Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Apply Findings

Turns evaluated code-review findings into actual code edits, verifying each suggested fix and escalating anything ambiguous to you.

Dev & CodingIntermediate★ 405⑂ 32AI score 8/10Last updated: Oct 3, 2026

What it does

  • Collects findings from the conversation that already carry Apply / Skip / Escalate verdicts and refuses to run on raw, unevaluated output.
  • Groups fixes by file and applies them in file order, re-reading the surrounding function and confirming the finding still applies.
  • Treats a suggested fix as a separate claim from the finding: traces it against the named failure modes, checks pre-fix behavior on unmentioned inputs, and for sanitizing fixes requires a named blocker for every special character class.
  • Escalates instead of guessing when a fix would reverse an earlier user decision or change which inputs the code accepts beyond the named defect, using AskUserQuestion with a recommended option and trade-offs.
  • Forces a full caller/reference sweep for renames and signature changes, and verifies that any contract-stating comment is actually enforced by the code.
  • Reports results as a one-line-per-finding table (File | Finding | Outcome).

Who it's for

  • Developers who run AI code reviews in Claude Code and want a disciplined way to land the results.
  • Teams burned by applying AI-suggested patches verbatim and shipping regressions.
  • Anyone building a review → evaluate → apply → note-for-later pipeline.

Example uses

  1. "apply the accepted findings" — edits land file by file, with a summary table at the end.
  2. A security finding ships a patch that only escapes some metacharacters — the skill declines, records why the remedy is incomplete, and escalates.
  3. A fix would undo an architecture choice you made earlier — the skill names the original decision and offers Apply / Skip / Note for later / Get a second opinion.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/tobihagemann/turbo/HEAD/claude/skills/apply-findings/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the claude/skills/apply-findings folder from the GitHub repo tobihagemann/turbo into my ~/.claude/skills/apply-findings/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/tobihagemann/turbo.git /tmp/turbo && mkdir -p ~/.claude/skills && cp -r /tmp/turbo/claude/skills/apply-findings ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Clone the repo: git clone https://github.com/tobihagemann/turbo.git /tmp/turbo
  4. Copy the skill: cp -r /tmp/turbo/claude/skills/apply-findings ~/.claude/skills/
  5. (Recommended) Install the companion skills too: cp -r /tmp/turbo/claude/skills/evaluate-findings /tmp/turbo/claude/skills/note-improvement ~/.claude/skills/ — run ls /tmp/turbo/claude/skills first to confirm folder names.
  6. Restart Claude Code and confirm apply-findings shows up in your skill list.
  7. Evaluate your review findings first, then say "apply findings" to trigger it.
View source on GitHub ↗License: MIT