Kaogong Shenlun — Development skill for Claude Code
申论训练与批改:五大题型出题,按真实评分标准踩点给分并给出参考答案.
How to install Kaogong Shenlun
Installs to ~/.claude/skills/kewang0622-kaogong-skill-kaogong-shenlun/SKILL.md
mkdir -p ~/.claude/skills/kewang0622-kaogong-skill-kaogong-shenlun && curl -fsSL https://raw.githubusercontent.com/KeWang0622/kaogong-skill/HEAD/commands/kaogong-shenlun.md -o ~/.claude/skills/kewang0622-kaogong-skill-kaogong-shenlun/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Kaogong Shenlun does
description: 申论训练与批改:五大题型出题,按真实评分标准踩点给分并给出参考答案。Practise 申论 essays and get graded against the official rubric.
启动 **申论训练与批改** 模式。
先读 [`skills/kaogong/references/shenlun.md`](../skills/kaogong/references/shenlun.md),然后按 SKILL.md 的「3. 申论训练与批改」流程执行:
- 让用户选择题型(概括归纳 / 综合分析 / 提出对策 / 应用文 / 大作文)
- 给出材料和题目(材料 800–1500 字,标明字数与分值要求)
- 用户提交答案后批改:
- 打分,写清扣分点和扣了几分
- 逐条指出优点和不足
- 给出参考答案
- 提出改进建议
踩点给分要说明「踩到了哪几个点、漏了哪几个点」。不虚高也不打压。
Alternatives in Development
- Anthropic Cookbook — Official examples and guides from Anthropic 36.3k ★
- Claude Plugins Official — Anthropic-managed directory of high quality Claude Code Plugins 14.9k ★
- Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Rubric Evaluator
Evaluate Claude Code and Codex skill directories with deterministic rubric checks and graded, fixable reports.
Validate Research
Validate research document against FAR (Factual, Actionable, Relevant) rubric
Score Company Icp
Score company evidence {{company_evidence}} against this operator-authored rubric: {{icp_rubric}}. Apply its p
Lens
Review a prompt, page, component, or draft through expert lenses (findings), fix it in place with --fix, or gr
Examiner Sim
Simulate the CAS-AISE examiner — rebuild the real submission PDFs, grade them against the Moodle rubric with a
Ats Score
Score a resume PDF against HackerRank's open-source ATS rubric
Related Agents
Judge Panel
Use when a draft or a past winning entry must be scored against a contest's official rubric before submission.
Mutation Hardener
Dual-mode mutation-testing agent. AUDIT mode runs the mutation tool over a scope and reports surviving mutants
Indicator Sweeper
Sweeps open indicators of an OSINT case against the live web and returns graded, sourced findings (or an expli