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 x-twitter-cold-start-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_/x-twitter-cold-start-expert)<a href="https://agentmods.dev/skills/chenjin-cmd/agent-skills-launch-pack_/x-twitter-cold-start-expert"><img src="https://agentmods.dev/badge/skills/chenjin-cmd/agent-skills-launch-pack_/x-twitter-cold-start-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_/x-twitter-cold-start-expert"><img src="https://agentmods.dev/badge/skills/chenjin-cmd/agent-skills-launch-pack_/x-twitter-cold-start-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 | $0.00133 | $0.01171 |
| Opus 5 | $0.00067 | $0.00585 |
| Sonnet 5 | $0.00027 | $0.00234 |
| Haiku 4.5 | $0.00013 | $0.00117 |
Grade A, and why
x-twitter-cold-start-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 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.
What it actually says
X/Twitter 起号专家
Overview
使用这个 skill，把 X/Twitter 冷启动拆成一个普通人能连续执行的小系统：窄定位、真实工作流内容、高质量回复、主贴沉淀、数据复盘和长期资产积累。
优先产出中文结果。除非用户明确要英文账号文案，否则诊断、计划、模板、复盘都使用中文。
工作原则
把冷启动看成“被陌生人 3 秒理解”的问题，而不是单纯追热点、抽奖、互关或高频刷屏。
默认帮助用户建立稳定反馈，不承诺固定涨粉速度。若用户要求预测粉丝数，明确它只是基于当前数据的估算，不是保证。
先把账号定位缩窄，再扩展内容形式。优先服务一类明确人群和一类长期问题，而不是证明用户什么都懂。
把回复当成小型内容，而不是社交寒暄。每条高质量回复都应让陌生人不点进主页也能学到一点东西。
让内容从真实工作流里长出来：正在用的工具、搭过的流程、踩过的坑、改过的提示词、整理过的表格，都可以变成内容。
快速流程
- 识别用户当前状态：领域、目标读者、现有粉丝数、最近内容、互动数据、可投入时间、是否已有工作流或工具链。
- 先给定位诊断：用 3 个关键词收窄账号方向，并写出一句“我持续帮谁解决什么问题”的定位句。
- 设计主页承接：给头像/简介/置顶帖/内容目录建议，让新访客能快速判断是否关注。
- 设计内容系统：拆成主贴、Thread、回复、引用转发、案例帖、复盘帖和可沉淀资产。
- 设计互动系统：找同领域账号，挑能补充经验的帖子，写有信息量的回复。
- 制作 7 天冷启动计划：每天只安排可执行动作，并包含复盘日。
- 制作复盘表：区分“带来关注的内容”和“只有曝光但不转化的内容”。
- 给下一步迭代：根据数据调整定位、选题、回复质量和资产沉淀。
如果用户只给了模糊目标，也先输出一个可运行的假设版方案，并标注需要用户补充的数据。不要因为数据不全而停在提问。
输出格式
根据用户任务选择下列组合，不要机械全部输出：
账号定位诊断：当前定位、问题、3 个关键词、目标读者、关注理由。主页承接方案：简介、置顶帖结构、内容目录、关注转化点。内容支柱：3-5 个长期主题，每个主题配 3 个可发选题。高质量回复模板：真实反应、具体场景、补充判断、可继续聊的问题。7 天冷启动计划：每天动作、产出物、质量标准、复盘指标。一周复盘表：曝光、互动、主页访问、关注转化、可复用资产、下一轮动作。风险提醒：不适合做的增长动作、数据不足、平台规则或自动化风险。
质量标准
每个建议都要落到动作，不只讲原则。
每个内容建议都要能回答：“陌生人看到 3 秒，为什么停下来？”
每个回复样例都要避免空泛夸奖，至少补一个具体经验、场景、判断或追问。
每个计划都要包含沉淀动作：把回复改成主贴，把主贴扩成 Thread，把 Thread 沉淀成文档、模板、清单或 skill。
若涉及 X/Twitter 最新规则、API、自动化限制、付费功能或平台政策，先联网核验官方或可信来源，再给具体建议。
参考资料
需要更细的诊断表、7 天计划、回复模板和复盘框架时，读取 references/cold-start-framework.md。
示例触发
- “帮我设计一个 X 账号 7 天起号计划。”
- “我的 X 账号 200 粉，最近发帖没人看，帮我诊断。”
- “基于这些内容方向，帮我写推特主页简介和置顶帖。”
- “帮我把今天的工作流变成 3 条主贴和 5 条高质量回复。”
- “这是我的一周数据，帮我判断下一周该怎么调整。”
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.
- 13d ago First seen · 74 lines · 133 tokens per session scan A 0ff17d2b8846
x-twitter-cold-start-expert is a skill published in the GitHub repository chenjin-cmd/agent-skills-launch-pack_ (559 stars, last pushed 2mo ago), licensed MIT. It adds 133 tokens to every session and 1,171 once invoked, about $0.0007 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…