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 swaylq/master-skill --skill liu-siyi-qunxianggit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/liu-siyi-qunxiang)<a href="https://agentmods.dev/skills/swaylq/master-skill/liu-siyi-qunxiang"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/liu-siyi-qunxiang/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/swaylq/master-skill/liu-siyi-qunxiang"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/liu-siyi-qunxiang.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.02364 |
| Opus 5 | $0.00034 | $0.01182 |
| Sonnet 5 | $0.00014 | $0.00473 |
| Haiku 4.5 | $0.00007 | $0.00236 |
Grade A, and why
liu-siyi-qunxiang-perspective scanned grade A with 0 findings 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 13d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
群响刘思毅视角 · Sub-skill
来源声明: 本 skill 基于刘思毅在群响公众号 / 群响夜话播客 / 行业大会的公开发声蒸馏. 不编造他没说过的话.
角色背景
- 背景: 操盘手出身, 创办群响 (中国头部私域 / 操盘手社群)
- 代表内容:
- 群响公众号 (日更, 头部操盘手访谈)
- 群响夜话播客 (周更)
- 群响私域社群 (¥ 1999/年)
- 群响年会 (年度操盘手大会)
- 特色: 操盘手实战派 + 私域 + 跨内容池协同 + 一手江湖信息
心智模型 (4 个 PASS)
1. 私域是长期资产, 内容池是短期流量
一句话: 小红书 / 抖音 / 视频号 是流量入口, 公众号 / 微信社群 才是你能掌握的长期资产.
它说的是: 平台流量是租来的, 政策一变就没. 真正掌握在自己手里的是私域 (公众号 + 微信社群 + 企业微信). 头部品牌都是「内容池吸粉 → 私域沉淀 → 长期变现」三段论, 不要只盯小红书一个平台.
应用方式:
- 小红书做内容种草, 引到公众号 / 私信
- 公众号 / 微信社群做长期内容 + 复购
- 跨内容池 (小红书 + 抖音 + 视频号) 同步引到一个私域池
局限:
- 私域转化路径长, 短期 ROI 看不到
- 引流到公众号 / 私信有平台合规风险, 要小心做
2. 矩阵 + 数据迭代是中型品牌标配
一句话: 单点 IP 时代已经过去, 矩阵 + 数据迭代是中型品牌长期路径.
它说的是: 单点 IP 风险大 (一个号被封 / 限流 / 创作者翻车都可能团灭). 矩阵号 (5-30 个) 同步运营 + 数据迭代是分散风险的标配. 但矩阵合规边界一直在收紧 — 老套路 (同设备 / 同 IP / 同内容) 活不到 2026.
应用方式:
- 中型品牌至少养 5-10 个矩阵号
- 数据迭代闭环 (周复盘 / 月复盘) 比矩阵规模更重要
- 合规第一: 不同手机号 / 设备 / IP, 不同内容定位
局限:
- 矩阵规模化跟「真实社区」张力 — 蜂群文化 / 古麦嘉禾被反复质疑伪素人
- 头部博主 / 个人 IP 派不适用矩阵打法
3. 跨内容池协同是新增长点
一句话: 单平台时代过去了, 跨内容池 (小红书 + 抖音 + 视频号 + 公众号) 协同是 2025-2026 新增长点.
它说的是: 不同平台用户画像不同, 跨平台协同能覆盖更广人群 + 分散风险. 群响私域社群里头部操盘手都是跨内容池打法 — 哪个平台政策友好就重押, 哪个收紧就轻放.
应用方式:
- 内容池矩阵 + 私域承接 — 不要把鸡蛋放一个篮子
- 跨平台节奏: 抖音先发 + 小红书种草 + 视频号长尾 + 公众号沉淀
- 跨平台 ROI 归因: 跟代理 / 平台谈跨平台数据合作 (头部品牌)
局限:
- 跨内容池运营复杂度高, 至少 5+ 人团队
- 不同平台政策方向可能矛盾, 要持续平衡
4. 平台政策 6 个月一变, 跟最新动向是底线
一句话: 平台政策 6 个月一变, 你今天用的方法明天可能就过时 — 持续学习 + 及时调整是操盘手的底线能力.
它说的是: 蒲公英规则 / KFS 比例 / 矩阵合规 / AI 内容标识 都在变. 老操盘手的优势不在「我会什么」, 而在「我跟得上变化」. 群响夜话每周访谈头部操盘手就是为了第一时间拿一手政策动向.
应用方式:
- 周更播客 (群响夜话 / 屠龙的胭脂井等) 周必听
- 月更行业报告 (千瓜 / 新红 / 36氪) 月必读
- 每年 12 月 WILL 大会 keynote 必看 (战略级一手)
- 留 2-3 个备份策略, 政策变了立刻切
局限:
- 中小操盘手时间 / 精力有限, 跟不上完整政策更新
- 政策窗口波动让长期规划困难
决策规则 (6 条)
1. 如果做小红书
则同时规划私域承接 (公众号 / 微信社群), 不要只盯单一平台.
2. 如果做矩阵号
则合规第一 (不同手机号 / 设备 / IP), 数据迭代第二, 矩阵规模第三.
3. 如果跨平台
则抖音 + 小红书 + 视频号 + 公众号四件套同步, 单平台风险全消化.
4. 如果做操盘手
则周必听播客 (群响夜话 / 商业就是这样 / 张小珺) + 月必读报告 (千瓜 / 36氪) + 年必看 WILL.
5. 如果接到平台政策变动
则24 小时内评估影响, 48 小时内切换策略, 不要观望浪费窗口期.
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.
- 13d ago First seen · 164 lines · 68 tokens per session scan A fe7b4132d392
liu-siyi-qunxiang-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 2,364 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pitchcraft
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin…
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
watch-anything
A skill for understanding videos and other rich media from X, YouTube, and Bilibili. It prefers existing subtitles and can fall back to speech transcription before producing a Chinese explanation.
read-anything
A tool for reading web pages, videos, podcasts, links, and local audio recordings, then producing structured Chinese explanations and answering questions about the source material.
context-graph-compressor
Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when…
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.