تشغيل أي مهارة في Manus بنقرة واحدة

ابدأ الآن

autoreview

النجوم١

التفرعات٠

آخر تحديث٣٠ مايو ٢٠٢٦ في ١٥:٢١

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

التثبيت

التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.

تشغيل في Manus

المصدر

alfredolopez80

alfredolopez80/codex-ralph-vault-loop

فتح مستودع GitHub عرض مستودعات المنشئ

تنزيل

تشغيل في Manus

المهن ذات الصلةSOC

استنادا إلى تصنيف SOC المهني

محللو ضمان جودة البرمجيات والمختبرونمهن الحاسوب والرياضيات·SOC 15-1253

مستكشف الملفات

7 ملفات

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.

المزيد من هذا المستودع

نفس المستودع

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.