Skills for Real Engineers. Straight from my .agents directory.
How to install kiro-spec-tasks
npx skills add gotalab/cc-sdd# or add only this skill to Claude Code: copy the folder
tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-spec-tasks/
# into
~/.claude/skills/kiro-spec-tasks/ (all projects)
.claude/skills/kiro-spec-tasks/ (one project)
1# Implementation Tasks Generator23<background_information>4- **Success Criteria**:5 - All requirements mapped to specific tasks6 - Tasks properly sized (1-3 hours each)7 - Clear task progression with proper hierarchy8 - Natural language descriptions focused on capabilities9 - A lightweight task-plan sanity review confirms the task graph is executable before `tasks.md` is written10</background_information>1112<instructions>13## Execution Steps1415### Step 1: Load Context1617**Read all necessary context**:18- `{{KIRO_DIR}}/specs/$1/spec.json`, `requirements.md`, `design.md`19- `{{KIRO_DIR}}/specs/$1/tasks.md` (if exists, for merge mode)20- Core steering context: `product.md`, `tech.md`, `structure.md`21- Additional steering files only when directly relevant to requirements coverage, design boundaries, runtime prerequisites, or team conventions that affect task executability22- Use explicitly requested skills and task-relevant local skills/playbooks, including design, accessibility, and UX. Select by description and read only needed guidance, even for small tasks; preserve required checks and host/project rules.2324**Validate approvals**:25- If `-y` flag provided: Auto-approve requirements and design in spec.json. Tasks approval is also handled automatically in Step 4.26- Otherwise: Verify both approved (stop if not, see Safety & Fallback)27- Determine sequential mode based on presence of `--sequential`2829### Step 2: Generate Implementation Tasks3031**Load generation rules and template**:32…
Excerpt shown under the repository's MIT license.
More skills in cc-sdd
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
