Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add redfox-data/redfox-community-dsh --skill wechat-creatorgit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/redfox-data/redfox-community-dsh/wechat-creator)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/wechat-creator"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/wechat-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/wechat-creator"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/wechat-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00187 | $0.10734 |
| Opus 5 | $0.00093 | $0.05367 |
| Sonnet 5 | $0.00037 | $0.02147 |
| Haiku 4.5 | $0.00019 | $0.01073 |
Grade A, and why
wechat-creator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> M1 脚本使用 Python 标准库（urllib.request），无需额外安装；M5 违禁词检测需要 python-docx / beautifulsoup4 / playwright；M6/M7 仅需 requests。 How it starts
The opening of the file, as written. The whole thing — 827 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号内容工坊
1. 简介
公众号内容工坊 —— 一个入口覆盖公众号创作与运营全链路：10w+ 爆文榜单 / 爆款正文创作 / 标题生成+评分 / 文案改写 / 违禁词检测 / 封面设计 / 账号诊断。
基于红狐数据每日持续收录的 1000+ 条 10w+ 爆文与全网公众号爆款数据，把灵感打磨成可直接发布的成品：
| # | 能力 | 一句话说明 |
|---|---|---|
| 1 | 10w+ 爆文榜单 | 全领域或 23 个分类查询每日 10w+ 阅读 TOP50，附四维度内容分析 + HTML 报告 |
| 2 | 爆款正文创作 | 关键词检索爆款 → 提炼流量密码 → 融合风格样本 → 生成可直接发布的完整文章 |
| 3 | 标题生成+评分 | 生成 10 个爆款标题，或对已有标题做四维百分制量化评分 |
| 4 | 文案改写 | 任意素材一键转为公众号爆款风格，自动上报改写记录（免费不扣积分） |
| 5 | 违禁词检测 | 文案 / 文件 / 图片 / 网页四端输入，风险分级标注+替换建议+安全版本 |
| 6 | 封面设计 | AI 分析同赛道爆款封面视觉规律，输出 3 套 2.35:1 横版设计方案 + HTML 报告 |
| 7 | 账号诊断 | 四维度 100 分制评分 + S/A/B/C/D/E 六级评级 + 行业对标 + 多账号对比 |
适用对象：公众号运营者、内容创作者、自媒体编辑、品牌方、MCN 机构、爆文研究者。
2. 功能路由（Agent 先识别意图再进对应模块）
⚠️ 进入具体执行前，Agent 必须先根据下表识别用户意图并路由到对应模块，禁止跨模块混用。
| 用户意图（关键词/示例） | 进入模块 | 必读参考 |
|---|---|---|
| "10w+ 爆文"、"公众号爆文榜单"、"今日爆文"、"科技数码赛道爆文" | M1 10w+ 爆文榜单 | references/m1_category_mapping.md |
| "写一篇公众号文章"、"生成公众号文案"、"关于 XX 的文章" | M2 爆款正文创作 | references/m2_gzh_trend_data_format.md |
| "帮我起公众号标题"、"生成爆款标题"、"关于 XX 的标题" | M3-A 标题生成 | 本文件 §6.2 |
| "这个标题打分"、"评估标题"、"哪个标题好" | M3-B 标题评分 | 本文件 §6.3 |
| "改写成公众号风格"、"这篇文案帮我公众号化" | M4 文案改写 | assets/m4_platform_rules.md |
| "有没有违禁词"、"检测敏感词"、"公众号合规"、"限流词" | M5 违禁词检测 | references/m5_prohibited_word_core_workflow.md |
| "设计公众号封面"、"做个推文封面"、"美妆/财经封面" | M6 封面设计 | references/m6_report_template.md |
| "诊断 XX 公众号"、"分析 XX 账号"、"对比诊断 A 和 B" | M7 账号诊断 | references/m7_core_workflow.md |
复合意图（如"写完文章顺便检测违禁词"）：按模块顺序串行执行，每模块独立输出。
仅询问功能（如"你能做什么"、"怎么用"）：只介绍能力清单，不进入任何模块执行。
3. 全局规则（所有模块共享）
3.1 鉴权（REDFOX_API_KEY）
所有模块共用同一个 API Key。
获取方式：
配置方式（按优先级从高到低）：
| 优先级 | 来源 | 说明 |
|---|---|---|
| 1 | 环境变量 REDFOX_API_KEY |
直接读取当前进程环境变量 |
| 2 | Shell 配置文件 | 自动扫描 ~/.zshrc ~/.bashrc ~/.bash_profile ~/.profile ~/.zprofile |
| 3 | 提示用户配置 | 以上都找不到时，引导用户配置 |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/m4_platform_rules.md 3.8 KB
- assets/m7_report_template.html 12 KB
- README.en.md 6.6 KB
- README.md 5.5 KB
- references/m1_api_spec.md 3.9 KB
- references/m1_category_mapping.md 4.5 KB
- references/m2_gzh_trend_data_format.md 4.9 KB
- references/m5_prohibited_word_core_workflow.md 15 KB
- references/m6_gzh_trend_data_format.md 4.1 KB
- references/m6_report_template.html 8.0 KB
- references/m6_report_template.md 4.1 KB
- references/m7_core_workflow.md 16 KB
- references/m7_workflow_guide.md 18 KB
- scripts/check_sensitive_words.py 13 KB runs code
- scripts/fetch_explosive_covers.py 12 KB runs code
- scripts/fetch_gzh_trends.py 12 KB runs code
- scripts/fetch_hot_articles.py 18 KB runs code
- scripts/fetch_official_account_trends.py 13 KB runs code
- scripts/generate_hot_html.py 19 KB runs code
- scripts/rewrite.py 8.1 KB runs code
- scripts/wechat_analyzer.py 73 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 827 lines · 187 tokens per session scan A e3a7c19da067
wechat-creator is a skill published in the GitHub repository redfox-data/redfox-community-dsh (5 stars, last pushed yesterday), licensed MIT. It adds 187 tokens to every session and 10,734 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
web-artifact-designer
A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.
dsh-sdk-upgrade
Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout — including syncing the project's declared DSH host-version floor…
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…