Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

adversarial-review

Estrelas4

Forks1

Atualizado19 de julho de 2026 às 08:19

Thin pointer: OpenClaw agents must load workspace skill openclaw/workspace/skills/adversarial-review/SKILL.md and run host scripts themselves. Humans only state intent (审一下 / 对抗审查).

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

yunsii

yunsii/wezdeck

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de garantia de qualidade de software e testadoresInformática e Matemática·SOC 15-1253

Explorador de arquivos

8 arquivos

SKILL.md

readonly

name	adversarial-review
description	Thin pointer: OpenClaw agents must load workspace skill openclaw/workspace/skills/adversarial-review/SKILL.md and run host scripts themselves. Humans only state intent (审一下 / 对抗审查).

Adversarial review (runner-side pointer)

Canonical agent skill: openclaw/workspace/skills/adversarial-review/SKILL.md

That skill tells Main/agents to:

Resolve REPO_ROOT / worktree
Run scripts/dev/adversarial-review/run.sh with --writer …
Paste L0-20 disclosure — without asking the human to run the script

Docs: docs/adversarial-review.md. Select: lib/select-backends.sh.

Mais deste repositório

mesmo repositório

task-ledger

yunsii/wezdeck

Ledger development tasks to Feishu Base via dev-task-ledger.sh. Write roots from ~/.openclaw/tasks-allowlist.json (per agent). Use on accept/confirm/close of coding/ops work; not for pure Q&A.

2026-07-194

chrome-devtools

yunsii/wezdeck

Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.

2026-07-194

dev-task

yunsii/wezdeck

Allowlisted development (wezdeck (+ optional team roots in local config)) under OpenClaw: wezdeck defaults to primary master; claw worktrees when parallel/isolation needed; 团队仓 still prefers claw-*; human/Claw rails (H1/H2, C1/C2/C3), ACP access layer.

2026-07-194

error-closed-loop

yunsii/wezdeck

Full error closed-loop for Dex (Main): diagnose, safe self-fix, verify, report; platform Exec failed handling; escalation with options. Load when handling failures or writing failure reports.

2026-07-194

exec-risk

yunsii/wezdeck

Host shell MUST go through claw-run (gate then exec). Three layers: rules → Grok re-check → human only if still danger. Prefer claw-run over bare exec.

2026-07-194

adversarial-review

yunsii/wezdeck

Multi-role adversarial code review for allowlisted repos. Agent loads this skill and runs host scripts (find → refute → sandbox repro); humans only state intent (e.g. 审一下 / 对抗审查). Use when user asks for adversarial review, task acceptance recommends review, or runtime code changed before merge.

2026-07-194

Execute qualquer Skill com um clique