Is the Apply Findings 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 Apply Findings SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Apply Findings?

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 Apply Findings 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.

Apply Findings

Applies evaluated code-review findings, escalating scope-widening or unsound fixes

by tobihagemann · tobihagemann/turbo

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 46481c3

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 21, 2026; it's queued for a re-test.

Fetched SKILL.md (HTTP 200) and confirmed all four referenced sibling skills (evaluate-findings, note-improvement, consult-codex, consult-oracle) return 200. Built a representative task: validate.py with a parse_port function plus an evaluated findings table (finding #1: improve error message = Apply; finding #2: replace int(s) with int(s.strip(),0) = Apply). Baseline applied both mechanically; following the skill body's Step 2.5 (escalate fixes that newly admit inputs beyond the named defect), the skill artifact applied only #1 and held #2. I ran python3 to prove the difference: baseline's int(s.strip(),0) silently parses "0x1f"->31 and "0o17"->15 and breaks valid "08", changes the skill correctly escalates instead of applying.

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 8/10
Docs & honesty 5/5

What Apply Findings does

A Claude Code skill that applies code-review findings that have already been given Apply/Skip/Escalate verdicts by the companion /evaluate-findings skill. It groups Apply findings by file, re-verifies each still holds against current code, independently checks whether a suggested fix widens accepted inputs or reverses an earlier decision, and routes anything ambiguous to the user via AskUserQuestion. Triggers on phrases like "apply findings", "apply the fixes", "apply accepted findings", or "fix the findings".

How to install Apply Findings

git clone --depth 1 https://github.com/tobihagemann/turbo.git /tmp/apply-findings-src
mkdir -p ~/.claude/skills
cp -R /tmp/apply-findings-src/claude/skills/apply-findings ~/.claude/skills/apply-findings
# Pure-prompt orchestration skill (SKILL.md only, no scripts/deps).
# Part of the Turbo skill suite; expects findings already produced by the sibling
# /evaluate-findings skill in context. Also references (install for full loop):
#   claude/skills/{evaluate-findings,note-improvement,consult-codex,consult-oracle}
# Uses Claude Code's AskUserQuestion + TaskList tools. Codex edition: codex/skills/apply-findings.

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

Commands — how to trigger Apply Findings

/apply-findings Applies evaluated code-review findings, escalating scope-widening or unsound fixes

It also activates on plain-language prompts like these:

Apply the accepted findings from this review
Fix the issues flagged in the code review
Apply these review suggestions to the code

Frequently asked questions

Is the Apply Findings 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 Apply Findings work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md (HTTP 200) and confirmed all four referenced sibling skills (evaluate-findings, note-improvement, consult-codex, consult-oracle) return 200. Built a representative task: validate.py with a parse_port function plus an evaluated findings table (finding #1: improve error message = Apply; finding #2: replace int(s) with int(s.strip(),0) = Apply). Baseline applied both mechanically; following the skill body's Step 2.5 (escalate fixes that newly admit inputs beyond the named defect), the skill artifact applied only #1 and held #2. I ran python3 to prove the difference: baseline's int(s.strip(),0) silently parses "0x1f"->31 and "0o17"->15 and breaks valid "08", changes the skill correctly escalates instead of applying.
What is the Apply Findings SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Apply Findings?: 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 Apply Findings 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.