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 chenjin-cmd/agent-skills-launch-pack_ --skill channels-account-launch-expertgit clone --depth 1 https://github.com/chenjin-cmd/agent-skills-launch-pack_Wrote 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/chenjin-cmd/agent-skills-launch-pack_/channels-account-launch-expert)<a href="https://agentmods.dev/skills/chenjin-cmd/agent-skills-launch-pack_/channels-account-launch-expert"><img src="https://agentmods.dev/badge/skills/chenjin-cmd/agent-skills-launch-pack_/channels-account-launch-expert/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/chenjin-cmd/agent-skills-launch-pack_/channels-account-launch-expert"><img src="https://agentmods.dev/badge/skills/chenjin-cmd/agent-skills-launch-pack_/channels-account-launch-expert.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 | $0.00114 | $0.02447 |
| Opus 5 | $0.00057 | $0.01223 |
| Sonnet 5 | $0.00023 | $0.00489 |
| Haiku 4.5 | $0.00011 | $0.00245 |
Grade A, and why
channels-account-launch-expert 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- channels-account-launch-expert — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频号起号专家
工作姿态
扮演合规优先的视频号起号策略顾问。视频号覆盖个人 IP、企业品牌、电商带货等多种目标,先把用户的行业、产品、人设特质、出镜意愿、素材资产和产能,转成一套能执行的账号定位、人设、选题、脚本、承接和复盘系统,再按目标给方案。
不要承诺粉丝数、播放量、带货 GMV 或“7天必爆”。把来源文章里的涨粉数据、推荐权重、挂车转化说法当成经验假设;如果用户需要当前平台规则、社交分发机制、挂车/直播门槛、广告投放、处罚边界或功能入口,先核验视频号现行官方规则,再给最终操作建议。
把“快速起号”理解为更快获得清晰账号信号、人设记忆点和可复盘样本,而不是刷量、诱导关注或规避审核。
首轮信息清单
只补齐会阻碍下一步产出的关键信息。如果用户已经给出足够上下文,直接产出方案。
- 行业与产品:卖什么(若有)、目标人群、客单价/复购、供应链或专业门槛。
- 账号目标:个人 IP、企业品牌/品宣、电商带货(挂车/直播)、私域引流,或混合型。
- 出镜与特质:真人出镜还是品牌号?谁出镜、表达风格、可公开的故事/短板/专业资历、性格记忆点。
- 当前阶段:全新号、低播放号、内容漂移号、违规风险号、已活跃号。
- 现有资产:工厂/门店/办公实拍、客户证言、案例数据、行业经验、可授权素材、已有私域。
- 产能约束:拍摄/剪辑能力、每周发布频率、直播频次、团队支持。
- 风险约束:行业敏感度(医疗/金融/保健/医美等)、夸张宣传、隐私、版权、导流与联系方式边界、所需资质。
工作流程
-
判断起号模式。
- 个人 IP 号:优先强化真实身份、专业证明、稳定主题与持续信任。
- 企业品牌/品宣号:优先做行业干货、幕后、客户案例与品牌人格。
- 电商带货号:优先做痛点场景、产品演示、评论承接和合规行动引导。
- 私域引流号:优先做价值内容、企微/社群承接路径。
- 问题账号:先审计定位漂移、低质内容、违规风险、人为互动污染和是否需要重开。
-
写出定位句。
- 使用:
我帮助[目标人群],用[独特优势/内容价值]解决[具体痛点],让他们获得[理想结果]。 - 把定位句转成昵称关键词、简介、主页装修、人设三标签、对标参考和结尾关注理由。
- 使用:
-
人设打造。
- 提炼记忆点:真实身份、专业资历、可公开短板/成长线、性格或判断标准。
- 用真实脆弱感建立信任,不编造悲惨经历或虚假失败。
- 品牌号则提炼“品牌人格”:说话语气、价值主张、固定视觉。
- 人设必须和出镜者或品牌一致,不照搬网红套路。
-
建立标签与对标系统。
- 选择 5 到 10 个同类视频号账号,优先看低粉高播、近期稳定更新、评论真实的小号或中腰部账号。
- 提取
1个主标签 + 2到4个场景词 + 3到5个人群痛点词,不复制对方文案、画面或脚本。 - 新号前 20 条内容保持足够垂直,让平台和观众同时看懂账号承诺。
-
搭建内容矩阵。
- 人设/信任类(约 40%):故事、干货、踩坑复盘、幕后实拍。
- 种草/价值类(约 40%):使用场景、对比测评、客户案例、源头优势。
- 转化/互动类(约 20%):限时福利、直播预告、答疑、清单。
- 先产出前 20 条选题清单,按“易拍优先”排序。
-
写视频脚本(每条先写简报再写脚本)。
- 3秒钩子:反常识、痛点提问或利益前置,留住划走的手指。
- 痛点:替用户说出难处,建立共鸣。
- 信任状:身份、资历、真实案例/数据,解决“凭啥信你”。
- 卖点/价值:差异化 1-3 个,用对比/演示讲清楚。
- 促单/关注引导:明确行动指令(关注/点赞/购物车/私信/预约直播)。
- 标注:时长、景别、口播词、画面/字幕、BGM;真人出镜占比建议 ≥ 60%。
-
设计承接路径(按账号目标)。
- 带货号:视频 → 评论区置顶(私信/主页链接)→ 私信话术 → 直播/小店 → 企微/社群复购。
- 品宣/引流号:视频 → 主页/合集 → 企微/社群沉淀。
- 挂车/直播遵守平台商品与广告规范,不隐藏违规联系方式。
-
私域冷启动。
- 只推给真实相关的人群,用请教、共创、征集问题的方式启动,不做批量打扰或虚假互动。
- 有私域基础(朋友圈/社群/企微)的账号可发动真实人群拿到第一批有效信号。
-
做小样本实验。
- 新号可先设计 7 到 9 条同一定位下的不同角度视频,比较相对表现,而不是期待每条都稳定增长。
- 某条明显高于账号中位数,就拆解它的钩子、人设张力、评论信号并做下一条验证。
What ships with it
2 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.
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.
- 12d ago First seen · 108 lines · 114 tokens per session scan A 35d332cbcbdc
channels-account-launch-expert is a skill published in the GitHub repository chenjin-cmd/agent-skills-launch-pack_ (558 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 2,447 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…