Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

reviewer

Étoiles7

Forks0

Mis à jour21 juillet 2026 à 11:06

Run the adversarial, read-only codex reviewer on the current diff and fix what it finds. Invoke as /reviewer with optional focus text and scope flags — it kicks off codex immediately (spends codex/OpenAI quota) and injects the report for Claude to act on. codex reads the whole repo to dig but CANNOT edit anything.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

beyarkay

beyarkay/dotfiles

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en assurance qualité des logiciels et testeursProfessions informatiques et mathématiques·SOC 15-1253

Explorateur de fichiers

3 fichiers

SKILL.md

readonly

name	reviewer
description	Run the adversarial, read-only codex reviewer on the current diff and fix what it finds. Invoke as /reviewer with optional focus text and scope flags — it kicks off codex immediately (spends codex/OpenAI quota) and injects the report for Claude to act on. codex reads the whole repo to dig but CANNOT edit anything.
argument-hint	[focus text] [--uncommitted \| --commit SHA \| --range A..B \| --base BRANCH] [--spec PATH_OR_URL]
allowed-tools	Bash($HOME/.claude/skills/reviewer/review.sh --quiet*)
disable-model-invocation	true

reviewer

The read-only, adversarial codex reviewer has been run on the current diff — it reads the whole repo to dig, but cannot edit anything. Its report:

$HOME/.claude/skills/reviewer/review.sh --quiet --focus-stdin <<'__REVIEWER_FOCUS_EOF__'
$ARGUMENTS
__REVIEWER_FOCUS_EOF__

That report is above. Now act on it:

Triage every finding — real blocker vs nit vs false positive. codex digs but can be wrong: verify each claim against the actual code before touching anything.
Fix the genuine issues yourself (the reviewer never edits). Make the smallest correct change per issue.
Account for the rest: for anything you skip, one line saying why (false positive / out of scope / intended).

Finish with a short summary of what you changed and what you deliberately left. If codex produced no report (e.g. no changes to review, or it errored), say so and stop — don't invent findings.

Args after /reviewer are forwarded to the reviewer: free text = focus; scope flags pick what to review (default: working tree vs merge-base with the base branch); --spec PATH_OR_URL points codex at the original issue/spec by link. Full reference in README.md / review.sh --help.

Plus depuis ce dépôt

même dépôt

ccpeer

beyarkay/dotfiles

Discover other Claude Code sessions running on this machine and message them directly — list who is live and what they are working on, then send a message straight into another session's chat so the two Claudes can talk. Use when context needs to move between sessions instead of the user copy-pasting it by hand, when work in one session depends on what another is doing, or when the user says "ask the other Claude", "tell the session in X", "what is the other Claude doing".

2026-07-217

drop-user-in-file

beyarkay/dotfiles

Hand the keyboard to the user so they can edit a file themselves mid-session, in a real nvim popup, then read back what they changed. Use when the user says things like "drop me into <file>", "let me hand-edit X", "open X in nvim for me", "I'll edit this part myself", "pause so I can tweak it", or otherwise wants to make manual edits rather than have you make them. Requires tmux + nvim.

2026-07-217

pbar

beyarkay/dotfiles

Put a live tqdm progress bar (items/second, ETA) in the status line for any long or repetitive job — batch loops, N-item processing, writing files or JSONL shards, downloads, sweeps, evaluations, migrations — instead of spamming the transcript with "1/200", "2/200". Use whenever a job iterates more than ~20 times or runs longer than ~30 seconds. The `ccbar` CLI can watch a growing file or directory, so the job needs no changes at all.

2026-07-217

quickplot

beyarkay/dotfiles

Quick honest terminal distribution plots (sparkline histogram + box-and-whisker) of numeric data. Use when the user wants a fast in-terminal look at the distribution/spread of some values (e.g. coherence/alignment scores across models) — "histogram of these", "show me the distribution", "plot these numbers", "box plot of", "what do these look like". For throwaway terminal viz, NOT publication plots.

2026-07-217

runpod

beyarkay/dotfiles

Manage RunPod GPU pods and run LLM fine-tuning experiments remotely. Use when user asks to create pods, run training, check training status, manage volumes, or do anything RunPod-related.

2026-07-217

tmux-run

beyarkay/dotfiles

Run a shell command in a specified tmux pane and return the pane's output. Use when user asks to run something in a tmux pane, send a command to tmux, or check tmux pane output.

2026-07-217

name	reviewer
description	Run the adversarial, read-only codex reviewer on the current diff and fix what it finds. Invoke as /reviewer with optional focus text and scope flags — it kicks off codex immediately (spends codex/OpenAI quota) and injects the report for Claude to act on. codex reads the whole repo to dig but CANNOT edit anything.
argument-hint	[focus text] [--uncommitted \| --commit SHA \| --range A..B \| --base BRANCH] [--spec PATH_OR_URL]
allowed-tools	Bash($HOME/.claude/skills/reviewer/review.sh --quiet*)
disable-model-invocation	true

reviewer

The read-only, adversarial codex reviewer has been run on the current diff — it reads the whole repo to dig, but cannot edit anything. Its report:

$HOME/.claude/skills/reviewer/review.sh --quiet --focus-stdin <<'__REVIEWER_FOCUS_EOF__'
$ARGUMENTS
__REVIEWER_FOCUS_EOF__

That report is above. Now act on it:

Triage every finding — real blocker vs nit vs false positive. codex digs but can be wrong: verify each claim against the actual code before touching anything.
Fix the genuine issues yourself (the reviewer never edits). Make the smallest correct change per issue.
Account for the rest: for anything you skip, one line saying why (false positive / out of scope / intended).

Finish with a short summary of what you changed and what you deliberately left. If codex produced no report (e.g. no changes to review, or it errored), say so and stop — don't invent findings.