Run any Skill in Manus with one click

adversarial-review

Stars4

Forks1

UpdatedJuly 19, 2026 at 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).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

yunsii

yunsii/wezdeck

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software Quality Assurance Analysts and TestersComputer and Mathematical Occupations·SOC 15-1253

File Explorer

8 files

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.

More from this repository

same repository

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

Run any Skill with one click