SkillHub is a self-hosted registry where organizations publish, discover, version, and manage reusable skills for AI agents. Teams use it to share governed skill packages privately, with namespaces, role-based access control, audit logs, and CLI installation; the catalogue entries are skills and related agent integrations that can be managed through it.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add iflytek/skillhub --skill adversarial-reviewgit clone --depth 1 https://github.com/iflytek/skillhubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/iflytek/skillhub/adversarial-review)<a href="https://agentmods.dev/skills/iflytek/skillhub/adversarial-review"><img src="https://agentmods.dev/badge/skills/iflytek/skillhub/adversarial-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iflytek/skillhub/adversarial-review"><img src="https://agentmods.dev/badge/skills/iflytek/skillhub/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00203 | $0.04262 |
| Opus 5.5 | $0.00081 | $0.01705 |
| Sonnet 5.5 | $0.00041 | $0.00852 |
| Haiku 4.5 | $0.00020 | $0.00426 |
Grade A, and why
adversarial-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
三方对抗式代码评审（Blue Team / Third Party / Adjudication）
这个 skill 要解决什么
单人或单 AI 写代码，最大的风险不是"不会写"，而是：
- 用未验证的乐观假设说服自己推迟修复（"这个兜底应该够了吧"）；
- 测试提供假安全感（测试全绿，但功能其实早坏了）；
- 为了修 A 而引入 B（新写的修复代码本身没被独立审视）。
这三个问题靠"再仔细看一遍"解决不了——写代码的人和审代码的人是同一个，就一定会为自己辩护。只能靠结构化的对抗关系：
| 角色 | 立场 | 硬性约束 |
|---|---|---|
| 蓝军 | 敌意审查——假设代码会出事，去证明 | 每条结论必须附证据链（文件:行号 / 实测命令 / 上游源码）；🔴/🟠 必须是实测结论，仅凭推理最高 🟡；禁止空话 |
| 第三方 | 独立审计——不信任任何一方文档，直接读代码 | 逐条复核"声称修了的是否真修了"、专找修改引入的新缺陷、并稽核蓝军漏掉了哪些维度 |
| 中立裁定 | 对双方结论逐条采纳 / 驳回 / 改级 | 必须由与蓝军不同的 agent 担任；当事人不能当法官 |
关键不是"多找两个 AI 看看"，而是顺序与互不信任：第三方不信开发团队，裁定方不信蓝军和第三方。任一环节缺失，闭环就破。
配套文件（按需读取）
references/review-dimensions.md—— 完整质量维度清单（19 项）。第 0 步按改动类型选维度时必须读，否则审查会漏掉大片区域。references/prompt-templates.md—— 三个角色的完整提示词模板 + 占位符约定 + 「设计要点」表（改模板前必读）。第 1/2/3 步派发子代理时直接取用，不要临时自编。references/quickstart.md—— 面向用户的上手说明（档位选择、什么时候不该用它）。examples/sample-review.md—— 一次真实评审的产出样例。
⚠️ 能力边界（必须向用户如实说明） 子代理与主代理通常是同一模型，这不是真正独立的第三方。其价值来自角色约束 + 强制证据，而非"另一个 AI 的观点"。
- ✅ 能有效抓出：代码级错误、逻辑漏洞、测试造假、自相矛盾、遗漏分支、声明与实现不符；
- ❌ 抓不出：双方共有的知识盲区（例如对某个上游行为的一致误解）。若某个结论依赖外部系统行为，必须要求实测验证，而不是两个 agent 互相点头。
向用户汇报时，不要说"经独立第三方验证无误"，要说"经同模型不同角色的对抗审查"。
🔁 降级模式（宿主无子代理能力时） 若宿主不提供
subagent，只能由同一个 agent 串行扮演三角色。此时：
- 独立性已被显著削弱，第 2、3 步的价值大幅下降；
- 必须在报告开头显式声明"本次为降级模式，角色由同一 agent 串行扮演"；
- 不得使用"独立复核""第三方验证"等措辞；
- 有条件时优先换一个有子代理能力的宿主，而不是将就。
执行流程
第 0 步：确定档位、范围与维度
先问用户或从上下文判断档位（默认标准档）：
| 档位 | 配置 | 相对成本 | 适用 |
|---|---|---|---|
| 轻档 | 1 个蓝军（聚焦选定维度） | ~1x | 小改动、时间紧 |
| 标准档（默认） | 蓝军全量 → 第三方复核 → 中立裁定，共 3 轮 | ~3x | 一般功能版本 |
| 重档 | 标准档 + 多路子代理并行交叉验证（按维度分组并行审） | ~5-8x | 发布前、重大重构、涉及上游兼容 |
（~Nx 为相对一轮蓝军审查的 token 经验估计，未经精确计量。）
必做四件事：
- 确定基线：
git rev-parse --short HEAD+git status，写进报告表头。 - 把待审状态提交或暂存——让蓝军拿到可复现的基线。工作区一片混乱时审查结论不可靠。
- 选维度：读
references/review-dimensions.md，按"按改动类型选维度"表选出本次必审维度。不要默认全审——19 项全塞进一次审查只会让报告又长又浅。 - 定报告目录（默认
docs/review/）。
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 182 lines · 203 tokens per session scan A 9ae38522bc6b
adversarial-review is a skill published in the GitHub repository iflytek/skillhub (5,223 stars, last pushed today), licensed Apache-2.0. It adds 203 tokens to every session and 4,262 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for architecture review, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source-file search.
openclaw-docs
Find authoritative guidance for installing, configuring, operating, securing, and troubleshooting OpenClaw, including channels, model providers, Gateway operations, tools, plugins, automation, nodes, multi-agent routing, and CLI errors. Use for any question or maintenance task involving an OpenClaw installation…
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
clawhub-pr-maintainer
Use when reviewing, triaging, validating, or discussing ClawHub GitHub issues or pull requests, including author context, CI, UI proof, evidence, labels, close decisions, and maintainer handoff.