Ready to supercharge your AI agents?

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

Get Started Free →

Style Modeler · dongbeixiaohuo | DecimalAI

marketingby dongbeixiaohuo

Style Modeler

dongbeixiaohuo/style-modeler

Source dongbeixiaohuo/writing-agent ↗License MIT

从同一作者或公众号的文章样本中建立、验证或增量更新可复用的写作风格档案。用户要求风格建模、提取写作配方、解构文章、学习作者风格、创建或更新风格库时调用；如果用户只要求直接写文章而不需要建立风格档案，不调用本 skill。

SkillScore36Maintained

Automatic

Writing & Editing pack

Last verified 8/21/2026

What it changes

Passed 5 of 15 test cases with the skill, and 3 of 15 without it.

Without skill23%

With skill36%

Checks it passed that the model alone missed

Returns the profile for core style adjustment when the imitation score is below 8 points.
Rejects validation passage when key rhythm metrics deviate from sample baselines by more than 30%.
Executes manage_style_registry.py verify with profile, evidence, and --blind-test-passed parameters.

and 2 more in the full report

5 fixed3 passed either way12 still failing2 broke

Pass-rate lift: +14 pp
Tokens: +55%
Agent turns: 0%
Response time: -48%

Model gemini-3.6-flashMeasured 8/21/2026v28 of 22 cases passed with skill · 15 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/dongbeixiaohuo-style-modeler/SKILL.md https://app.decimal.ai/s/dongbeixiaohuo-style-modeler/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add dongbeixiaohuo-style-modeler, 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/dongbeixiaohuo-style-modeler/ and pins it in .decimal/skills.lock

decimalai skills add dongbeixiaohuo-style-modeler

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

curl -fsSL --create-dirs -o .claude/skills/dongbeixiaohuo-style-modeler/SKILL.md https://app.decimal.ai/s/dongbeixiaohuo-style-modeler/SKILL.md

Raw file: /s/dongbeixiaohuo-style-modeler/SKILL.md ↗ · machine-readable summary at /s/dongbeixiaohuo-style-modeler.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

All evidence ledgers are saved, imitation testing scored 9/10, and 3-set blind testing passed for profile `Jia.md`. Execute the command to elevate its registry status.

What was checked, without and with the skill
Checked	Without skill	With skill
Executes manage_style_registry.py verify with profile, evidence, and --blind-test-passed parameters.	Missed	Passed

case-22 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md155 lines7 filesincludes scripts

风格建模专家

只根据用户提供或明确允许获取的样本建模。把作者身份用于样本分组和风格库检索，不把外部履历、既有印象或样本之外的观点写进风格档案。

0. 解析可写风格根目录

开始前必须执行：

python "${CLAUDE_SKILL_DIR}/scripts/manage_style_registry.py" resolve-root --workspace-root "."

把命令唯一输出记录为 [风格根目录]，后续档案、证据和登记表全部使用这个根目录：

在本仓库开发环境中返回 claude-runtime/styles，它是唯一源；完成后再运行同步脚本更新消费端镜像。
在插件安装到普通工作区时返回 .claude/styles，不得写入插件缓存。
禁止跳过解析后直接假定 .claude/styles，否则会造成运行时镜像漂移。

1. 收集样本并确认作者锚点

接收本地文档或 URL。URL 先调用 web-article-extractor，将正文保存到 docs/YYYY-MM-DD-文章标题.md。
批量 URL 按“导航 → 等待 → 提取 → 保存”的顺序串行处理；不要在同一页面上下文并发导航。
从每篇样本的作者、公众号和来源 URL 提取作者锚点。
在合并文本前核对全部锚点：
- 作者锚点一致：继续建模。
- 作者锚点不一致：按作者分组；无法可靠分组时停下，请用户确认是否真的要建立“混合风格”。
- 作者未知：保留来源标识，不猜测作者。
检索 [风格根目录]/：新作者新建档案；已存在的作者读取旧档案和旧证据账本，执行增量验证。

2. 先建立证据账本

在任何风格归纳前，将证据保存到 [风格根目录]/_evidence/[风格名]_evidence.md。每条记录包含：

字段	要求
观察现象	样本中具体出现的写法
原文证据	支撑判断的必要短摘录
出现位置	样本标题、编号或 URL
功能判断	该写法在上下文中的作用
可复用规则	如何在新主题中复现

Track record

Benchmark

5 / 15

test cases passed, vs 3 / 15 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 — 8/17/2026

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

dongbeixiaohuo / writing-agent

.claude/skills/style-modeler/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v2Bundled 6 files · scripts

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