agentleFS
CassiiopeiaCassiiopeia/projectops/skills/pro-review/SKILL.md

pro-review

Skill6 starsChanged 32 days agoMITView on GitHub

Code review across security, performance, bugs and quality, with Critical/Major/Minor prioritized feedback. Use for PR review, file review, self-check after implementing, or /review.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When you need a PR review, file review or self-check after implementing, or on /review.

    line 10
  2. Very specific:

    Run the work start protocol in ../references/common-rules.md

    line 19
  3. Distinctive:

    Before starting: ask only about items that change the result a lot, one at a time (do not ask if the input already answers it)

    line 21
  4. Distinctive:

    Do not show config key names or file paths to the user

    line 24
  5. Very specific:

    If preferences have sections, use them for the review result's section layout.

    line 28
  6. Very specific:

    Do not build the save path yourself.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review Mode

When to use

  • When you need a PR review, file review or self-check after implementing, or on /review.
  • Typical requests: "review this code", "review the PR" (Korean: "코드 리뷰해줘", "PR 리뷰해줘").

As a code review expert, review the code's quality, security and performance thoroughly.

Talk to the user in the user's language (or the configured language preference). Write the review document in the configured language; if none is set, match the repo or the user.

Before you start

  1. Run the work start protocol in ../references/common-rules.md
  2. This skill produces a md file, so follow ../references/approval-and-questions.md (#526):
    • Before starting: ask only about items that change the result a lot, one at a time (do not ask if the input already answers it)
    • Before saving: show the content and get approval. If the user says "chat only", do not create a file. Do not skip the approval gate; take that answer at the "Save it?" step and finish without saving. In an auto-mode repo, show a summary and save right away
    • Once, on first run: ask whether to proceed without confirmation from now on, and remember the answer
    • Do not show config key names or file paths to the user

Review process

If preferences have sections, use them for the review result's section layout.

StepWhat to doDetails
1 ScopeType (PR / file / whole), changed line count, main changed areas—
2 Six-angle reviewSecurity · performance · bugs/logic · code quality · architecture · testsreferences/review-checklist.md
3 Prioritize🚨 Critical (now) · ⚠️ Major (before deploy) · 💡 Minor (recommended) · ✅ Positivereferences/review-checklist.md
4 Overall verdictApprove / Request Changes / Comment + issue counts + top 3 improvementsreferences/review-checklist.md
5 SaveSave to the path from get-output-pathBelow

Feedback principles

  • Constructive feedback (improve, do not blame)
  • Concrete, actionable suggestions (current code + suggested code), with file:line for each item
  • Review against the project's existing style

Save the output

Do not build the save path yourself; get it from the CLI (../references/doc-output-path.md, standard self-contained 5-line call):

PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
PYTHON=$(for _py in python3 python; do _path=$(command -v "$_py" 2>/dev/null) || continue; "$_path" -c "import sys; sys.exit(0)" 2>/dev/null && echo "$_path" && break; done)
[ -z "$PYTHON" ] && { echo "Python not found"; exit 1; }
SKILL=pro-review; ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
[ -d "$ROOT/skills/$SKILL/scripts" ] || for B in ~/.claude/plugins/cache ~/.codex/plugins/cache ~/.gemini/extensions ~/.pi/agent/git; do
  H=$(find "$B" -maxdepth 8 -type d -path "*/projectops/*skills/$SKILL/scripts" 2>/dev/null | sort -V | tail -1)
  [ -n "$H" ] && { ROOT="${H%/skills/$SKILL/scripts}"; break; }
done
# Home-copied installs from npx projectops: GitHub Copilot and Cursor (#200)
[ -d "$ROOT/skills/$SKILL/scripts" ] || for B in ~/.copilot ~/.cursor; do [ -d "$B/skills/$SKILL/scripts" ] && { ROOT="$B"; break; }; done
SCRIPTS="$ROOT/skills/$SKILL/scripts"
[ -d "$SCRIPTS" ] || { echo "projectops skill scripts not found. Check the plugin installation."; exit 1; }
PYTHONIOENCODING=utf-8 "$PYTHON" "$SCRIPTS/review_cli.py" get-output-path review --title "{title}"

Save the file at the path in the path field of the output JSON. If ok: false, read code and next and stop. Do not make up a path.

Customize

Your own language, tone and rules apply: see ../references/preferences.md. Read them once at the start: run the snippet in ../references/preferences.md with SKILL_ID=pro-review. Keys for this skill: sections plus the common language, tone, rules. Preferences change presentation only; approval gates, secret protection and --dry-run stay in force.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.