Agent skill

Apply Findings

by tobihagemann in tobihagemann/turbo

Apply findings by making the suggested code changes. An agent skill from tobihagemann/turbo.

MITAuto-check passed

Install Apply Findings

skills CLI
$ npx skills add tobihagemann/turbo --skill apply-findings -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tobihagemann/turbo apply-findings --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tobihagemann/turbo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex/skills/apply-findings .claude/skills/apply-findings && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
apply-findings
GitHub stars
408
Token cost
~2.5k tokens
SKILL.md length
1,559 words
Files
1
Skills in repo
81
Repo updated
First seen
Licence
MIT

At a glance

Apply findings by making the suggested code changes. An agent skill from tobihagemann/turbo.

  • Works in 4 steps: Identify Findings → Apply in File Order → Handle Escalated Findings → …
  • The user asks to apply findings
  • SKILL.md covers Step 1: Identify Findings, Step 2: Apply in File Order, Step 3: Handle Escalated… and Step 4: Format Output, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Apply Findings is an agent skill from tobihagemann/turbo. Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to "apply findings", "apply fixes", "apply suggestions", "apply accepted findings", "fix the findings", or "apply the review results".

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Reusable workflows for planning, building, reviewing, and shipping with Claude Code and Codex. The licence is MIT.

When your agent uses it

  • The user asks to apply findings
  • Apply suggestions
  • Apply accepted findings
  • Fix the findings

Example prompts

  • “apply findings”
  • “apply fixes”
  • “apply suggestions”
  • “/apply-findings”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Identify Findings
  2. Apply in File Order
  3. Handle Escalated Findings
  4. Format Output

What it can do on your machine

Read from SKILL.md and the folder at commit 931eda5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Apply Findings loads about 2.5k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 1,559 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tobihagemann/turbo at commit 931eda5, republished under its MIT licence (© tobihagemann). 1,559 words, ~2,475 tokens.

Download SKILL.mdSave it as .claude/skills/apply-findings/SKILL.md (or your agent's skills folder).
name
apply-findings
description
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to "apply findings", "apply fixes", "apply suggestions", "apply accepted findings", "fix the findings", or "apply the review results".

Apply Findings

Apply evaluated findings from the conversation context. Findings must have been through $evaluate-findings first.

Step 1: Identify Findings

Collect all findings from the conversation context. Findings should have Verdict columns (Apply, Skip, Escalate) from $evaluate-findings.

If findings are unevaluated (raw output without verdicts), stop and say to run $evaluate-findings first.

Step 2: Apply in File Order

Group Apply findings by file path and apply in file order to minimize context switching. For each finding:

  1. Read the full function or logical block at the referenced location
  2. Verify the finding still applies to the current code
  3. Before applying a fix that stops a failure, whether the finding suggested it or you derived it, confirm the fix makes the failure the finding describes unreachable rather than only defeating the finding's reproduction: construct an input that clears the point the fix guards, trace whether it still reaches that failure further along, and write any regression test the fix adds from that input. When the fix encodes, escapes, quotes, or otherwise sanitizes untrusted input, construct such inputs from every character class the target interpreter treats specially and name what in the fix blocks each one; a class with no blocker means the fix is incomplete, including when it reproduces the finding's suggested wording. When the finding carries a suggested fix, also treat the fix as a separate claim from the finding and verify it independently — trace it against the failure modes the finding names, then against the behavior the code had before the fix on inputs the finding never mentioned, since a remedy can address the named mode while regressing an axis alongside it. Where the finding arrives with opposing remedies recorded, verify the measured one first, and where none was measured, measure before applying rather than choosing on the proposer's authority. If a suggested fix does not hold up, treat the finding as Escalate (surface it in Step 3) and record why the remedy fails, rather than applying an unsound fix on the finding's authority. If a fix you derived does not hold up, revise it, and when no revision holds up, treat the finding as Escalate (surface it in Step 3) and record why.
  4. When the fix would reverse a decision the user made earlier — in discussion or recorded in the artifact — treat the finding as Escalate (surface it in Step 3) and name the original decision. Judge by the outcome rather than the wording of the option the user chose: a reversal leaves the user with something materially different from what they chose. When the finding refutes only the factual premise the user's choice rested on and the fix leaves the chosen outcome intact, that is a premise correction: confirm the refutation against whichever of the code, the governing artifact, or authoritative documentation the premise turns on, and when none settles it, treat the finding as Escalate. Otherwise continue with the remaining checks, and state both the corrected premise and the chosen outcome it leaves standing in Step 4.
  5. Check what the fix you are about to make changes about the inputs the code accepts. When the change in accepted inputs is exactly the defect the finding names, continue with the remaining checks. When it turns away or newly admits anything beyond that defect — a value or path a legitimate caller could send — that is a behavior change: treat the finding as Escalate (surface it in Step 3) and name the input class that changes.
  6. Check whether the fix you are about to make adds machinery the evaluated finding does not name: a lease, lock, queue, versioning scheme, state machine, or new persistent entity. When it does, treat the finding as Escalate (surface it in Step 3) and name the machinery.
  7. Make the fix
  8. If the finding renames an identifier or changes a recurring shape — a type signature, call pattern, or wrapper that appears in many places — search every caller and reference the change reaches, not only the changed files, by concept rather than by the literal just replaced: a stem that survives inflection and compounding, or the shape common to every variant. A clean search proves nothing when its pattern was derived from a single instance, and the cited location is often only one of several references. When the finding names several sites, also tick them off against the finding text. Complete the sweep before marking the fix complete.
  9. When the fix adds or edits a comment stating a contract — what is handled, what is excluded, what callers may rely on — verify the code enforces that contract before marking the fix complete. When it does not, add the enforcement rather than narrowing the comment.

If a finding references code that has changed since it was generated (e.g., by a prior fix in this same run), re-assess whether it still applies. Skip if the code has diverged.

When an escalated finding's outcome would change what the other fixes should look like, settle it in Step 3 before applying them.

Show full SKILL.md (721 more words)Show less

Step 3: Handle Escalated Findings

For findings with Escalate verdict, use request_user_input to let the user decide. Output the finding's technical detail as text first, including the fact that forces the choice, then state the question as the decision the user owns. When the finding is a disagreement between two artifacts, first establish which artifact changed last and which one the code or content that consumes them follows today. Include that in the detail and weigh it in the recommendation, then ask which behavior is wanted; reconciling the artifacts follows from that answer.

Recommend the genuinely best option: place it first and append (Recommended) to its label, judging "best" on technical merit alone (the soundest engineering outcome), independent of how closely the option conforms to the task's original scope. Reserve the Note for later recommendation for a fix that is not ready to make: it needs design work of its own, or rests on a cause or fact this session cannot establish. Name what it waits on in that option's description. Treat a finding being pre-existing or outside the changeset as a scope cost to state beside the recommended option, with no bearing on which option that is. When the choice hinges on product intent or domain knowledge you lack and merit cannot settle it, say so instead of forcing a pick. Where an established convention answers a visual or interaction choice, that settles it: recommend the option that follows the convention and name it. Take the project's own treatment of like elements ahead of the platform's, and the platform's ahead of general practice. Give each option a plain-language description that carries the trade-off: its concrete effect and what it costs. Before asking, confirm every claim a description makes about what its remedy does, including its effect on legitimate callers and what it leaves untouched, the way Step 2 items 3 and 5 check a fix. Correct a claim that check contradicts. When the check needs material this session has not read, read it. Mark as unverified in that description only a claim this session cannot establish, and leave (Recommended) off the option whose remedy it describes. When a tool available in this session can carry out the remedy directly, make that action the Apply option rather than tooling that would carry it out later, and name in its description the system it acts on and whether the action can be undone. When the recommended option also widens the changeset's scope, name both its merit and that scope cost so the user can weigh them. When an earlier escalation already widened the changeset, state the running total alongside this option's increment. When the choice is costly to reverse — it establishes a pattern others will follow, defines an interface, or commits to a data shape — offer the consultation option in place of whichever alternative fits the finding least, labeled "Get a second opinion", keeping the question at three options, and resolve a freeform answer naming the alternative left out the same way as a selected one. Offer it as well whenever no option earns (Recommended) with conviction, and whenever the finding names a defect in a fix this session made earlier.

  • Apply — make the change, then run Step 2's post-fix checks (items 8 and 9) against it
  • Skip — leave as-is
  • Note for later — run the $note-improvement skill to capture it
  • Get a second opinion — run the $consult-claude skill for a second opinion on the choice, or the $consult-oracle skill when standard approaches have already failed. Then apply, skip, or note the finding with that answer in hand

Step 4: Format Output

Report the outcome as a table, one row per finding, keeping every cell to a single line:

FileFindingOutcome

Where Outcome is one of:

  • Applied — the fix was made
  • Escalated — name the resolution the user chose: applied, skipped, or noted for later
  • Skipped — name the reason

Keep the report to the table. Add prose only where an escalation's resolution changed what the other fixes look like, or where a fix corrected the factual premise a user's choice rested on.

Then call update_plan to mark this step completed and continue with the next step of the active workflow.

Rules

  • Only edit files, except for a direct action the user chose as Apply in Step 3. Do not stage, build, or test.

© tobihagemann, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in codex/skills/apply-findings of tobihagemann/turbo.

Open the folder on GitHubat commit 931eda5

Compare with similar skills

Apply Findings next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Apply Findings compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Apply Findings this skilltobihagemann/turbo408—~2.5kAutomated safety check: PassMIT
Find Releaseflutter/flutter180k—~545Automated safety check: PassBSD-3-Clause
Suggestion Boxpaperclipai/paperclip100k—~1.3kAutomated safety check: PassMIT
Fd Findpenpot/penpot61k—~882Automated safety check: PassMPL-2.0
Suggest Automationsn8n-io/n8n207k—~2kAutomated safety check: PassCustom licence
Employee Suggestion Hubsickn33/agentic-awesome-skills47k1 repos~3.4kAutomated safety check: PassMIT

Similar skills

  • Find Release

    flutter/flutter

    A skill to find the lowest Dart and Flutter release containing a given commit.

    180k GitHub stars~545 tokensUpdated today
    MobileAuto-check passed
  • Suggestion Box

    paperclipai/paperclip

    Quietly suggest a concrete improvement after observing material, generalizable friction in agent work.

    100k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Fd Find

    penpot/penpot

    A fast and user-friendly alternative to 'find' - simple syntax, smart defaults, respects gitignore.

    61k GitHub stars~882 tokensUpdated yesterday
    Auto-check passed
  • Official

    Offer the three most common automations for a user as a single-choice card, from your own knowledge of their team and their apps, then build the one they choose once they confirm, or offer more.

    207k GitHub stars~2k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Employee Suggestion Hub

    sickn33/agentic-awesome-skills

    Suggestion register: submitter or anonymous flag, category, votes, reviewer, decision and response status.

    47k GitHub starsUsed in 1 repo~3.4k tokens
    Business, Finance & HRAuto-check passed
  • Find Matching Tenders

    sickn33/agentic-awesome-skills

    Find open AU/NZ government tenders matching what a company does, ranked by fit with why and gap analysis.

    47k GitHub starsUsed in 1 repo~1k tokens
    Sales & SupportAuto-check passed

More from tobihagemann/turbo

All 81 skills in this repo
  • Consult Oracle

    tobihagemann/turbo

    Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches.

    408 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Fetch PR Comments

    tobihagemann/turbo

    Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes.

    408 GitHub stars~967 tokensUpdated 2 days ago
    Auto-check passed
  • Recall Rationale

    tobihagemann/turbo

    Recall why a past change was made by locating the Claude Code transcript that produced it.

    408 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed
  • Resolve PR Comments

    tobihagemann/turbo

    Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments.

    408 GitHub stars~3.8k tokensUpdated 2 days ago
    Auto-check passed
  • Resolve PR Comments

    tobihagemann/turbo

    Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments.

    408 GitHub stars~3.8k tokensUpdated 2 days ago
    Auto-check passed
  • Assess Technical Debt

    tobihagemann/turbo

    Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, architecture rot, and low-value tests.

    408 GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check passed

Questions about Apply Findings

What does Apply Findings do?

Apply findings by making the suggested code changes. An agent skill from tobihagemann/turbo. Apply Findings is an agent skill from tobihagemann/turbo. Apply findings by making the suggested code changes.

When should I use Apply Findings?

Apply Findings fits situations like: the user asks to apply findings; apply suggestions; apply accepted findings; fix the findings.

How do I install Apply Findings in Claude Code?

Run `npx skills add tobihagemann/turbo --skill apply-findings -a claude-code`. Or copy the skill folder (codex/skills/apply-findings in tobihagemann/turbo) into .claude/skills/apply-findings in your project. Claude Code loads it when a task matches its description.

How do I install Apply Findings in Codex?

Run `npx skills add tobihagemann/turbo --skill apply-findings -a codex`. Or copy the skill folder (codex/skills/apply-findings in tobihagemann/turbo) into .agents/skills/apply-findings in your project. Codex loads it when a task matches its description.

Can I use Apply Findings in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tobihagemann/turbo --skill apply-findings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apply-findings, .gemini/skills/apply-findings, .github/skills/apply-findings and .opencode/skills/apply-findings in your project.

What does Apply Findings need to run?

SKILL.md names no scripts, command-line tools or credentials: Apply Findings is instructions for the agent only.

Does Apply Findings access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Apply Findings safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Apply Findings use?

Apply Findings is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Apply Findings use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Apply Findings?

Skills that share tags, products or a category with Apply Findings: Find Release (flutter/flutter, 180k stars), Suggestion Box (paperclipai/paperclip, 100k stars), Fd Find (penpot/penpot, 61k stars) and Suggest Automations (n8n-io/n8n, 207k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Apply Findings?

tobihagemann (a GitHub user) maintains it in tobihagemann/turbo, which has 408 GitHub stars. The repository holds 81 skills in this directory. The repository was last updated on October 9, 2026.

Source: tobihagemann/turbo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.