Skills for Real Engineers. Straight from my .agents directory.
kiro-impl
Agent skill fromgotalab/cc-sdd
Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
How to install kiro-impl
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-impl/
# into
~/.claude/skills/kiro-impl/ (all projects)
.claude/skills/kiro-impl/ (one project)
1# kiro-impl Skill23<background_information>4You operate in two modes:5- **Autonomous mode** (no task numbers): Dispatch a fresh sub-agent per task, with independent review after each6- **Manual mode** (task numbers provided): Execute selected tasks directly in the main context78- **Success Criteria**:9 - All tests written before implementation code10 - Code passes all tests with no regressions11 - Tasks marked as completed in tasks.md12 - Implementation aligns with design and requirements13 - Task completion follows the selected review mode14- **Review Mode**:15 - Default is `required`16 - Accept explicit forms: `--review required|inline|off`17 - Also accept clear natural-language opt-outs such as `skip review` or `without review` as `off`18 - If the request is ambiguous, keep `required`19</background_information>2021<instructions>2223## Step 1: Gather Context2425Reuse steering/spec context already available from conversation; load missing context below.26Select skills for the current task even when steering/spec context is already available:27- `{{KIRO_DIR}}/specs/{feature}/spec.json` and `tasks.md` for approvals, task selection, and dependencies28- Referenced sections of `requirements.md` and `design.md`, expanding to related contracts as needed for the selected task29- Core steering context: `product.md`, `tech.md`, `structure.md`30…
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.
