Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

Commencer

autoreview

Étoiles1

Forks0

Mis à jour30 mai 2026 à 15:21

Run structured code/security review for local, branch, or commit diffs with explicit RED-safe routing.

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

alfredolopez80

alfredolopez80/codex-ralph-vault-loop

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

7 fichiers

SKILL.md

readonly

name	autoreview
description	Run structured code/security review for local, branch, or commit diffs with explicit RED-safe routing.

AutoReview

Use this skill for AI-assisted code review of local, branch, or commit changes when the reviewed content is safe for the selected reviewer engine.

This local Ralph variant changes the upstream defaults:

Sensitive content blocks review before any reviewer engine is invoked.
Web search is disabled by default and requires --web-search.
Untracked files are excluded by default and require --include-untracked.
git fetch is disabled by default and requires --fetch.
Findings outside changed files are preserved when causally tied to the change.
--parallel-tests is explicit trusted shell input from the operator.
Real reviewer execution requires --review-pass N; --review-total M defaults to 2 and is capped at 10.

Bounded-pass stop rule

Never run an open-ended fix/review loop.

Choose the total pass budget before starting, between 1 and 10.
Run each pass at most once, using --review-pass N --review-total M.
Do not commit between passes. Batch findings and fixes.
Stop early if a pass returns no findings.
Stop after pass M even if findings remain; report them as residual findings for human decision instead of running another automatic correction loop.

Run

python3 skills/autoreview/scripts/autoreview.py --mode auto --dry-run
python3 skills/autoreview/scripts/autoreview.py --mode local --review-pass 1 --review-total 10
python3 skills/autoreview/scripts/autoreview.py --mode branch --base origin/main --review-pass 1 --review-total 10
python3 skills/autoreview/scripts/autoreview.py --mode branch --base origin/main --review-pass 10 --review-total 10
python3 skills/autoreview/scripts/autoreview.py --mode commit --commit HEAD --review-pass 1 --review-total 10

Use web search only for public/GREEN context:

python3 skills/autoreview/scripts/autoreview.py --mode branch --web-search --sensitivity GREEN --review-pass 1 --review-total 10

Keep this skill repo-local until review passes. Promote the whole skills/autoreview/ directory to the global skill root only after explicit user approval.

Plus depuis ce dépôt

même dépôt

improve-prompt

alfredolopez80/codex-ralph-vault-loop

Improve, audit, simplify, rewrite, or migrate prompts, tool descriptions, agent instructions, and prompt stacks for GPT-5.6 Sol or the GPT-5.6 family. Use for outcome-first prompt design, autonomy boundaries, tool routing, PTC, grounding, verbosity, reasoning effort, and prompt evals.

2026-07-161

ultrathink

alfredolopez80/codex-ralph-vault-loop

Apply a deep, design-minded engineering workflow for complex work that needs careful planning, iteration, and simplification.

2026-07-161

claude-agentic-review

alfredolopez80/codex-ralph-vault-loop

Use when preparing or running a Claude CLI agentic engineering review through claude -p for repository audits, architecture analysis, system design, security review, large refactors, specs, RFCs, or evidence-grounded long-form engineering analysis.

2026-06-241

zcode-agentic-builder

alfredolopez80/codex-ralph-vault-loop

Use when preparing or running a ZCode GLM-5.2 agentic builder workflow through zcode --prompt for fast implementation, iterative code generation, focused fixes, and validation on an existing repository.

2026-06-241

adversarial

alfredolopez80/codex-ralph-vault-loop

Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.

2026-06-191

bugbot-pr-review

alfredolopez80/codex-ralph-vault-loop

Review and adjudicate Bugbot, Cursor, Seer, and similar automated PR feedback with local evidence before accepting, fixing, or dismissing findings.

2026-06-121

AutoReview

Use this skill for AI-assisted code review of local, branch, or commit changes when the reviewed content is safe for the selected reviewer engine.

This local Ralph variant changes the upstream defaults:

Sensitive content blocks review before any reviewer engine is invoked.

Web search is disabled by default and requires --web-search.

Untracked files are excluded by default and require --include-untracked.

git fetch is disabled by default and requires --fetch.

Findings outside changed files are preserved when causally tied to the change.

--parallel-tests is explicit trusted shell input from the operator.

Real reviewer execution requires --review-pass N; --review-total M defaults to 2 and is capped at 10.

Bounded-pass stop rule

Never run an open-ended fix/review loop.

Choose the total pass budget before starting, between 1 and 10.

Run each pass at most once, using --review-pass N --review-total M.

Do not commit between passes. Batch findings and fixes.

Stop early if a pass returns no findings.

Stop after pass M even if findings remain; report them as residual findings for human decision instead of running another automatic correction loop.

Run

python3 skills/autoreview/scripts/autoreview.py --mode auto --dry-run python3 skills/autoreview/scripts/autoreview.py --mode local --review-pass 1 --review-total 10 python3 skills/autoreview/scripts/autoreview.py --mode branch --base origin/main --review-pass 1 --review-total 10 python3 skills/autoreview/scripts/autoreview.py --mode branch --base origin/main --review-pass 10 --review-total 10 python3 skills/autoreview/scripts/autoreview.py --mode commit --commit HEAD --review-pass 1 --review-total 10

Use web search only for public/GREEN context:

python3 skills/autoreview/scripts/autoreview.py --mode branch --web-search --sensitivity GREEN --review-pass 1 --review-total 10

Keep this skill repo-local until review passes. Promote the whole skills/autoreview/ directory to the global skill root only after explicit user approval.