Civil Service Essay Grader
mingchen666/Reviva
公务员考试申论精细批改与多轮改写助手。用户要求“批改申论”“给申论小题打分”“看看漏了哪些采分点”“批改公文/汇报提纲/发言稿”“批改大作文”“逐段修改”“我改完了再批一次”“对比两版答案”，或提交申论材料、题干、作答要求和答案时，应使用本 Skill。覆盖归纳概括、综合分析、提出对策、公文应用文和大作文；输出评分依据等级、模拟得分区间、材料采分点矩阵、逐项/逐段问题、修改任务和二次批改对比。不…
申论小题批改与训练：归纳概括、综合分析、对策启示、公文写作，双视角参考作答 （小马哥版 + 白鹭版）并以阅卷人视角逐条评分。
MITAuto-check passed
Install Shenlun Xiaoti
$ npx skills add coffe-d/Shenlun.skill --skill shenlun-xiaoti -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install coffe-d/Shenlun.skill shenlun-xiaoti --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/coffe-d/Shenlun.skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/shenlun-xiaoti .claude/skills/shenlun-xiaoti && 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 "shenlun-xiaoti" agent skill from https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaoti into .claude/skills/shenlun-xiaoti/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shenlun-xiaoti", 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/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaotiType 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 coffe-d/Shenlun.skill --skill shenlun-xiaoti -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install coffe-d/Shenlun.skill shenlun-xiaoti --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coffe-d/Shenlun.skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/shenlun-xiaoti .agents/skills/shenlun-xiaoti && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "shenlun-xiaoti" agent skill from https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaoti into .agents/skills/shenlun-xiaoti/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shenlun-xiaoti", 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 coffe-d/Shenlun.skill --skill shenlun-xiaoti -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install coffe-d/Shenlun.skill shenlun-xiaoti --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coffe-d/Shenlun.skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/shenlun-xiaoti .cursor/skills/shenlun-xiaoti && 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 "shenlun-xiaoti" agent skill from https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaoti into .cursor/skills/shenlun-xiaoti/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shenlun-xiaoti", 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/coffe-d/Shenlun.skill.git --path skills/shenlun-xiaoti--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 coffe-d/Shenlun.skill --skill shenlun-xiaoti -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install coffe-d/Shenlun.skill shenlun-xiaoti --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coffe-d/Shenlun.skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/shenlun-xiaoti .gemini/skills/shenlun-xiaoti && 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 "shenlun-xiaoti" agent skill from https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaoti into .gemini/skills/shenlun-xiaoti/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shenlun-xiaoti", 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 coffe-d/Shenlun.skill shenlun-xiaotiInstalls 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 coffe-d/Shenlun.skill --skill shenlun-xiaoti -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/coffe-d/Shenlun.skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/shenlun-xiaoti .github/skills/shenlun-xiaoti && 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 "shenlun-xiaoti" agent skill from https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaoti into .github/skills/shenlun-xiaoti/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shenlun-xiaoti", 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 coffe-d/Shenlun.skill --skill shenlun-xiaoti -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install coffe-d/Shenlun.skill shenlun-xiaoti --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/coffe-d/Shenlun.skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/shenlun-xiaoti .opencode/skills/shenlun-xiaoti && 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 "shenlun-xiaoti" agent skill from https://github.com/coffe-d/Shenlun.skill/tree/master/skills/shenlun-xiaoti into .opencode/skills/shenlun-xiaoti/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "shenlun-xiaoti", 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
shenlun-xiaoti- GitHub stars
- 122
- Token cost
- ~685 tokens
- SKILL.md length
- 135 words
- Files
- 11 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
申论小题批改与训练：归纳概括、综合分析、对策启示、公文写作，双视角参考作答 （小马哥版 + 白鹭版）并以阅卷人视角逐条评分。
- Works in 5 steps: 判题型与要素 → 【门控】读白鹭 references/bai-lu-methodology.md… → 【门控】读小马哥… → …
- SKILL.md covers 一、解题流程（门控）, 二、用户作答评判, 三、公文写作题补充 and 四、反馈输出, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Shenlun Xiaoti is an agent skill from coffe-d/Shenlun.skill. 申论小题批改与训练：归纳概括、综合分析、对策启示、公文写作，双视角参考作答 （小马哥版 + 白鹭版）并以阅卷人视角逐条评分。 重要：用户只要涉及申论小题——概括题、分析题、对策题、公文题，或提交小题作答 要求批改、要参考答案、问某道小题怎么答——都必须使用本 skill。 覆盖关键词：申论、小题、归纳概括、综合分析、对策题、启示题、公文写作、 倡议书、通知、报告、提纲、讲话稿、批改、评分、参考答案、采分点、 小马哥、白鹭、总括句、概括词、分类归并。 图片输入（试卷照片、手写作答）由 shenlun-router 处理。
Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/bai-lu-methodology.md`, `references/real-exams/2022-fujian-shi.md` and `references/real-exams/2023-fujian-xianxiang.md`).
The repository describes itself as: 深度解析小马哥、白鹭、袁东三位老师的申论教学理念，整合出一套申论做题与智能批改的实用skill. The licence is MIT.
Example prompts
- “/shenlun-xiaoti”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 判题型与要素
- 【门控】读白鹭 references/bai-lu-methodology.md → 取其审题法与阅读法
- 【门控】读小马哥 references/xiaoma-methodology.md → 取其结构逻辑
- 分别产出两版作答，两版必须结构性地不同（若只是换措辞，说明没真按各自方法论产出，须重做）
- 给"差异对照"，不只是两个分数
What it can do on your machine
Read from SKILL.md and the folder at commit 354341c. 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.
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
Shenlun Xiaoti loads about 685 tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 135 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
The full file from coffe-d/Shenlun.skill at commit 354341c, republished under its MIT licence (© coffe-d). 135 words, ~685 tokens.
Download SKILL.mdSave it as
.claude/skills/shenlun-xiaoti/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.- name
- shenlun-xiaoti
- description
- 申论小题批改与训练：归纳概括、综合分析、对策启示、公文写作，双视角参考作答 （小马哥版 + 白鹭版）并以阅卷人视角逐条评分。 **重要：用户只要涉及申论小题——概括题、分析题、对策题、公文题，或提交小题作答 要求批改、要参考答案、问某道小题怎么答——都必须使用本 skill。** 覆盖关键词：申论、小题、归纳概括、综合分析、对策题、启示题、公文写作、 倡议书、通知、报告、提纲、讲话稿、批改、评分、参考答案、采分点、 小马哥、白鹭、总括句、概括词、分类归并。 图片输入（试卷照片、手写作答）由 shenlun-router 处理。
申论小题
本 skill 只管小题（归纳概括／综合分析／对策／公文）。大作文见 shenlun-dawenti；
图片输入、真题识别、错题库、导出见 shenlun-router。
一、解题流程（门控）
⛔ 不要照本文件产出答案——本文件只给流程与门控，两版答案的方法论依据在名师库。 （旧版把一份"压缩版"流程内联在主文件里，结果两版答案长得一样——那正是名师库失效的原因。）
- 判题型与要素
- 【门控】读白鹭
references/bai-lu-methodology.md→ 取其审题法与阅读法 - 【门控】读小马哥
references/xiaoma-methodology.md→ 取其结构逻辑 - 分别产出两版作答，两版必须结构性地不同（若只是换措辞，说明没真按各自方法论产出，须重做）
- 给"差异对照"，不只是两个分数
题型判定
| 题干关键词 | 题型 |
|---|---|
| 概括/梳理/总结/提炼/归纳 + 问题/原因/做法/经验/成效/变化/特点 | 归纳概括题 |
| 分析、理解、评析、认识、看法、谈谈为什么 | 综合分析题 |
| 提出/建议/对策/启示 | 对策启示题 |
| 写一份/起草/拟写 + 文种 | 公文写作题 |
两版结构特征
| 小马哥版 | 白鹭版 | |
|---|---|---|
| 结构特征 | 结构固定、要素融合——一律「上位概括词 + 具体做法」 | 结构随题干、要素分栏——题干有几个要素/对象/主体就分几栏 |
| 实例 | 「推广铁路运输。与上级部门协同推进…」 | 「举措 1:… / 成效 1:…」 |
差异对照五项：① 各自多踩/漏了哪个采分点 ② 分类逻辑差异 ③ 各自适用场景 ④ 各自风险（小马哥易结构松散；白鹭易分栏过细） ⑤ 落点：帮使用者判断"我更适合哪一套"。
诚实边界：某些环节两版其实不分歧（如总括句有无、概括词需统一句式）， 必须直说"此处两版一致"，不得为了凑对照而编造差异。差异来源详见白鹭库第八节。
二、用户作答评判
评分 = 采分点覆盖法（子项逐条核对）：拆子项 → 逐条核对（踩到≥80%满分／40–80%一半／<40%零分）→ 汇总。
核心规则：
- 申论踩点加分制，不存在倒扣；编造内容不得分但不额外扣分
- 口语化不单独扣分，但命中不了采分点关键词 → 该项不得分
- 概括词必须来自材料，禁止自创
- 答案不写任何非得分句
- 不做错别字检查（除非用户明确要求）；表述问题只给规范替换建议
评分必须使用题目实际分值，不是百分制。完整评分方法与格式模板见 references/scoring-rules.md。
作答铁律（字数/句子结构/去水/概括词/自检）见 references/writing-rules.md。
手写作答照片：不因拍照质量（模糊、光线、倾斜）扣分；字迹与卷面只在无题干模式下按兜底模式评定。
三、公文写作题补充
除上述规则外，公文题额外关注：
- 格式分：标题、称呼、落款、日期等文种格式要素
- 内容选择：材料要点按文种目的筛选——倡议书聚焦"为什么做/怎么做/怎么参与"，汇报材料聚焦"做法/成效/数据"
- 语言风格：倡议书需感染力+号召结尾；报告/提纲需客观简洁
四、反馈输出
默认用精简格式；用户说"展开"/"详细"才切换详细格式。格式模板见 references/scoring-rules.md。
输出顺序（改进建议优先，不做诊断）：
- 必须补的失分点（2-3 个，各附"影响哪个维度 + 怎么改"）
- 表述升级（口语化 → 申论规范表述，见
../shared/references/expression-upgrade-rules.md） - 成语与名言可用之处
- 论证思路怎么改
- 优化示范（挑 1-2 句改写对比）
五、名师库索引
| 文件 | 内容 |
|---|---|
references/bai-lu-methodology.md | 白鹭小题（8类信号词以此为准；第八节含差异对照权威版） |
references/xiaoma-methodology.md | 小马哥小题（开头有验证状态矩阵：已证实／已证伪／待验证） |
references/scoring-rules.md | 评分方法（Step 0-5）、什么不算扣分点、格式模板 |
references/writing-rules.md | 作答铁律（7 条） |
references/real-exams/ | 真题库（INDEX.md 索引 + _TEMPLATE.md 模板） |
使用限制：名师库中标 ❌ 的条项（如"归并＝按领域归类""3W 十六字方针"） 不得用于批改；标 ⚠️ 的仅供参考。详见各库开头的验证状态矩阵。
六、批改收尾（不得跳过）
批改完成后必须走一遍 shenlun-router 的错题库流程：记录本次失分点类型、更新计数、
若累计 ≥2 则给出复发提醒。规则见 ../shared/references/error-bank-rules.md。
© coffe-d, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 10 other files (references) in skills/shenlun-xiaoti of coffe-d/Shenlun.skill.
- SKILL.md
- references/bai-lu-methodology.md
- references/real-exams/2022-fujian-shi.md
- references/real-exams/2023-fujian-xianxiang.md
- references/real-exams/2023-sichuan-shi.md
- references/real-exams/2024-guangxi-A.md
- references/real-exams/INDEX.md
- references/real-exams/_TEMPLATE.md
- references/scoring-rules.md
- references/writing-rules.md
- references/xiaoma-methodology.md
Open the folder on GitHubat commit 354341c
Compare with similar skills
Shenlun Xiaoti next to the 4 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 |
|---|---|---|---|---|---|---|
| Shenlun Xiaoti this skillcoffe-d/Shenlun.skill | 122 | — | ~685 | Automated safety check: Pass | MIT | |
| Civil Service Essay Gradermingchen666/Reviva | 244 | — | ~1.2k | Automated safety check: Pass | None | |
| Linkfox Amazon Opportunity Report By Keywordlinkfox-ai/linkfox-skills | 107 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Shenlun Routercoffe-d/Shenlun.skill | 122 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Shenlun Dawenticoffe-d/Shenlun.skill | 122 | — | ~692 | Automated safety check: Pass | MIT |
Similar skills
Linkfox Amazon Opportunity Report By Keyword
linkfox-ai/linkfox-skills
按关键词查询亚马逊商业洞察报告，涵盖市场潜力、产品特征、用户评论、客户画像、搜索趋势、定价分析六大维度的AI 综合分析。当用户提到亚马逊商业洞察、市场洞察报告、选品报告、市场机会分析、竞争格局、消费者画像、定价分析、细分市场调研、Amazon opportunity report, market insight, business insight, market potential…
Shenlun Router
coffe-d/Shenlun.skill
申论训练总调度。负责跨题型的公共环节：图片/文字输入处理、真题识别与匹配、 命题预判、错题库记录与复发提醒，并把具体批改分派给 shenlun-xiaoti（小题） 或 shenlun-dawenti（大作文）。
Shenlun Dawenti
coffe-d/Shenlun.skill
申论大作文批改与训练：袁东体系（累进四类文评分、双主题 AB/ABC 型模板、 标题等式、开头 6 种写法、分论点 5 步走、结尾 3 步走），并含无题干时的通用文章评改模式。
Questions about Shenlun Xiaoti
What does Shenlun Xiaoti do?
申论小题批改与训练：归纳概括、综合分析、对策启示、公文写作，双视角参考作答 （小马哥版 + 白鹭版）并以阅卷人视角逐条评分。. skill.
How do I install Shenlun Xiaoti in Claude Code?
Run `npx skills add coffe-d/Shenlun.skill --skill shenlun-xiaoti -a claude-code`. Or copy the skill folder (skills/shenlun-xiaoti in coffe-d/Shenlun.skill) into .claude/skills/shenlun-xiaoti in your project. Claude Code loads it when a task matches its description.
How do I install Shenlun Xiaoti in Codex?
Run `npx skills add coffe-d/Shenlun.skill --skill shenlun-xiaoti -a codex`. Or copy the skill folder (skills/shenlun-xiaoti in coffe-d/Shenlun.skill) into .agents/skills/shenlun-xiaoti in your project. Codex loads it when a task matches its description.
Can I use Shenlun Xiaoti 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 coffe-d/Shenlun.skill --skill shenlun-xiaoti -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shenlun-xiaoti, .gemini/skills/shenlun-xiaoti, .github/skills/shenlun-xiaoti and .opencode/skills/shenlun-xiaoti in your project.
What does Shenlun Xiaoti need to run?
SKILL.md names no scripts, command-line tools or credentials: Shenlun Xiaoti is instructions for the agent only.
Does Shenlun Xiaoti 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 Shenlun Xiaoti 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 Shenlun Xiaoti use?
Shenlun Xiaoti is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Shenlun Xiaoti use?
About 685 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 18k tokens, read only when the agent opens those files.
What are the alternatives to Shenlun Xiaoti?
Skills that share tags, products or a category with Shenlun Xiaoti: Civil Service Essay Grader (mingchen666/Reviva, 244 stars), Linkfox Amazon Opportunity Report By Keyword (linkfox-ai/linkfox-skills, 107 stars), Shenlun Router (coffe-d/Shenlun.skill, 122 stars) and Shenlun Dawenti (coffe-d/Shenlun.skill, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Shenlun Xiaoti?
coffe-d (a GitHub user) maintains it in coffe-d/Shenlun.skill, which has 122 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 25, 2026.
Source: coffe-d/Shenlun.skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.