Is the Answer Reviewer Questions skill free?

Yes. The skill itself is free from tobihagemann/turbo. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Answer Reviewer Questions 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 Answer Reviewer Questions?

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 Answer Reviewer Questions 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.

Answer Reviewer Questions

Turns PR reviewer question threads into raw, per-thread answers for a reply drafter

by tobihagemann · tobihagemann/turbo

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 774052b

Fetched SKILL.md via the GitHub API from a 70+ skill monorepo; it is a single-file pure-prompt skill with clean name+description frontmatter and no scripts. Body-referenced peer skills /recall-reasoning, /interpret-feedback, /github-voice all fetch HTTP 200. I built a mock PR (slugify in utils.py) with two reviewer question threads and produced two artifacts: a baseline conversational reply and a skill-following one. Concrete difference observed: the skill output uses strict per-thread `**Thread <id>** (path:line)` blocks, 1-2 sentence implementer-voice answers with no reviewer-address or filler, and the `_Grounding: derived from current code_` line (correct per the no-transcript fallback rule), versus the baseline's multi-paragraph reply that directly addresses the reviewer. Executed the /recall-reasoning fallback path myself since no transcript store exists; scored 7/10 as the format and constraints materially reshape the artifact.

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 Answer Reviewer Questions does

A pipeline skill that composes a short plain-text answer for each reviewer question thread on a pull request, recalling the implementer's reasoning (or falling back to the current code and commit diff) and emitting one formatted block per thread. It triggers when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions", and feeds its raw output into a downstream reply-drafting skill that applies voice and formatting.

How to install Answer Reviewer Questions

git clone --depth 1 https://github.com/tobihagemann/turbo.git /tmp/answer-reviewer-questions-src
mkdir -p ~/.claude/skills
cp -R /tmp/answer-reviewer-questions-src/claude/skills/answer-reviewer-questions ~/.claude/skills/answer-reviewer-questions
# Pipeline skill: it consumes reviewer "question threads" from conversation context
# (normally produced upstream by /interpret-feedback) and calls peer skills.
# For full function also install these sibling skills from the same repo:
#   claude/skills/recall-reasoning, claude/skills/interpret-feedback,
#   claude/skills/github-voice  (and the downstream reply-drafting skills)
# No external CLI/API key needed; pure-prompt skill.

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

Commands — how to trigger Answer Reviewer Questions

/answer-reviewer-questions Turns PR reviewer question threads into raw, per-thread answers for a reply drafter

It also activates on plain-language prompts like these:

Draft answers to these PR review comments
Explain why I made this implementation choice
Answer the reviewer's questions on this pull request

Frequently asked questions

Is the Answer Reviewer Questions skill free?: Yes. The skill itself is free from tobihagemann/turbo. SkillProof publishes the install command and an independent test verdict at no cost.
Does Answer Reviewer Questions work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md via the GitHub API from a 70+ skill monorepo; it is a single-file pure-prompt skill with clean name+description frontmatter and no scripts. Body-referenced peer skills /recall-reasoning, /interpret-feedback, /github-voice all fetch HTTP 200. I built a mock PR (slugify in utils.py) with two reviewer question threads and produced two artifacts: a baseline conversational reply and a skill-following one. Concrete difference observed: the skill output uses strict per-thread `**Thread <id>** (path:line)` blocks, 1-2 sentence implementer-voice answers with no reviewer-address or filler, and the `_Grounding: derived from current code_` line (correct per the no-transcript fallback rule), versus the baseline's multi-paragraph reply that directly addresses the reviewer. Executed the /recall-reasoning fallback path myself since no transcript store exists; scored 7/10 as the format and constraints materially reshape the artifact.
What is the Answer Reviewer Questions 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 Answer Reviewer Questions?: 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 Answer Reviewer Questions 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.