AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Siyu Pyq

skill-maojiebc-majia-siyu-team-siyu-pyq · by maojiebc

私域朋友圈文案生成——输入主题/产品,按内容配比与爆款结构一次出可直接发的整周朋友圈文案(含 emoji + 标签 + 发布时段),并做合规前置扫描。Use this skill when 写朋友圈文案、排朋友圈内容池、企微/私域运营发圈、按节日节点出朋友圈、给门店导购写发圈素材时。

No reviews yet
0 installs
7 views
0.0% view→install

Install

$ agentstack add skill-maojiebc-majia-siyu-team-siyu-pyq

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-maojiebc-majia-siyu-team-siyu-pyq)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
17d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Siyu Pyq? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

朋友圈文案官(siyu-pyq)

这个 skill 干什么

一线私域运营每天最磨人的活:黄金时段要发好几条朋友圈,天天想新文案还不能重样,写到枯竭。这个 skill 输入主题/产品/场景,一次产出可直接复制发布的朋友圈文案——按内容配比排布、套爆款结构、配 emoji 与话题标签、标注建议发布时段,产出前做合规前置扫描

方法论引擎:内容即产品——每条朋友圈当一个有钩子、有承接、可复用的产品来做,不是发一条扔一条。

输入(缺就先问,一次问清)

  • 品牌 / 品类(如:餐饮 · 牛肉火锅)
  • 本次主题或产品(如:新品毛肚上市 / 周末活动 / 节气借势)
  • 目标动作(到店 / 加微领券 / 社群引流 / 单纯养人设)
  • 可给的真实素材(卖点、活动规则、客户评价原文)——见 assets/真实语料-待填.md
  • 要几条 / 排几天

生成流程(SOP)

1. 定配比

默认一周/一批结构:40% 行业干货 · 30% 产品场景 · 20% 生活人设 · 10% 互动福利,硬广不超过 30%。配比与说明见 [references/内容模型-配比与爆款结构.md](references/内容模型-配比与爆款结构.md)。

2. 每条套爆款结构

默认:痛点提问 → 解决方案 → 客户见证/信任状 → 弱行动指令;人设类可用「场景故事 → 价值观」。结构模板库见同一 reference。

3. 出文案

  • 口语、短句、有真实感;emoji 克制(1–3 个/条,不刷屏);结尾配 1–2 个话题标签。
  • 标注建议发布时段(默认 10:00 / 15:00 / 19:00 三黄金时段轮排)。
  • 需要时出 A/B 两版(只换钩子/首句),供原生测试。

4. 合规前置扫描(边写边合规,必做)

产出前对每条跑一遍合规扫描(复用专家团合规词库,单一真源):

echo "你的朋友圈文案" | python3 plugins/siyu-execution/skills/siyu-pyq/scripts/pyq_lint.py -
  • 命中封号动作 / 广告法绝对化用词(诱导分享、最、第一、100%、包治…)→ 就地改写,不交带红线的文案。
  • 餐饮特有:产地 / 工艺 / 功效表述别越界,见 [references/合规前置扫描.md](references/合规前置扫描.md)。

5. 三句话自检(内置质检,用户无感)

  • 内容即产品:这条有钩子吗?用户愿意看/存/转,还是自嗨硬广?
  • 私域即公关:语气是平等的朋友,还是居高临下推销?
  • 运营即广告:这次触达值不值这个曝光?(不刷屏、不浪费额度)

输出格式

按天/条给一张表:发布时段 | 分类(干货/产品/人设/福利) | 文案正文 | 标签 | [A/B版],末尾附「合规扫描:通过 / 改写记录」。

马甲护城河注入点

优先查询私有原子库:python3 tools/atoms_query.py --skills siyu-pyq。再用 [assets/真实语料-待填.md](assets/真实语料-待填.md) 补充本次真实卖点、客户见证和活动规则。输出由此从「行业通用层」变成「懂本品、能转化」。

> 未接真实语料时用占位示例,产物顶部标注「⚠️ 未接真实语料,当前为通用示例」。

收尾时如果已形成可复用结论,提示一次:「有结论想留下,输入 /siyu-save。」一次对话最多提示一次。


不知道下一步用哪个 skill?

输入 /siyu

这是私域工具箱的导航入口。它会读取刚才的具体结论,选择当前最值得处理的一个方向, 并直接路由到对应 skill。迷路了就回 /siyu

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.