation Integration Validation checks completed feature tasks as a whole to catch cross-task integration issues, run the full test suite, verify spec coverage, and confirm design boundaries before a GO/NO-GO call. Use it after all tasks in a feature are implemented to decide whether the implementation is ready.
Quality
3.6K275
📝
2w ago

Kiro Custom Steering Creation

Kiro Custom Steering Creation creates custom steering documents for specialized project contexts beyond core product, tech, and structure files. Use it to capture domain-specific patterns like API standards, testing strategies, or security conventions.
Writing
3.6K275
🔍
2w ago

Kiro Debug

Kiro Debug investigates implementation failures using root-cause-first debugging, gathering evidence from errors, runtime config, and external docs to identify root cause and recommend the smallest safe next action. Use it when an implementer is blocked or verification fails.
Quality
3.6K275
🔍
2w ago

Kiro Debug

Kiro Debug investigates implementation failures using root-cause-first debugging, gathering local evidence, runtime/config inspection, and external docs before proposing a fix. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
Quality
3.6K275

More AI Engineering skills

Spec Batch is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #582 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K