Ready to supercharge your AI agents?

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

Cjc Supplementary · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Cjc Supplementary

brycewang-stanford/cjc-supplementary

Source brycewang-stanford/awesome-journal-skills ↗License MIT

在为投向《计算机学报》(Chinese Journal of Computers, CJC) 的长文组织附录、补充材料与多媒体附件时调用。覆盖如何在正文长文与补充材料之间按"是否决定录用"划分内容、附录中放证明细节/额外实验/参数表/算法伪码/大图表的取舍原则、补充材料的引用与自洽要求、多媒体附件的格式与容量、以及在双盲外审下补充材料的匿名处理。适用于让一篇计算机全学科中文原创长文主体紧凑有力、支撑材料完备可查的场景。

SkillScore88Maintained

Automatic

Writing & Editing pack

Last verified 8/31/2026

What it changes

Passed 22 of 25 test cases with the skill, and 12 of 25 without it.

Without skill48%

With skill88%

Checks it passed that the model alone missed

The output includes the line tag '[划分]'.
The output includes the line tag '[多媒体]'.
The response includes the line tag '[指引]'.

and 12 more in the full report

12 fixed10 passed either way1 still failing2 broke

Pass-rate lift: +40 pp
Tokens: +63%
Agent turns: 0%
Response time: -1%

Model gemini-3.6-flashMeasured 8/31/2026v122 of 25 cases passed with skill

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/brycewang-stanford-cjc-supplementary/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cjc-supplementary/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-cjc-supplementary, 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/brycewang-stanford-cjc-supplementary/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-cjc-supplementary

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

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cjc-supplementary/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cjc-supplementary/SKILL.md

Raw file: /s/brycewang-stanford-cjc-supplementary/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-cjc-supplementary.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

我们针对《计算机学报》撰写了一篇算法论文。正文中给出了核心算法框架图和核心逻辑步。同时，我们写了一个 120 行包含全部初始化、异常处理和边界条件判定的完整算法伪代码。完整伪代码应该放在正文还是附录？

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies keeping the core algorithm framework in the main text.	Passed	Passed
The response assigns the complete 120-line pseudocode implementation to Appendix C.	Missed	Passed

case-12 · gemini-3.6-flash · 8/31/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md120 linessingle file

《计算机学报》附录与补充材料

《计算机学报》(Chinese Journal of Computers, CJC) 以长文见长，容量比会议短文宽裕，因此很多在会议里被迫外置的内容（完整证明、额外实验、大参数表、算法伪码）在 CJC 可以放进正文。但长文也不是无限长，需要在正文与附录/补充材料之间做有纪律的取舍。核心判据只有一条：任何决定稿件能否录用的内容，都必须留在外审专家一定会读的正文里；只有"支撑性、可查阅、非决定性"的内容才外置。本技能给出面向 CJC 的划分方法。核验日期 2026-07-09，补充材料接收方式等以编辑部为准，未确认项标 待核实。

一、划分总原则：按"决定性"分层

内容	归属	理由
核心方法、主定理与关键证明思路	正文	决定贡献成立与否
主实验结果与主要对比	正文	决定结论可信度
威胁有效性/局限性讨论	正文	决定结论边界
冗长证明的完整推导细节	附录	支撑但不改变主结论
额外数据集/消融的完整表格	附录/补充	增强但非决定性
超参数全表、实现细节、环境配置	附录/补充	可查阅性内容
演示视频、交互界面、大规模原始数据	多媒体附件	无法印刷承载

判断口诀："专家要靠它判录用 → 正文；专家想核对才翻 → 附录/补充。"

二、CJC 长文语境下的特别提示

因为是长文，不要滥用外置把本该在正文讲清的方法赶进附录，否则正文空洞、外审看不到贡献全貌。
反过来，也不要把几十页原始表格塞进正文淹没主线；用代表性结果进正文 + 完整表进附录。
附录应服务于正文：正文中在需要处明确指引"详细推导见附录 A""完整结果见附录表 B"。

三、附录组织

按主题分节编号（附录 A、附录 B……），每节有明确标题与用途。
证明附录：给出正文中略去的完整推导，命题/引理编号与正文一致，便于比对。
实验附录：额外数据集、更多基线、完整消融、失败案例分析；表图编号延续正文体系。
实现附录：算法伪码全版、超参数表、系统参数、环境依赖清单。

四、补充材料与多媒体附件

补充材料应能被引用且自洽：读者/审稿人无需口头解释即可理解其内容与用途。
多媒体附件（视频、动画、交互演示、可执行样例）注明格式、容量与播放/运行方式；具体接收方式与

Track record

Benchmark

22 / 25

test cases passed, vs 12 / 25 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 v4 — 8/10/2026

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

brycewang-stanford / awesome-journal-skills

Chinese-Journal-of-Computers-Skills/skills/cjc-supplementary/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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