Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
多轮对抗式稿件打磨技能。通过"批评→改写→综合→盲评"循环，像学术同行评审一样反复打磨稿件直到收敛。所有中间产物（批评、改写、综合、评分）保存为独立文件，完整记录进化过程。当用户说"对抗打磨""反复打磨""深度打磨""多轮润色""盲评打磨""打磨到收敛""帮我把这篇稿子磨一磨""pressure polish""adversarial…
Install Adversarial Polish
$ npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JimLiu/Illustrated-Agent-Skills adversarial-polish --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JimLiu/Illustrated-Agent-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/adversarial-polish .claude/skills/adversarial-polish && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "adversarial-polish" agent skill from https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polish into .claude/skills/adversarial-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-polish", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polishType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JimLiu/Illustrated-Agent-Skills adversarial-polish --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/Illustrated-Agent-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/adversarial-polish .agents/skills/adversarial-polish && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "adversarial-polish" agent skill from https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polish into .agents/skills/adversarial-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-polish", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JimLiu/Illustrated-Agent-Skills adversarial-polish --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/Illustrated-Agent-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/adversarial-polish .cursor/skills/adversarial-polish && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "adversarial-polish" agent skill from https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polish into .cursor/skills/adversarial-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-polish", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/JimLiu/Illustrated-Agent-Skills.git --path skills/adversarial-polish--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JimLiu/Illustrated-Agent-Skills adversarial-polish --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/Illustrated-Agent-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/adversarial-polish .gemini/skills/adversarial-polish && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "adversarial-polish" agent skill from https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polish into .gemini/skills/adversarial-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-polish", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install JimLiu/Illustrated-Agent-Skills adversarial-polishInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JimLiu/Illustrated-Agent-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/adversarial-polish .github/skills/adversarial-polish && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "adversarial-polish" agent skill from https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polish into .github/skills/adversarial-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-polish", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JimLiu/Illustrated-Agent-Skills adversarial-polish --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/Illustrated-Agent-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/adversarial-polish .opencode/skills/adversarial-polish && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "adversarial-polish" agent skill from https://github.com/JimLiu/Illustrated-Agent-Skills/tree/main/skills/adversarial-polish into .opencode/skills/adversarial-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adversarial-polish", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
adversarial-polish- GitHub stars
- 714
- Token cost
- ~2k tokens
- SKILL.md length
- 411 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- None found
At a glance
多轮对抗式稿件打磨技能。通过"批评→改写→综合→盲评"循环，像学术同行评审一样反复打磨稿件直到收敛。所有中间产物（批评、改写、综合、评分）保存为独立文件，完整记录进化过程。当用户说"对抗打磨""反复打磨""深度打磨""多轮润色""盲评打磨""打磨到收敛""帮我把这篇稿子磨一磨""pressure polish""adversarial…
- Works in 4 steps: 稻草人 → spawn 一个 sub-agent，prompt… → 改写者 → spawn 一个新的… → 综合者 → spawn 一个新的… → …
- Tasks that involve Subagents
- SKILL.md covers 核心理念, ⚠️ 执行模型：Sub-Agent 隔离（核心机制）, 工作流程 and 重要原则, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Adversarial Polish is an agent skill from JimLiu/Illustrated-Agent-Skills. 多轮对抗式稿件打磨技能。通过"批评→改写→综合→盲评"循环，像学术同行评审一样反复打磨稿件直到收敛。所有中间产物（批评、改写、综合、评分）保存为独立文件，完整记录进化过程。当用户说"对抗打磨""反复打磨""深度打磨""多轮润色""盲评打磨""打磨到收敛""帮我把这篇稿子磨一磨""pressure polish""adversarial polish"时触发。也适用于用户说"这篇稿子很重要，帮我好好打磨"或"我需要更高质量的润色"等暗示需要超越单轮润色的场景。注意：如果用户只是要求普通润色，优先使用已有 polish 技能。本技能适合对质量要求极高、愿意花更多时间打磨的稿件。
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: 《图解Skill——AI提效实战指南》官方 Repo.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “批评→改写→综合→盲评”
- “帮我把这篇稿子磨一磨”
- “pressure polish”
- “/adversarial-polish”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 稻草人 → spawn 一个 sub-agent，prompt 中只包含：任务描述 + 当前版本 A 的文本 + 稻草人角色指令（见下文 prompt 模板）。不包含任何历史轮次的批评、改写、投票信息。
- 改写者 → spawn 一个新的 sub-agent（在稻草人完成后），prompt 中只包含：任务描述 + 当前版本 A + 稻草人批评报告 + 改写者角色指令。不包含综合者或评委的任何信息。
- 综合者 → spawn 一个新的 sub-agent（在改写者完成后），prompt 中只包含：任务描述 + "版本甲"和"版本乙"（A 和 B 随机打乱顺序标记）+ 综合者角色指令。不包含稻草人批评报告（综合者不应知道哪个版本是"被批评后改的"）。
- 三位评委 → 同时 spawn 3 个独立 sub-agent（并行执行）。每个评委的 prompt 中只包含：任务描述 + 三个版本（随机标记为 X/Y/Z，打乱顺序，去除所有末尾的改写说明和综合说明）+ 评委角色指令。三位评委之间完全独立，互不可见。
What it can do on your machine
Read from SKILL.md and the folder at commit 6ce5243. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Adversarial Polish loads about 2k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 411 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 411 words (~2,046 tokens).
- name
- adversarial-polish
Files
Just SKILL.md in skills/adversarial-polish of JimLiu/Illustrated-Agent-Skills.
Open the folder on GitHubat commit 6ce5243
Compare with similar skills
Adversarial Polish next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Adversarial Polish this skillJimLiu/Illustrated-Agent-Skills | 714 | — | ~2k | Automated safety check: Pass | None | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~11k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from JimLiu/Illustrated-Agent-Skills
All 8 skills in this repoBook Illustrator
JimLiu/Illustrated-Agent-Skills
《图解 Skill —— AI 提效实战指南》专用配图技能。分析本书章节、附录或书稿内容，批量识别需要视觉辅助的位置，并行生成本书统一风格的插图提示词，批量出图，最后回写书稿。
Baoyu Weekly Report
JimLiu/Illustrated-Agent-Skills
生成中文周报（Markdown 表格格式）。当用户提到"周报""写周报""本周工作""weekly report"或描述本周完成的工作内容时触发。即使用户只是随意列出这周做了什么，也应该触发这个技能来帮忙整理成周报。
Content Analyzer
JimLiu/Illustrated-Agent-Skills
素材深度分析技能。当用户提供文章、推文、视频文稿等内容并要求分析时使用. An agent skill from JimLiu/Illustrated-Agent-Skills.
Info Digest
JimLiu/Illustrated-Agent-Skills
把任何输入的信息快速转化为简洁、易懂的中文资讯，让读者一两分钟抓住要点. An agent skill from JimLiu/Illustrated-Agent-Skills.
Interview Writing
JimLiu/Illustrated-Agent-Skills
将播客/视频访谈的分析素材转化为访谈实录整理文章。按访谈原始 顺序组织，保留问答结构的对话感，补充背景解读，让读者通过文字快速了解 访谈全貌。当用户已完成访谈内容分析（有素材包和提纲），需要撰写正式文章 时使用此 skill。
Outliner
JimLiu/Illustrated-Agent-Skills
科技专栏提纲生成技能。当用户提供素材（文章、推文、视频文稿等） 要求生成写作提纲时使用。生成 3-5 个差异化大纲方案（优先包含故事驱动型）， 每个方案保存独立文件供用户选择。
Related
Categories
Questions about Adversarial Polish
What does Adversarial Polish do?
多轮对抗式稿件打磨技能。通过"批评→改写→综合→盲评"循环，像学术同行评审一样反复打磨稿件直到收敛。所有中间产物（批评、改写、综合、评分）保存为独立文件，完整记录进化过程。当用户说"对抗打磨""反复打磨""深度打磨""多轮润色""盲评打磨""打磨到收敛""帮我把这篇稿子磨一磨""pressure polish""adversarial…. Adversarial Polish is an agent skill from JimLiu/Illustrated-Agent-Skills.
When should I use Adversarial Polish?
Adversarial Polish fits situations like: tasks that involve Subagents.
How do I install Adversarial Polish in Claude Code?
Run `npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a claude-code`. Or copy the skill folder (skills/adversarial-polish in JimLiu/Illustrated-Agent-Skills) into .claude/skills/adversarial-polish in your project. Claude Code loads it when a task matches its description.
How do I install Adversarial Polish in Codex?
Run `npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a codex`. Or copy the skill folder (skills/adversarial-polish in JimLiu/Illustrated-Agent-Skills) into .agents/skills/adversarial-polish in your project. Codex loads it when a task matches its description.
Can I use Adversarial Polish in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JimLiu/Illustrated-Agent-Skills --skill adversarial-polish -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adversarial-polish, .gemini/skills/adversarial-polish, .github/skills/adversarial-polish and .opencode/skills/adversarial-polish in your project.
What does Adversarial Polish need to run?
SKILL.md names no scripts, command-line tools or credentials: Adversarial Polish is instructions for the agent only.
Does Adversarial Polish access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Adversarial Polish safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Adversarial Polish use?
No licence was found for Adversarial Polish or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Adversarial Polish use?
About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Adversarial Polish?
Skills that share tags, products or a category with Adversarial Polish: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Adversarial Polish?
JimLiu (a GitHub user) maintains it in JimLiu/Illustrated-Agent-Skills, which has 714 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on June 15, 2026.
Source: JimLiu/Illustrated-Agent-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.