Agent skill

PR Review Cycle Retro

by victorGPT in victorGPT/vibeusage

A skill your agent uses when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

MITAuto-check passedDevelopment

Install PR Review Cycle Retro

skills CLI
$ npx skills add victorGPT/vibeusage --skill pr-review-cycle-retro -a claude-code

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

GitHub CLI
$ gh skill install victorGPT/vibeusage pr-review-cycle-retro --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/victorGPT/vibeusage.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/skills/pr-review-cycle-retro .claude/skills/pr-review-cycle-retro && 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
pr-review-cycle-retro
GitHub stars
130
Token cost
~1.4k tokens
SKILL.md length
578 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

  • Works in 7 steps: Select: Find PRs with Codex review churn… → Isolate: Filter only Codex Cloud reviews… → Evidence: Collect a traceable chain… → …
  • A team sees repeated @codex review cycles
  • SKILL.md covers Overview, When to Use, Core Pattern and Quick Reference, plus 8 more sections
  • Calls node and gh

What it does

PR Review Cycle Retro is an agent skill from victorGPT/vibeusage. Use when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

Its SKILL.md is about 1.4k 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 Pull requests, Retrospectives and Root cause analysis. The licence is MIT.

When your agent uses it

  • A team sees repeated @codex review cycles
  • Codex Cloud feedback churn and needs root-cause attribution by development stage

Example prompts

  • “/pr-review-cycle-retro”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Select: Find PRs with Codex review churn (comment -> code update -> Codex review).
  2. Isolate: Filter only Codex Cloud reviews and actionable feedback.
  3. Evidence: Collect a traceable chain (Codex feedback -> code change or follow-up fix).
  4. Classify: Assign primary + secondary stage causes.
  5. Abstract: Roll causes into a stable taxonomy.
  6. Aggregate: Summarize causes across frontend/backends.
  7. Prevent: Enforce the PR template risk-layer gate before any future @codex review.

What it can do on your machine

Read from SKILL.md and the folder at commit 4891a58. 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:

    • node
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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

PR Review Cycle Retro loads about 1.4k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 578 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 victorGPT/vibeusage at commit 4891a58, republished under its MIT licence (© victorGPT). 578 words, ~1,408 tokens.

Download SKILL.mdSave it as .claude/skills/pr-review-cycle-retro/SKILL.md (or your agent's skills folder).
name
pr-review-cycle-retro
description
Use when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

Codex Review Churn Analysis (PR Retrospective)

Overview

Explain why Codex Cloud review had to be re-run. Attribute causes to specific development stages, not just PR outcomes.

When to Use

  • Multiple @codex review cycles on the same PR.
  • The same feedback appears across successive Codex reviews.
  • Follow-up fix PRs exist shortly after merge.
  • You need stage-level causes (design / implementation / testing / review packaging / release).

When NOT to use:

  • Human-review-only churn.
  • Pure formatting or mechanical PRs.

Core Pattern

  1. Select: Find PRs with Codex review churn (comment -> code update -> Codex review).
  2. Isolate: Filter only Codex Cloud reviews and actionable feedback.
  3. Evidence: Collect a traceable chain (Codex feedback -> code change or follow-up fix).
  4. Classify: Assign primary + secondary stage causes.
  5. Abstract: Roll causes into a stable taxonomy.
  6. Aggregate: Summarize causes across frontend/backends.
  7. Prevent: Enforce the PR template risk-layer gate before any future @codex review.

Quick Reference

ItemRule
Codex cycleCodex review comment -> code update -> new Codex review
EvidenceCodex comment + fix commit OR follow-up fix PR OR regression doc
Stage attributiondesign / implementation / testing / review packaging / release
Mixed PRrecord both frontend and backend impact
Noise guardif Codex comments are generic, mark low-signal
Risk-layer gateif any trigger matches, fill the addendum before @codex review

Stage Taxonomy (Definition)

  • Design: missing requirements, unclear acceptance criteria, privacy/exposure gaps, cross-endpoint invariants not specified.
  • Implementation: logic errors, incomplete edge cases, inconsistent ordering/aggregation.
  • Testing: missing regression/E2E/contract tests, no reproduction script.
  • Review Packaging: PR lacks context, spec, evidence, or minimal repro for Codex to review well.
  • Release/Integration: environment constraints (gateway, permissions, paths), deploy-time mismatches.

Cause Taxonomy (Abstract)

  • Spec Gap: requirement or invariant not defined.
  • Context Gap: Codex lacked PR context (spec, expected behavior, tests).
  • Implementation Drift: code diverged from intent or was inconsistent across modules.
  • Test Gap: no automated proof for edge cases or invariants.
  • Integration Constraint: environment or platform limitations discovered late.

Implementation (Repo-Specific)

Baseline candidate list (optional):

bash
node scripts/ops/pr-retro.cjs \
  --since YYYY-MM-DD \
  --min-cycles 3 \
  --limit 5 \
  --out-dir docs/retrospective \
  --max-prs 80

Then isolate Codex Cloud feedback per PR:

bash
gh pr view <num> --json reviews,comments --jq '(.reviews + .comments) | map(select(.author.login == "chatgpt-codex-connector"))'

Output notes:

  • docs/retrospective/YYYY-MM-DD-pr-retro.json keeps summary fields for all PRs; picked contains full detail (reviews/comments/commits/files) for the selected PRs only.
  • docs/retrospective/YYYY-MM-DD-pr-retro.csv is built from the picked list.
Show full SKILL.md (229 more words)Show less

Risk-Layer Gate (Preventive)

Before requesting @codex review, check .github/PULL_REQUEST_TEMPLATE.md:

  • If any Risk Layer Trigger is checked, you MUST fill the Risk Layer Addendum.
  • Provide rules/invariants, boundary matrix (>=3), and evidence (tests or repro).
  • Summarize these items in Codex Context so Codex sees the delta clearly.

Evidence Rules

  • Each PR must cite at least 1 evidence item.
  • If Codex feedback is generic, mark low-signal and rely on follow-up fixes or PR gate docs.
  • Do not infer root cause without a traceable artifact.

Common Mistakes

  • Treating Codex review count as the root cause.
  • Ignoring PR context quality (tests, spec links, repro steps).
  • Mixing symptoms (bug) with stage cause (missing invariant).
  • Skipping frontend/backend split on mixed PRs.
  • Triggering @codex review without completing the risk-layer addendum.

Rationalization Table

ExcuseReality
"Codex asked again, so it's Codex's fault"Repeated reviews usually reflect missing context or gaps in our stages.
"Review cycles are enough"Cycles show churn, not cause. Evidence is required.
"Titles explain the issue"Titles are symptoms, not root causes.
"We fixed it later, so root cause is obvious"Fixes show symptom; stage attribution still required.
"Template is optional"Risk-layer addendum is mandatory when any trigger matches.

Red Flags - STOP

  • No evidence chain from Codex feedback to code change.
  • All Codex comments are generic and no follow-up fixes exist.
  • Root cause stated without stage attribution.
  • Evidence relies only on PR title or description.

© victorGPT, 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 docs/skills/pr-review-cycle-retro of victorGPT/vibeusage.

Open the folder on GitHubat commit 4891a58

Compare with similar skills

PR Review Cycle Retro 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.

PR Review Cycle Retro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Review Cycle Retro this skillvictorGPT/vibeusage130—~1.4kAutomated safety check: PassMIT
Dough Landterryyin/lizard2.5k—~2.7kAutomated safety check: PassCustom licence
Review PRapache/shardingsphere21k—~6.5kAutomated safety check: PassApache-2.0
Om Auto Fix Issuego-musicfox/go-musicfox2.6k1 repos~5kAutomated safety check: NotesGPL-3.0
Reviewing Pull RequestsShopify/shopify-app-js541—~1.9kAutomated safety check: PassMIT
Issue BriefVasiHemanth/tokentelemetry379—~1.5kAutomated safety check: PassMIT

Similar skills

  • Dough Land

    terryyin/lizard

    Dough Land lands everything in one reviewed checkout on the authorized remote trunk: commits all of its changes, reconciles and publishes them without force, and refreshes a supplied default…

    2.5k GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Review PR

    apache/shardingsphere

    Review Apache ShardingSphere or user-authorized downstream pull requests and PR discussions from public or authorized repository evidence.

    21k GitHub stars~6.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Om Auto Fix Issue

    go-musicfox/go-musicfox

    Fix or implement a tracker issue end to end from a single command — takes an issue id or a plain problem description (filed first via om-prepare-issue), classifies, then drives the bug autofix chain…

    2.6k GitHub starsUsed in 1 repo~5k tokens
    DevelopmentAuto-check: notes
  • Reviewing Pull Requests

    Shopify/shopify-app-js

    Official

    Reviews pull requests for Shopify/shopify-app-js with comprehensive analysis including semver compliance (MAJOR/MINOR/PATCH classification), single responsibility validation, pattern consistency…

    541 GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Issue Brief

    VasiHemanth/tokentelemetry

    Explain a GitHub issue, discussion, or feature request in plain language before deciding whether to build it.

    379 GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Issue Tracer

    ZaxbyHub/opencode-swarm

    Drives a bug report from validation and root-cause tracing through a critic-reviewed plan, an approved minimal fix and a PR-ready closure, never merging without recorded human approval.

    496 GitHub stars~4.4k tokensUpdated today
    DevelopmentAuto-check passed

More from victorGPT/vibeusage

  • Frontend UI Functional

    victorGPT/vibeusage

    A skill your agent uses when building or refactoring functional React/Vite/Tailwind UI pages, templates, or component libraries that need consistent structure, tokenized styling, accessibility…

    130 GitHub stars~939 tokensUpdated 2 mo ago
    Auto-check passed
  • Backend Mvp Guardrails

    victorGPT/vibeusage

    A skill your agent uses when designing or reviewing a backend MVP with tight budget, evolving schema, and reliance on third-party backends where idempotency, replay, and responsibility attribution…

    130 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Codex PR Review Loop

    victorGPT/vibeusage

    A skill your agent uses when managing Codex review iterations for a PR and you must enforce preflight risk-layer checks and post-merge learning capture.

    130 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Vibeusage Design

    victorGPT/vibeusage

    A skill your agent uses to generate well-branded interfaces and assets for VibeUsage, either for production or throwaway prototypes/mocks/etc.

    130 GitHub stars~566 tokensUpdated 2 mo ago
    Auto-check passed
  • Vibeusage Agent Readiness

    victorGPT/vibeusage

    Use VibeUsage to track AI coding agent token usage, inspect model and project usage, and find scoped API documentation.

    130 GitHub stars~252 tokensUpdated 2 mo ago
    Auto-check passed

Questions about PR Review Cycle Retro

What does PR Review Cycle Retro do?

A skill your agent uses when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage. PR Review Cycle Retro is an agent skill from victorGPT/vibeusage. Use when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

When should I use PR Review Cycle Retro?

PR Review Cycle Retro fits situations like: A team sees repeated @codex review cycles; Codex Cloud feedback churn and needs root-cause attribution by development stage.

How do I install PR Review Cycle Retro in Claude Code?

Run `npx skills add victorGPT/vibeusage --skill pr-review-cycle-retro -a claude-code`. Or copy the skill folder (docs/skills/pr-review-cycle-retro in victorGPT/vibeusage) into .claude/skills/pr-review-cycle-retro in your project. Claude Code loads it when a task matches its description.

How do I install PR Review Cycle Retro in Codex?

Run `npx skills add victorGPT/vibeusage --skill pr-review-cycle-retro -a codex`. Or copy the skill folder (docs/skills/pr-review-cycle-retro in victorGPT/vibeusage) into .agents/skills/pr-review-cycle-retro in your project. Codex loads it when a task matches its description.

Can I use PR Review Cycle Retro 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 victorGPT/vibeusage --skill pr-review-cycle-retro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-review-cycle-retro, .gemini/skills/pr-review-cycle-retro, .github/skills/pr-review-cycle-retro and .opencode/skills/pr-review-cycle-retro in your project.

What does PR Review Cycle Retro need to run?

Going by SKILL.md and its folder, PR Review Cycle Retro needs the command-line tools its instructions call (node and gh).

Does PR Review Cycle Retro access the network?

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

Is PR Review Cycle Retro 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 PR Review Cycle Retro use?

PR Review Cycle Retro 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 PR Review Cycle Retro use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 PR Review Cycle Retro?

Skills that share tags, products or a category with PR Review Cycle Retro: Dough Land (terryyin/lizard, 2.5k stars), Review PR (apache/shardingsphere, 21k stars), Om Auto Fix Issue (go-musicfox/go-musicfox, 2.6k stars) and Reviewing Pull Requests (Shopify/shopify-app-js, 541 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Review Cycle Retro?

victorGPT (a GitHub user) maintains it in victorGPT/vibeusage, which has 130 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on July 31, 2026.

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