Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

ChineseResearchLaTeX 模板落地与高保真对齐器 · huangwb8 | DecimalAI

documentationby huangwb8

ChineseResearchLaTeX 模板落地与高保真对齐器

huangwb8/make-latex-model

Source huangwb8/chineseresearchlatex ↗License MIT

当用户明确要求“LaTeX 模板优化”“样式参数对齐”“像素级比对”“make-latex-model”或旧写法“make_latex_model”，或要把 ChineseResearchLaTeX 里的某个项目做成高质量模板时使用。适配 NSFC / paper / thesis / cv 四条产品线；先依据 packages/ 与 projects/ 的真实分层判断改项目层还是公共包，再用各产品线官方构建入口验收。若必须修改 packages 下公共包，需先生成受影响模板回归计划并完成相关回归；NSFC 专项工具仅在明确属于 NSFC 参数对齐场景时按需使用。

SkillScore68Maintained

Automatic

Doc Ops pack

Last verified 9/9/2026

What it changes

Passed 13 of 19 test cases with the skill, and 3 of 19 without it.

Without skill18%

With skill68%

Checks it passed that the model alone missed

Rejects compiling directly with raw xelatex
Validates Chinese language output for CV templates
Validates English language output for CV templates

and 17 more in the full report

11 fixed4 passed either way7 still failing0 broke

Pass-rate lift: +50 pp
Tokens: +29%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 9/9/2026v215 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/huangwb8-make-latex-model/SKILL.md https://app.decimal.ai/s/huangwb8-make-latex-model/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add huangwb8-make-latex-model, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/huangwb8-make-latex-model/ and pins it in .decimal/skills.lock

decimalai skills add huangwb8-make-latex-model

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/huangwb8-make-latex-model/SKILL.md https://app.decimal.ai/s/huangwb8-make-latex-model/SKILL.md

Raw file: /s/huangwb8-make-latex-model/SKILL.md ↗ · machine-readable summary at /s/huangwb8-make-latex-model.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

I am updating the curriculum vitae template under `projects/cv-academic`. The prompt asks to adjust line heights for entry items. What build target outputs must be verified during testing?

What was checked, without and with the skill
Checked	Without skill	With skill
Validates Chinese language output for CV templates	Missed	Passed
Validates English language output for CV templates	Missed	Passed
Runs official build verification using cv_project_tool.py	Missed	Passed

case-08 · gemini-3.6-flash · 9/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md123 lines32 filesincludes scripts

ChineseResearchLaTeX 模板落地与高保真对齐器

让 ChineseResearchLaTeX 中的目标项目按当前真实架构落成高质量模板。
先判断该改 projects/* 还是 packages/bensz-*。
若必须改公共包，先做回归计划，再跑受影响模板的官方验证。
验收始终以各产品线官方构建入口为准。

适用任务

把某个项目对齐到官方 PDF、Word 导出 PDF 或既有 baseline
判断问题属于项目层差异还是共享样式/共享脚本
做像素级 PDF 比对、标题对齐、参数抽取
新增或重构 NSFC / paper / thesis / cv 模板

流程

输入

按用户请求和配置文件提供必要输入；缺失信息应明确列出并停止依赖该输入的步骤。

执行步骤

当用户环境中出现因本 skill 设计缺陷导致的 bug 时，优先使用 bensz-collect-bugs 按规范记录到 ~/.bensz-skills/bugs/，严禁直接修改用户本地 Claude Code / Codex 中已安装的 skill 源码。
若 AI 仍可通过 workaround 继续完成用户任务，应先记录 bug，再继续完成当前任务。
当用户明确要求“report bensz skills bugs”等公开上报动作时，调用本地 gh 与 bensz-collect-bugs，仅上传新增 bug 到 huangwb8/bensz-bugs；不要 pull / clone 整个 bug 仓库。
产品线标准：docs/for-developers/*-template-standard.md
本 skill 工作流：docs/WORKFLOW.md
产品线识别：references/PRODUCT_LINE_RULES.md
脚本职责：references/SCRIPT_SCOPE.md
工具说明：scripts/README.md
基线准备：docs/BASELINE_GUIDE.md

判断验收口径

用户要“像某份 PDF/Word 一样”
还是“按当前仓库标准做成好模板”
还是“新增一套模板能力”

判断修改层级

Track record

Benchmark

13 / 19

test cases passed, vs 3 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/9/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

huangwb8 / chineseresearchlatex

skills/make-latex-model/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v2Bundled 31 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

ChineseResearchLaTeX 模板落地与高保真对齐器

适用任务

流程

输入

执行步骤

判断验收口径

判断修改层级

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills