New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Record Code Review Feedback

by haru in haru/redmine_ai_helper

Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis.

MITAuto-check passedDevelopment

Install Record Code Review Feedback

skills CLI
$ npx skills add haru/redmine_ai_helper --skill record-code-review-feedback -a claude-code

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

GitHub CLI
$ gh skill install haru/redmine_ai_helper record-code-review-feedback --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/haru/redmine_ai_helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/record-code-review-feedback .claude/skills/record-code-review-feedback && 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
record-code-review-feedback
GitHub stars
106
Token cost
~1.1k tokens
SKILL.md length
586 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis.

  • Works in 8 steps: Read the Rules → Collect the Findings → Check Existing Entries → …
  • Asks to log review feedback
  • SKILL.md covers User Input, Procedure and Notes
  • Calls gh and git

What it does

Record Code Review Feedback is an agent skill from haru/redmine_ai_helper. Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis. Use right after fixing code in response to a review finding (AGENTS.md and the constitution require this), or when the user asks to log review feedback. Skips findings that were not adopted.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review, Root cause analysis and Pull requests. The repository describes itself as: A Redmine plugin that adds AI agents, MCP Server, smart completion, and vector search. The licence is MIT.

When your agent uses it

  • Asks to log review feedback
  • Tasks that involve Code review
  • Tasks that involve Root cause analysis

Example prompts

  • “/record-code-review-feedback”

Workflow steps

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

  1. Read the Rules
  2. Collect the Findings
  3. Check Existing Entries
  4. Analyze the Root Cause
  5. Write the Prevention Rule
  6. Create the Entry
  7. Propose Promotion When It Recurs
  8. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 54cee42. 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

    Shell commands in SKILL.md call:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    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

Record Code Review Feedback loads about 1.1k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 586 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 haru/redmine_ai_helper at commit 54cee42, republished under its MIT licence (© haru). 586 words, ~1,131 tokens.

Download SKILL.mdSave it as .claude/skills/record-code-review-feedback/SKILL.md (or your agent's skills folder).
name
record-code-review-feedback
description
Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis. Use right after fixing code in response to a review finding (AGENTS.md and the constitution require this), or when the user asks to log review feedback. Skips findings that were not adopted.
argument-hint
Optional: PR number, review source, or the findings to record
user-invocable
true
disable-model-invocation
false

Record Code Review Feedback

Record review findings on AI-generated code that resulted in a fix, analyze why the AI wrote the original code, and derive a rule that prevents the same mistake next time.

User Input

text
$ARGUMENTS

Consider any context from the user input (PR number, which findings, the review source) before proceeding.

Procedure

Step 1: Read the Rules

Read docs/code-review-feedback/README.md. It defines what to record, the root-cause categories, the template, and the index. Follow it; this skill only describes the workflow.

Step 2: Collect the Findings

Identify the review source:

  • GitHub Copilot PR review: determine the PR from the user input or gh pr view --json number -q .number on the current branch, then fetch Copilot's review comments:

    bash
    gh api repos/{owner}/{repo}/pulls/<PR>/comments --paginate \
  --jq '.[] | select(.user.login == "Copilot") | {id, path, line, html_url, body}'

  • Local AI review (/code-review, speckit-review-*, etc.): use the findings reported earlier in the conversation. If they are no longer available (e.g. after /clear or in a new session), ask the user for them instead of reconstructing them.

For each finding, check whether it led to a code change (git diff, git log -p on the affected files, or the conversation). Keep only adopted findings. Skip typo-only and formatting-only fixes.

If nothing remains, stop and tell the user there is nothing to record.

Group the remaining findings by root cause: one entry per root cause.

Step 3: Check Existing Entries

Scan the index in the README and open entries with the same category or touching the same files/area. If an existing entry describes the same pattern, list it under Related.

Step 4: Analyze the Root Cause

Answer concretely:

  • What did the AI base the original code on (a nearby pattern, the spec, a guess, a generic idiom)?
  • What should it have checked — name the AGENTS.md rule, constitution principle, ADR, existing helper, or Redmine API?
  • Why did it not do so (rule not documented, rule documented but not consulted, edge case not considered, tests did not cover it)?

Pick the category from the README table. Use other only with an explanation.

Show full SKILL.md (259 more words)Show less
Step 5: Write the Prevention Rule

Write a rule that is concrete and checkable at code-generation time (e.g. "Tools that take a project ID must return the same error for missing and invisible projects" — not "check permissions carefully"). Set Promoted to to Not yet unless the rule is actually added to a durable place.

Step 6: Create the Entry
  1. Find the highest existing number in docs/code-review-feedback/ and add one (start at 001).
  2. Create docs/code-review-feedback/NNN-short-title.md from the template, in English, with today's date. Include the review comment URL and the fix commit hash when available.
  3. Append a row to the README index: | [CRF-NNN](./NNN-short-title.md) | Title | category | source | Not yet |.

Never edit or delete existing entries, except for updating the Promoted to field in Step 7.

Step 7: Propose Promotion When It Recurs

If the new entry has one or more Related entries (the pattern has occurred at least twice), propose to the user where the prevention rule should be promoted (AGENTS.md, the constitution, an ADR, a skill) and show the proposed text. Do not change those files without the user's approval. After the approved rule is added, update the entry's Promoted to field and the matching index cell to name the destination.

Step 8: Report

Tell the user the created files, categories, prevention rules, and any promotion proposal. Do not commit.

Notes

  • Write entries in English regardless of the conversation language.
  • Keep code excerpts short (the relevant lines only).
  • If gh fails (not authenticated, API error), report the error to the user instead of guessing the review content.

© haru, 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 .claude/skills/record-code-review-feedback of haru/redmine_ai_helper.

Open the folder on GitHubat commit 54cee42

Compare with similar skills

Record Code Review Feedback 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.

Record Code Review Feedback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Record Code Review Feedback this skillharu/redmine_ai_helper106—~1.1kAutomated safety check: PassMIT
Cwe Code ReviewSpecterOps/skills706—~2.4kAutomated safety check: PassApache-2.0
Code Overviewtestdouble/han281—~8.5kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence
Open Code Review CLIalibaba/open-code-review46k—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Cwe Code Review

    SpecterOps/skills

    Perform CWE-grounded security code reviews and precise weakness mapping using a locally derived MITRE CWE corpus, relationship graphs, mapping notes, detection methods, mitigations, and schema…

    706 GitHub stars~2.4k tokensUpdated 17 days ago
    DevelopmentAuto-check passed

  • Code Overview

    testdouble/han

    Produces a human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — why it exists (the real problem it solves or goal it serves for the business or a user)…

    281 GitHub stars~8.5k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Open Code Review CLI

    alibaba/open-code-review

    Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.

    46k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • GitHub Review Iteration

    prisma/orm

    Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from haru/redmine_ai_helper

All 23 skills in this repo

  • Commit

    haru/redmine_ai_helper

    Stage the current changes and create a git commit with a properly formatted English message.

    106 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

  • Create Pull Request

    haru/redmine_ai_helper

    Create a pull request from the current branch. An agent skill from haru/redmine_ai_helper.

    106 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Create Release Branch

    haru/redmine_ai_helper

    Create a release branch for a given version. An agent skill from haru/redmine_ai_helper.

    106 GitHub stars~599 tokensUpdated today
    Auto-check passed

  • Record Spec Feedback

    haru/redmine_ai_helper

    Record a user's correction of an AI-written specification in docs/spec-feedback/ as an append-only entry with root-cause analysis.

    106 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Qlty Check

    haru/redmine_ai_helper

    Code quality checks, formatting, and metrics via qlty CLI. An agent skill from haru/redmine_ai_helper.

    106 GitHub starsUsed in 2 repos~628 tokens
    Auto-check passed

  • Redmine Playwright Login

    haru/redmine_ai_helper

    Connect to the running Redmine instance and log in via the Playwright MCP browser, using REDMINEPLAYRIGHTURL/REDMINEPLAYRIGHTUSER/REDMINEPLAYRIGHTPASSWORD environment variables.

    106 GitHub stars~796 tokensUpdated today
    Auto-check passed

Categories

Questions about Record Code Review Feedback

What does Record Code Review Feedback do?

Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis. Record Code Review Feedback is an agent skill from haru/redmine_ai_helper. Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis.

When should I use Record Code Review Feedback?

Record Code Review Feedback fits situations like: asks to log review feedback; tasks that involve Code review; tasks that involve Root cause analysis.

How do I install Record Code Review Feedback in Claude Code?

Run `npx skills add haru/redmine_ai_helper --skill record-code-review-feedback -a claude-code`. Or copy the skill folder (.claude/skills/record-code-review-feedback in haru/redmine_ai_helper) into .claude/skills/record-code-review-feedback in your project. Claude Code loads it when a task matches its description.

How do I install Record Code Review Feedback in Codex?

Run `npx skills add haru/redmine_ai_helper --skill record-code-review-feedback -a codex`. Or copy the skill folder (.claude/skills/record-code-review-feedback in haru/redmine_ai_helper) into .agents/skills/record-code-review-feedback in your project. Codex loads it when a task matches its description.

Can I use Record Code Review Feedback 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 haru/redmine_ai_helper --skill record-code-review-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/record-code-review-feedback, .gemini/skills/record-code-review-feedback, .github/skills/record-code-review-feedback and .opencode/skills/record-code-review-feedback in your project.

What does Record Code Review Feedback need to run?

Going by SKILL.md and its folder, Record Code Review Feedback needs the command-line tools its instructions call (gh and git).

Does Record Code Review Feedback access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Record Code Review Feedback 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 Record Code Review Feedback use?

Record Code Review Feedback 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 Record Code Review Feedback use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 Record Code Review Feedback?

Skills that share tags, products or a category with Record Code Review Feedback: Cwe Code Review (SpecterOps/skills, 706 stars), Code Overview (testdouble/han, 281 stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and WooCommerce Code Review (woocommerce/woocommerce, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Record Code Review Feedback?

haru (a GitHub user) maintains it in haru/redmine_ai_helper, which has 106 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 11, 2026.

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