Is the Kiro Debug skill free?

Yes. The skill itself is free from gotalab/cc-sdd. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Kiro Debug SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Kiro Debug?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Kiro Debug with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Kiro Debug

Root-cause-first debug protocol that blocks guess-and-check patching after a failed fix

by gotalab · gotalab/cc-sdd

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 10, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 5734445

Reproduced a real failing pytest (integer-division bug) and ran both approaches: baseline jumped straight to a one-line fix, while the skill forced a structured Debug Report (ROOT_CAUSE, CATEGORY: LOGIC_ERROR, FIX_PLAN, VERIFICATION, NEXT_ACTION: RETRY_TASK, CONFIDENCE: HIGH) that correctly identified the same root cause but in a form an orchestrating agent could act on directly.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Kiro Debug does

Structures debugging as evidence-gathering before fixing: read the exact error, inspect repo/runtime config (package.json, git diff, build files), optionally check docs, then classify the failure into one of ten categories and emit a structured Debug Report with FIX_PLAN, VERIFICATION, NEXT_ACTION and CONFIDENCE. Triggers when an implementer is blocked, verification fails, or repeated remediation attempts don't converge — it is explicit about refusing to propose a patch before root cause is established.

How to install Kiro Debug

git clone https://github.com/gotalab/cc-sdd
cd cc-sdd
mkdir -p ~/.claude/skills
cp -r tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-debug ~/.claude/skills/kiro-debug

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Kiro Debug

/kiro-debug Root-cause-first debug protocol that blocks guess-and-check patching after a failed fix

It also activates on plain-language prompts like these:

My fix didn't work, help me find the actual root cause
Debug this failing build and give me a structured debug report
Stop guessing fixes and diagnose why this test keeps failing

Frequently asked questions

Is the Kiro Debug skill free?: Yes. The skill itself is free from gotalab/cc-sdd. SkillProof publishes the install command and an independent test verdict at no cost.
Does Kiro Debug work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 10, 2026. Verdict: Tested · Works. Reproduced a real failing pytest (integer-division bug) and ran both approaches: baseline jumped straight to a one-line fix, while the skill forced a structured Debug Report (ROOT_CAUSE, CATEGORY: LOGIC_ERROR, FIX_PLAN, VERIFICATION, NEXT_ACTION: RETRY_TASK, CONFIDENCE: HIGH) that correctly identified the same root cause but in a form an orchestrating agent could act on directly.
What is the Kiro Debug SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Kiro Debug?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Kiro Debug with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.